Update version to 0.1.118 (#3505)

Signed-off-by: Andrew Carbonetto <andrew.carbonetto@improving.com>
Co-authored-by: Siddhartha Sahu <dev@sdht.in>

.github/workflows/cd.yml

@@ -18,20 +18,17 @@ jobs:
         with:
           python-version: '3.11'
 
-      - name: Install Poetry
+      - name: Install Hatch
         run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-          echo "$HOME/.local/bin" >> $GITHUB_PATH
+          pip install hatch
 
       - name: Install dependencies
         run: |
-          cd mem0
-          poetry install
+          hatch env create
 
       - name: Build a binary wheel and a source tarball
         run: |
-          cd mem0
-          poetry build
+          hatch build --clean
 
       # TODO: Needs to setup mem0 repo on Test PyPI
       # - name: Publish distribution 📦 to Test PyPI

.github/workflows/ci.yml

@@ -37,28 +37,31 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11"]
+        python-version: ["3.10", "3.11", "3.12"]
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install poetry
-        uses: snok/install-poetry@v1
-        with:
-          version: 1.4.2
-          virtualenvs-create: true
-          virtualenvs-in-project: true
+      - name: Install Hatch
+        run: pip install hatch
       - name: Load cached venv
-        id: cached-poetry-dependencies
+        id: cached-hatch-dependencies
         uses: actions/cache@v3
         with:
           path: .venv
-          key: venv-mem0-${{ runner.os }}-${{ hashFiles('**/poetry.lock') }}
+          key: venv-mem0-${{ runner.os }}-${{ hashFiles('**/pyproject.toml') }}
+      - name: Install GEOS Libraries
+        run: sudo apt-get update && sudo apt-get install -y libgeos-dev
       - name: Install dependencies
-        run: make install_all
-        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+        run: |
+          pip install --upgrade pip
+          pip install -e ".[test,graph,vector_stores,llms,extras]"
+          pip install ruff
+        if: steps.cached-hatch-dependencies.outputs.cache-hit != 'true'
+      - name: Run Linting
+        run: make lint
       - name: Run tests and generate coverage report
         run: make test
 
@@ -68,28 +71,28 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.9", "3.10", "3.11"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install poetry
-        uses: snok/install-poetry@v1
-        with:
-          version: 1.4.2
-          virtualenvs-create: true
-          virtualenvs-in-project: true
+      - name: Install Hatch
+        run: pip install hatch
       - name: Load cached venv
-        id: cached-poetry-dependencies
+        id: cached-hatch-dependencies
         uses: actions/cache@v3
         with:
           path: .venv
-          key: venv-embedchain-${{ runner.os }}-${{ hashFiles('**/poetry.lock') }}
+          key: venv-embedchain-${{ runner.os }}-${{ hashFiles('**/pyproject.toml') }}
       - name: Install dependencies
         run: cd embedchain && make install_all
-        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+        if: steps.cached-hatch-dependencies.outputs.cache-hit != 'true'
+      - name: Run Formatting
+        run: |
+          mkdir -p embedchain/.ruff_cache && chmod -R 777 embedchain/.ruff_cache
+          cd embedchain && hatch run format
       - name: Lint with ruff
         run: cd embedchain && make lint
       - name: Run tests and generate coverage report
@@ -99,4 +102,4 @@ jobs:
         with:
           file: coverage.xml
         env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

CONTRIBUTING.md

@@ -16,18 +16,20 @@ To make a contribution, follow these steps:
 For more details about pull requests, please read [GitHub's guides](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request).
 
 
-### 📦 Package manager
+### 📦 Development Environment
 
-We use `poetry` as our package manager. You can install poetry by following the instructions [here](https://python-poetry.org/docs/#installation).
-
-Please DO NOT use pip or conda to install the dependencies. Instead, use poetry:
+We use `hatch` for managing development environments. To set up:
 
 ```bash
-make install_all
+# Activate environment for specific Python version:
+hatch shell dev_py_3_9   # Python 3.9
+hatch shell dev_py_3_10  # Python 3.10  
+hatch shell dev_py_3_11  # Python 3.11
+hatch shell dev_py_3_12  # Python 3.12
 
-#activate
-
-poetry shell
+# The environment will automatically install all dev dependencies
+# Run tests within the activated shell:
+make test
 ```
 
 ### 📌 Pre-commit
@@ -40,16 +42,22 @@ pre-commit install
 
 ### 🧪 Testing
 
-We use `pytest` to test our code. You can run the tests by running the following command:
+We use `pytest` to test our code across multiple Python versions. You can run tests using:
 
 ```bash
-poetry run pytest tests
-
-# or
-
+# Run tests with default Python version
 make test
+
+# Test specific Python versions:
+make test-py-3.9   # Python 3.9 environment
+make test-py-3.10  # Python 3.10 environment
+make test-py-3.11  # Python 3.11 environment
+make test-py-3.12  # Python 3.12 environment
+
+# When using hatch shells, run tests with:
+make test  # After activating a shell with hatch shell test_XX
 ```
 
-Several packages have been removed from Poetry to make the package lighter. Therefore, it is recommended to run `make install_all` to install the remaining packages and ensure all tests pass. Make sure that all tests pass before submitting a pull request.
+Make sure that all tests pass across all supported Python versions before submitting a pull request.
 
-We look forward to your pull requests and can't wait to see your contributions!
+We look forward to your pull requests and can't wait to see your contributions!

Makefile

@@ -8,36 +8,48 @@ PROJECT_NAME := mem0ai
 all: format sort lint
 
 install:
-	poetry install
+	hatch env create
 
 install_all:
-	poetry install
-	poetry run pip install groq together boto3 litellm ollama chromadb weaviate weaviate-client sentence_transformers vertexai \
-	                        google-generativeai elasticsearch opensearch-py vecs pinecone pinecone-text
+	pip install ruff==0.6.9 groq together boto3 litellm ollama chromadb weaviate weaviate-client sentence_transformers vertexai \
+	            google-generativeai elasticsearch opensearch-py vecs "pinecone<7.0.0" pinecone-text faiss-cpu langchain-community \
+							upstash-vector azure-search-documents langchain-memgraph langchain-neo4j langchain-aws rank-bm25 pymochow pymongo psycopg kuzu databricks-sdk valkey
 
 # Format code with ruff
 format:
-	poetry run ruff format mem0/
+	hatch run format
 
 # Sort imports with isort
 sort:
-	poetry run isort mem0/
+	hatch run isort mem0/
 
 # Lint code with ruff
 lint:
-	poetry run ruff check mem0/
+	hatch run lint
 
 docs:
 	cd docs && mintlify dev
 
 build:
-	poetry build
+	hatch build
 
 publish:
-	poetry publish
+	hatch publish
 
 clean:
-	poetry run rm -rf dist
+	rm -rf dist
 
 test:
-	poetry run pytest tests
+	hatch run test
+
+test-py-3.9:
+	hatch run dev_py_3_9:test
+
+test-py-3.10:
+	hatch run dev_py_3_10:test
+
+test-py-3.11:
+	hatch run dev_py_3_11:test
+
+test-py-3.12:
+	hatch run dev_py_3_12:test

README.md

@@ -1,87 +1,101 @@
 <p align="center">
   <a href="https://github.com/mem0ai/mem0">
-  <img src="docs/images/banner-sm.png" width="800px" alt="Mem0 - The Memory Layer for Personalized AI">
+    <img src="docs/images/banner-sm.png" width="800px" alt="Mem0 - The Memory Layer for Personalized AI">
   </a>
+</p>
 <p align="center" style="display: flex; justify-content: center; gap: 20px; align-items: center;">
-  <a href="https://trendshift.io/repositories/11194" target="_blank">
-    <img src="https://trendshift.io/api/badge/repositories/11194" alt="mem0ai%2Fmem0 | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
-  </a>
-  <a href="https://www.ycombinator.com/launches/LpA-mem0-open-source-memory-layer-for-ai-apps" target="_blank">
-    <img alt="Launch YC: Mem0 - Open Source Memory Layer for AI Apps" src="https://www.ycombinator.com/launches/LpA-mem0-open-source-memory-layer-for-ai-apps/upvote_embed.svg"/>
+  <a href="https://trendshift.io/repositories/11194" target="blank">
+    <img src="https://trendshift.io/api/badge/repositories/11194" alt="mem0ai%2Fmem0 | Trendshift" width="250" height="55"/>
   </a>
 </p>
 
-
-  <p align="center">
-    <a href="https://mem0.ai">Learn more</a>
-    ·
-    <a href="https://mem0.dev/DiG">Join Discord</a>
-    ·
-    <a href="https://mem0.dev/demo">Demo</a>
-  </p>
+<p align="center">
+  <a href="https://mem0.ai">Learn more</a>
+  ·
+  <a href="https://mem0.dev/DiG">Join Discord</a>
+  ·
+  <a href="https://mem0.dev/demo">Demo</a>
+  ·
+  <a href="https://mem0.dev/openmemory">OpenMemory</a>
 </p>
 
 <p align="center">
   <a href="https://mem0.dev/DiG">
-    <img src="https://dcbadge.vercel.app/api/server/6PzXDgEjG5?style=flat" alt="Mem0 Discord">
+    <img src="https://img.shields.io/badge/Discord-%235865F2.svg?&logo=discord&logoColor=white" alt="Mem0 Discord">
   </a>
   <a href="https://pepy.tech/project/mem0ai">
-    <img src="https://img.shields.io/pypi/dm/mem0ai" alt="Mem0 PyPI - Downloads" >
+    <img src="https://img.shields.io/pypi/dm/mem0ai" alt="Mem0 PyPI - Downloads">
   </a>
   <a href="https://github.com/mem0ai/mem0">
     <img src="https://img.shields.io/github/commit-activity/m/mem0ai/mem0?style=flat-square" alt="GitHub commit activity">
   </a>
-  <a href="https://pypi.org/project/mem0ai" target="_blank">
-        <img src="https://img.shields.io/pypi/v/mem0ai?color=%2334D058&label=pypi%20package" alt="Package version">
-    </a>
-    <a href="https://www.npmjs.com/package/mem0ai" target="_blank">
-        <img src="https://img.shields.io/npm/v/mem0ai" alt="Npm package">
-    </a>
+  <a href="https://pypi.org/project/mem0ai" target="blank">
+    <img src="https://img.shields.io/pypi/v/mem0ai?color=%2334D058&label=pypi%20package" alt="Package version">
+  </a>
+  <a href="https://www.npmjs.com/package/mem0ai" target="blank">
+    <img src="https://img.shields.io/npm/v/mem0ai" alt="Npm package">
+  </a>
   <a href="https://www.ycombinator.com/companies/mem0">
     <img src="https://img.shields.io/badge/Y%20Combinator-S24-orange?style=flat-square" alt="Y Combinator S24">
   </a>
 </p>
 
+<p align="center">
+  <a href="https://mem0.ai/research"><strong>📄 Building Production-Ready AI Agents with Scalable Long-Term Memory →</strong></a>
+</p>
+<p align="center">
+  <strong>⚡ +26% Accuracy vs. OpenAI Memory • 🚀 91% Faster • 💰 90% Fewer Tokens</strong>
+</p>
+
+##  🔥 Research Highlights
+- **+26% Accuracy** over OpenAI Memory on the LOCOMO benchmark
+- **91% Faster Responses** than full-context, ensuring low-latency at scale
+- **90% Lower Token Usage** than full-context, cutting costs without compromise
+- [Read the full paper](https://mem0.ai/research)
 
 # Introduction
 
-[Mem0](https://mem0.ai) (pronounced as "mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. Mem0 remembers user preferences, adapts to individual needs, and continuously improves over time, making it ideal for customer support chatbots, AI assistants, and autonomous systems.
+[Mem0](https://mem0.ai) ("mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. It remembers user preferences, adapts to individual needs, and continuously learns over time—ideal for customer support chatbots, AI assistants, and autonomous systems.
 
-### Features & Use Cases
+### Key Features & Use Cases
 
-Core Capabilities:
-- **Multi-Level Memory**: User, Session, and AI Agent memory retention with adaptive personalization
-- **Developer-Friendly**: Simple API integration, cross-platform consistency, and hassle-free managed service
+**Core Capabilities:**
+- **Multi-Level Memory**: Seamlessly retains User, Session, and Agent state with adaptive personalization
+- **Developer-Friendly**: Intuitive API, cross-platform SDKs, and a fully managed service option
 
-Applications:
-- **AI Assistants**: Seamless conversations with context and personalization
-- **Learning & Support**: Tailored content recommendations and context-aware customer assistance
-- **Healthcare & Companions**: Patient history tracking and deeper relationship building
-- **Productivity & Gaming**: Streamlined workflows and adaptive environments based on user behavior
+**Applications:**
+- **AI Assistants**: Consistent, context-rich conversations
+- **Customer Support**: Recall past tickets and user history for tailored help
+- **Healthcare**: Track patient preferences and history for personalized care
+- **Productivity & Gaming**: Adaptive workflows and environments based on user behavior
 
-## Get Started
+## 🚀 Quickstart Guide <a name="quickstart"></a>
 
-Get started quickly with [Mem0 Platform](https://app.mem0.ai) - our fully managed solution that provides automatic updates, advanced analytics, enterprise security, and dedicated support. [Create a free account](https://app.mem0.ai) to begin.
+Choose between our hosted platform or self-hosted package:
 
-For complete control, you can self-host Mem0 using our open-source package. See the [Quickstart guide](#quickstart) below to set up your own instance.
+### Hosted Platform
 
-## Quickstart Guide <a name="quickstart"></a>
+Get up and running in minutes with automatic updates, analytics, and enterprise security.
 
-Install the Mem0 package via pip:
+1. Sign up on [Mem0 Platform](https://app.mem0.ai)
+2. Embed the memory layer via SDK or API keys
+
+### Self-Hosted (Open Source)
+
+Install the sdk via pip:
 
 ```bash
 pip install mem0ai
 ```
 
-Install the Mem0 package via npm:
-
+Install sdk via npm:
 ```bash
 npm install mem0ai
 ```
 
 ### Basic Usage
 
-Mem0 requires an LLM to function, with `gpt-4o-mini` from OpenAI as the default. However, it supports a variety of LLMs; for details, refer to our [Supported LLMs documentation](https://docs.mem0.ai/llms).
+Mem0 requires an LLM to function, with `gpt-4o-mini` from OpenAI as the default. However, it supports a variety of LLMs; for details, refer to our [Supported LLMs documentation](https://docs.mem0.ai/components/llms/overview).
 
 First step is to instantiate the memory:
 
@@ -96,7 +110,7 @@ def chat_with_memories(message: str, user_id: str = "default_user") -> str:
     # Retrieve relevant memories
     relevant_memories = memory.search(query=message, user_id=user_id, limit=3)
     memories_str = "\n".join(f"- {entry['memory']}" for entry in relevant_memories["results"])
-    
+
     # Generate Assistant response
     system_prompt = f"You are a helpful AI. Answer the question based on query and memories.\nUser Memories:\n{memories_str}"
     messages = [{"role": "system", "content": system_prompt}, {"role": "user", "content": message}]
@@ -122,68 +136,34 @@ if __name__ == "__main__":
     main()
 ```
 
-See the example for [Node.js](https://docs.mem0.ai/examples/ai_companion_js).
+For detailed integration steps, see the [Quickstart](https://docs.mem0.ai/quickstart) and [API Reference](https://docs.mem0.ai/api-reference).
 
-For more advanced usage and API documentation, visit our [documentation](https://docs.mem0.ai).
+## 🔗 Integrations & Demos
 
-> [!TIP]
-> For a hassle-free experience, try our [hosted platform](https://app.mem0.ai) with automatic updates and enterprise features.
+- **ChatGPT with Memory**: Personalized chat powered by Mem0 ([Live Demo](https://mem0.dev/demo))
+- **Browser Extension**: Store memories across ChatGPT, Perplexity, and Claude ([Chrome Extension](https://chromewebstore.google.com/detail/onihkkbipkfeijkadecaafbgagkhglop?utm_source=item-share-cb))
+- **Langgraph Support**: Build a customer bot with Langgraph + Mem0 ([Guide](https://docs.mem0.ai/integrations/langgraph))
+- **CrewAI Integration**: Tailor CrewAI outputs with Mem0 ([Example](https://docs.mem0.ai/integrations/crewai))
 
-## Demos
+## 📚 Documentation & Support
 
-- Mem0 - ChatGPT with Memory: A personalized AI chat app powered by Mem0 that remembers your preferences, facts, and memories.
+- Full docs: https://docs.mem0.ai
+- Community: [Discord](https://mem0.dev/DiG) · [Twitter](https://x.com/mem0ai)
+- Contact: founders@mem0.ai
 
-[Mem0 - ChatGPT with Memory](https://github.com/user-attachments/assets/cebc4f8e-bdb9-4837-868d-13c5ab7bb433)
+## Citation
 
-Try live [demo](https://mem0.dev/demo/)
+We now have a paper you can cite:
 
-<br/><br/>
+```bibtex
+@article{mem0,
+  title={Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory},
+  author={Chhikara, Prateek and Khant, Dev and Aryan, Saket and Singh, Taranjeet and Yadav, Deshraj},
+  journal={arXiv preprint arXiv:2504.19413},
+  year={2025}
+}
+```
 
-- AI Companion: Experience personalized conversations with an AI that remembers your preferences and past interactions
+## ⚖️ License
 
-[AI Companion Demo](https://github.com/user-attachments/assets/3fc72023-a72c-4593-8be0-3cee3ba744da)
-
-<br/><br/>
-
-- Enhance your AI interactions by storing memories across ChatGPT, Perplexity, and Claude using our browser extension. Get [chrome extension](https://chromewebstore.google.com/detail/mem0/onihkkbipkfeijkadecaafbgagkhglop?hl=en).
-
-
-[Chrome Extension Demo](https://github.com/user-attachments/assets/ca92e40b-c453-4ff6-b25e-739fb18a8650)
-
-<br/><br/>
-
-- Customer support bot using <strong>Langgraph and Mem0</strong>. Get the complete code from [here](https://docs.mem0.ai/integrations/langgraph)
-
-
-[Langgraph: Customer Bot](https://github.com/user-attachments/assets/ca6b482e-7f46-42c8-aa08-f88d1d93a5f4)
-
-<br/><br/>
-
-- Use Mem0 with CrewAI to get personalized results. Full example [here](https://docs.mem0.ai/integrations/crewai)
-
-[CrewAI Demo](https://github.com/user-attachments/assets/69172a79-ccb9-4340-91f1-caa7d2dd4213)
-
-
-
-## Documentation
-
-For detailed usage instructions and API reference, visit our [documentation](https://docs.mem0.ai). You'll find:
-- Complete API reference
-- Integration guides
-- Advanced configuration options
-- Best practices and examples
-- More details about:
-  - Open-source version
-  - [Hosted Mem0 Platform](https://app.mem0.ai)
-
-## Support
-
-Join our community for support and discussions. If you have any questions, feel free to reach out to us using one of the following methods:
-
-- [Join our Discord](https://mem0.dev/DiG)
-- [Follow us on Twitter](https://x.com/mem0ai)
-- [Email founders](mailto:founders@mem0.ai)
-
-## License
-
-This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.
+Apache 2.0 — see the [LICENSE](LICENSE) file for details.

cookbooks/customer-support-chatbot.ipynb

@@ -13,7 +13,7 @@
     "import anthropic\n",
     "\n",
     "# Set up environment variables\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"your_openai_api_key\" # needed for embedding model\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"your_openai_api_key\"  # needed for embedding model\n",
     "os.environ[\"ANTHROPIC_API_KEY\"] = \"your_anthropic_api_key\""
    ]
   },
@@ -33,7 +33,7 @@
     "                    \"model\": \"claude-3-5-sonnet-latest\",\n",
     "                    \"temperature\": 0.1,\n",
     "                    \"max_tokens\": 2000,\n",
-    "                }\n",
+    "                },\n",
     "            }\n",
     "        }\n",
     "        self.client = anthropic.Client(api_key=os.environ[\"ANTHROPIC_API_KEY\"])\n",
@@ -50,11 +50,7 @@
     "        - Keep track of open issues and follow-ups\n",
     "        \"\"\"\n",
     "\n",
-    "    def store_customer_interaction(self,\n",
-    "                                 user_id: str,\n",
-    "                                 message: str,\n",
-    "                                 response: str,\n",
-    "                                 metadata: Dict = None):\n",
+    "    def store_customer_interaction(self, user_id: str, message: str, response: str, metadata: Dict = None):\n",
     "        \"\"\"Store customer interaction in memory.\"\"\"\n",
     "        if metadata is None:\n",
     "            metadata = {}\n",
@@ -63,24 +59,17 @@
     "        metadata[\"timestamp\"] = datetime.now().isoformat()\n",
     "\n",
     "        # Format conversation for storage\n",
-    "        conversation = [\n",
-    "            {\"role\": \"user\", \"content\": message},\n",
-    "            {\"role\": \"assistant\", \"content\": response}\n",
-    "        ]\n",
+    "        conversation = [{\"role\": \"user\", \"content\": message}, {\"role\": \"assistant\", \"content\": response}]\n",
     "\n",
     "        # Store in Mem0\n",
-    "        self.memory.add(\n",
-    "            conversation,\n",
-    "            user_id=user_id,\n",
-    "            metadata=metadata\n",
-    "        )\n",
+    "        self.memory.add(conversation, user_id=user_id, metadata=metadata)\n",
     "\n",
     "    def get_relevant_history(self, user_id: str, query: str) -> List[Dict]:\n",
     "        \"\"\"Retrieve relevant past interactions.\"\"\"\n",
     "        return self.memory.search(\n",
     "            query=query,\n",
     "            user_id=user_id,\n",
-    "            limit=5  # Adjust based on needs\n",
+    "            limit=5,  # Adjust based on needs\n",
     "        )\n",
     "\n",
     "    def handle_customer_query(self, user_id: str, query: str) -> str:\n",
@@ -112,15 +101,12 @@
     "            model=\"claude-3-5-sonnet-latest\",\n",
     "            messages=[{\"role\": \"user\", \"content\": prompt}],\n",
     "            max_tokens=2000,\n",
-    "            temperature=0.1\n",
+    "            temperature=0.1,\n",
     "        )\n",
     "\n",
     "        # Store interaction\n",
     "        self.store_customer_interaction(\n",
-    "            user_id=user_id,\n",
-    "            message=query,\n",
-    "            response=response,\n",
-    "            metadata={\"type\": \"support_query\"}\n",
+    "            user_id=user_id, message=query, response=response, metadata={\"type\": \"support_query\"}\n",
     "        )\n",
     "\n",
     "        return response.content[0].text"
@@ -203,12 +189,12 @@
     "    # Get user input\n",
     "    query = input()\n",
     "    print(\"Customer:\", query)\n",
-    "    \n",
+    "\n",
     "    # Check if user wants to exit\n",
-    "    if query.lower() == 'exit':\n",
+    "    if query.lower() == \"exit\":\n",
     "        print(\"Thank you for using our support service. Goodbye!\")\n",
     "        break\n",
-    "    \n",
+    "\n",
     "    # Handle the query and print the response\n",
     "    response = chatbot.handle_customer_query(user_id, query)\n",
     "    print(\"Support:\", response, \"\\n\\n\")"

cookbooks/helper/mem0_teachability.py

@@ -7,10 +7,12 @@
 # forked from autogen.agentchat.contrib.capabilities.teachability.Teachability
 
 from typing import Dict, Optional, Union
+
 from autogen.agentchat.assistant_agent import ConversableAgent
 from autogen.agentchat.contrib.capabilities.agent_capability import AgentCapability
 from autogen.agentchat.contrib.text_analyzer_agent import TextAnalyzerAgent
 from termcolor import colored
+
 from mem0 import Memory
 
 

docs/_snippets/async-memory-add.mdx

@@ -0,0 +1,5 @@
+<Note type="info">
+  📢 Heads up!
+  We're moving to async memory add for a faster experience.
+  If you signed up after July 1st, 2025, your add requests will work in the background and return right away.
+</Note> 

docs/_snippets/paper-release.mdx

@@ -0,0 +1,3 @@
+<Note type="info">
+  📢 Announcing our research paper: Mem0 achieves <strong>26%</strong> higher accuracy than OpenAI Memory, <strong>91%</strong> lower latency, and <strong>90%</strong> token savings! [Read the paper](https://mem0.ai/research) to learn how we're revolutionizing AI agent memory.
+</Note>

docs/api-reference.mdx

@@ -0,0 +1,191 @@
+---
+title: Overview
+icon: "info"
+iconType: "solid"
+---
+
+Mem0 provides a powerful set of APIs that allow you to integrate advanced memory management capabilities into your applications. Our APIs are designed to be intuitive, efficient, and scalable, enabling you to create, retrieve, update, and delete memories across various entities such as users, agents, apps, and runs.
+
+## Key Features
+
+- **Memory Management**: Add, retrieve, update, and delete memories with ease.
+- **Entity-based Operations**: Perform operations on memories associated with specific users, agents, apps, or runs.
+- **Advanced Search**: Utilize our search API to find relevant memories based on various criteria.
+- **History Tracking**: Access the history of memory interactions for comprehensive analysis.
+- **User Management**: Manage user entities and their associated memories.
+
+## API Structure
+
+Our API is organized into several main categories:
+
+1. **Memory APIs**: Core operations for managing individual memories and collections.
+2. **Entities APIs**: Manage different entity types (users, agents, etc.) and their associated memories.
+3. **Search API**: Advanced search functionality to retrieve relevant memories.
+4. **History API**: Track and retrieve the history of memory interactions.
+
+## Authentication
+
+All API requests require authentication using HTTP Basic Auth. Ensure you include your API key in the Authorization header of each request.
+
+## Organizations and projects (optional)
+
+Organizations and projects provide the following capabilities:
+
+- **Multi-org/project Support**: Specify organization and project when initializing the Mem0 client to attribute API usage appropriately
+- **Member Management**: Control access to data through organization and project membership
+- **Access Control**: Only members can access memories and data within their organization/project scope
+- **Team Isolation**: Maintain data separation between different teams and projects for secure collaboration
+
+Example with the mem0 Python package:
+
+<Tabs>
+  <Tab title="Python">
+
+```python
+from mem0 import MemoryClient
+client = MemoryClient(org_id='YOUR_ORG_ID', project_id='YOUR_PROJECT_ID')
+```
+
+  </Tab>
+
+  <Tab title="Node.js">
+
+```javascript
+import { MemoryClient } from "mem0ai";
+const client = new MemoryClient({organizationId: "YOUR_ORG_ID", projectId: "YOUR_PROJECT_ID"});
+```
+
+  </Tab>
+</Tabs>
+
+### Project Management Methods
+
+The Mem0 client provides comprehensive project management capabilities through the `client.project` interface:
+
+#### Get Project Details
+
+Retrieve information about the current project:
+
+```python
+# Get all project details
+project_info = client.project.get()
+
+# Get specific fields only
+project_info = client.project.get(fields=["name", "description", "custom_categories"])
+```
+
+#### Create a New Project
+
+Create a new project within your organization:
+
+```python
+# Create a project with name and description
+new_project = client.project.create(
+    name="My New Project",
+    description="A project for managing customer support memories"
+)
+```
+
+#### Update Project Settings
+
+Modify project configuration including custom instructions, categories, and graph settings:
+
+```python
+# Update project with custom categories
+client.project.update(
+    custom_categories=[
+        {"customer_preferences": "Customer likes, dislikes, and preferences"},
+        {"support_history": "Previous support interactions and resolutions"}
+    ]
+)
+
+# Update project with custom instructions
+client.project.update(
+    custom_instructions="..."
+)
+
+# Enable graph memory for the project
+client.project.update(enable_graph=True)
+
+# Update multiple settings at once
+client.project.update(
+    custom_instructions="...",
+    custom_categories=[
+        {"personal_info": "User personal information and preferences"},
+        {"work_context": "Professional context and work-related information"}
+    ],
+    enable_graph=True
+)
+```
+
+#### Delete Project
+
+<Note>
+This action will remove all memories, messages, and other related data in the project. This operation is irreversible.
+</Note>
+
+Remove a project and all its associated data:
+
+```python
+# Delete the current project (irreversible)
+result = client.project.delete()
+```
+
+#### Member Management
+
+Manage project members and their access levels:
+
+```python
+# Get all project members
+members = client.project.get_members()
+
+# Add a new member as a reader
+client.project.add_member(
+    email="colleague@company.com",
+    role="READER"  # or "OWNER"
+)
+
+# Update a member's role
+client.project.update_member(
+    email="colleague@company.com",
+    role="OWNER"
+)
+
+# Remove a member from the project
+client.project.remove_member(email="colleague@company.com")
+```
+
+#### Member Roles
+
+- **READER**: Can view and search memories, but cannot modify project settings or manage members
+- **OWNER**: Full access including project modification, member management, and all reader permissions
+
+#### Async Support
+
+All project methods are also available in async mode:
+
+```python
+from mem0 import AsyncMemoryClient
+
+async def manage_project():
+    client = AsyncMemoryClient(org_id='YOUR_ORG_ID', project_id='YOUR_PROJECT_ID')
+
+    # All methods support async/await
+    project_info = await client.project.get()
+    await client.project.update(enable_graph=True)
+    members = await client.project.get_members()
+
+# To call the async function properly
+import asyncio
+asyncio.run(manage_project())
+```
+
+## Getting Started
+
+To begin using the Mem0 API, you'll need to:
+
+1. Sign up for a [Mem0 account](https://app.mem0.ai) and obtain your API key.
+2. Familiarize yourself with the API endpoints and their functionalities.
+3. Make your first API call to add or retrieve a memory.
+
+Explore the detailed documentation for each API endpoint to learn more about request/response formats, parameters, and example usage.

docs/api-reference/memory/feedback.mdx

@@ -0,0 +1,4 @@
+---
+title: 'Feedback'
+openapi: post /v1/feedback/
+---

docs/api-reference/memory/get-memory-export.mdx

@@ -1,6 +1,6 @@
 ---
 title: 'Get Memory Export'
-openapi: get /v1/exports/
+openapi: post /v1/exports/get
 ---
 
 Retrieve the latest structured memory export after submitting an export job. You can filter the export by `user_id`, `run_id`, `session_id`, or `app_id` to get the most recent export matching your filters.

docs/api-reference/memory/v2-get-memories.mdx

@@ -3,12 +3,15 @@ title: 'Get Memories (v2)'
 openapi: post /v2/memories/
 ---
 
-The v2 get memories API is powerful and flexible, allowing for more precise memory listing without the need for a search query. It supports complex logical operations (AND, OR) and comparison operators for advanced filtering capabilities. The comparison operators include:
+The v2 get memories API is powerful and flexible, allowing for more precise memory listing without the need for a search query. It supports complex logical operations (AND, OR, NOT) and comparison operators for advanced filtering capabilities. The comparison operators include:
 - `in`: Matches any of the values specified
 - `gte`: Greater than or equal to
 - `lte`: Less than or equal to
 - `gt`: Greater than
 - `lt`: Less than
+- `ne`: Not equal to
+- `icontains`: Case-insensitive containment check
+- `*`: Wildcard character that matches everything
 
 <CodeGroup>
 ```python Code
@@ -41,3 +44,22 @@ memories = m.get_all(
 ]
 ```
 </CodeGroup>
+
+<CodeGroup>
+```python Wildcard Example
+# Using wildcard to get all memories for a specific user across all run_ids
+memories = m.get_all(
+    filters={
+        "AND": [
+            {
+                "user_id": "alex"
+            },
+            {
+                "run_id": "*"
+            }
+        ]
+    },
+    version="v2"
+)
+```
+</CodeGroup>

docs/api-reference/memory/v2-search-memories.mdx

@@ -3,7 +3,7 @@ title: 'Search Memories (v2)'
 openapi: post /v2/memories/search/
 ---
 
-The v2 search API is powerful and flexible, allowing for more precise memory retrieval. It supports complex logical operations (AND, OR) and comparison operators for advanced filtering capabilities. The comparison operators include:
+The v2 search API is powerful and flexible, allowing for more precise memory retrieval. It supports complex logical operations (AND, OR, NOT) and comparison operators for advanced filtering capabilities. The comparison operators include:
 - `in`: Matches any of the values specified
 - `gte`: Greater than or equal to
 - `lte`: Less than or equal to
@@ -11,14 +11,15 @@ The v2 search API is powerful and flexible, allowing for more precise memory ret
 - `lt`: Less than
 - `ne`: Not equal to
 - `icontains`: Case-insensitive containment check
+- `*`: Wildcard character that matches everything
 
   <CodeGroup>
   ```python Code
-  related_memories = m.vsearch(
+  related_memories = m.search(
       query="What are Alice's hobbies?",
       version="v2",
       filters={
-          "AND": [
+          "OR": [
               {
                 "user_id": "alice"
               },
@@ -49,3 +50,59 @@ The v2 search API is powerful and flexible, allowing for more precise memory ret
   }
   ```
   </CodeGroup>
+
+  <CodeGroup>
+  ```python Wildcard Example
+  # Using wildcard to match all run_ids for a specific user
+  all_memories = m.search(
+      query="What are Alice's hobbies?",
+      version="v2",
+      filters={
+          "AND": [
+              {
+                  "user_id": "alice"
+              },
+              {
+                  "run_id": "*"
+              }
+          ]
+      },
+  )
+  ```
+  </CodeGroup>
+
+  <CodeGroup>
+  ```python Categories Filter Examples
+  # Example 1: Using 'contains' for partial matching
+  finance_memories = m.search(
+      query="What are my financial goals?",
+      version="v2",
+      filters={
+          "AND": [
+              { "user_id": "alice" },
+              {
+                  "categories": {
+                      "contains": "finance"
+                  }
+              }
+          ]
+      },
+  )
+
+  # Example 2: Using 'in' for exact matching
+  personal_memories = m.search(
+      query="What personal information do you have?",
+      version="v2",
+      filters={
+          "AND": [
+              { "user_id": "alice" },
+              {
+                  "categories": {
+                      "in": ["personal_information"]
+                  }
+              }
+          ]
+      },
+  )
+  ```
+  </CodeGroup>

docs/api-reference/organization/delete-org-member.mdx

@@ -1,4 +0,0 @@
----
-title: 'Delete Member'
-openapi: delete /api/v1/orgs/organizations/{org_id}/members/
----

docs/api-reference/organization/update-org-member.mdx

@@ -1,9 +0,0 @@
----
-title: 'Update Member'
-openapi: put /api/v1/orgs/organizations/{org_id}/members/
----
-
-The API provides two roles for organization members:
-
-- `READER`: Allows viewing of organization resources.
-- `OWNER`: Grants full administrative access to manage the organization and its resources.

docs/api-reference/overview.mdx

@@ -1,69 +0,0 @@
----
-title: Overview
-icon: "info"
-iconType: "solid"
----
-
-Mem0 provides a powerful set of APIs that allow you to integrate advanced memory management capabilities into your applications. Our APIs are designed to be intuitive, efficient, and scalable, enabling you to create, retrieve, update, and delete memories across various entities such as users, agents, apps, and runs.
-
-## Key Features
-
-- **Memory Management**: Add, retrieve, update, and delete memories with ease.
-- **Entity-based Operations**: Perform operations on memories associated with specific users, agents, apps, or runs.
-- **Advanced Search**: Utilize our search API to find relevant memories based on various criteria.
-- **History Tracking**: Access the history of memory interactions for comprehensive analysis.
-- **User Management**: Manage user entities and their associated memories.
-
-## API Structure
-
-Our API is organized into several main categories:
-
-1. **Memory APIs**: Core operations for managing individual memories and collections.
-2. **Entities APIs**: Manage different entity types (users, agents, etc.) and their associated memories.
-3. **Search API**: Advanced search functionality to retrieve relevant memories.
-4. **History API**: Track and retrieve the history of memory interactions.
-
-## Authentication
-
-All API requests require authentication using HTTP Basic Auth. Ensure you include your API key in the Authorization header of each request.
-
-## Organizations and projects (optional)
-
-Organizations and projects provide the following capabilities:
-
-- **Multi-org/project Support**: Specify organization and project when initializing the Mem0 client to attribute API usage appropriately
-- **Member Management**: Control access to data through organization and project membership
-- **Access Control**: Only members can access memories and data within their organization/project scope
-- **Team Isolation**: Maintain data separation between different teams and projects for secure collaboration
-
-Example with the mem0 Python package:
-
-<Tabs>
-  <Tab title="Python">
-
-```python
-from mem0 import MemoryClient
-client = MemoryClient(org_id='YOUR_ORG_ID', project_id='YOUR_PROJECT_ID')
-```
-
-  </Tab>
-
-  <Tab title="Node.js">
-
-```javascript
-import { MemoryClient } from "mem0ai";
-const client = new MemoryClient({organizationId: "YOUR_ORG_ID", projectId: "YOUR_PROJECT_ID"});
-```
-
-  </Tab>
-</Tabs>
-
-## Getting Started
-
-To begin using the Mem0 API, you'll need to:
-
-1. Sign up for a [Mem0 account](https://app.mem0.ai) and obtain your API key.
-2. Familiarize yourself with the API endpoints and their functionalities.
-3. Make your first API call to add or retrieve a memory.
-
-Explore the detailed documentation for each API endpoint to learn more about request/response formats, parameters, and example usage.

docs/api-reference/project/delete-project-member.mdx

@@ -1,4 +0,0 @@
----
-title: 'Delete Member'
-openapi: delete /api/v1/orgs/organizations/{org_id}/projects/{project_id}/members/
----

docs/api-reference/project/update-project-member.mdx

@@ -1,9 +0,0 @@
----
-title: 'Update Member'
-openapi: put /api/v1/orgs/organizations/{org_id}/projects/{project_id}/members/
----
-
-The API provides two roles for project members:
-
-- `READER`: Allows viewing of project resources.
-- `OWNER`: Grants full administrative access to manage the project and its resources.

docs/api-reference/project/update-project.mdx

@@ -1,4 +0,0 @@
----
-title: 'Update Project'
-openapi: patch /api/v1/orgs/organizations/{org_id}/projects/{project_id}/
----

docs/components/embedders/config.mdx

@@ -4,6 +4,7 @@ icon: "gear"
 iconType: "solid"
 ---
 
+
 Config in mem0 is a dictionary that specifies the settings for your embedding models. It allows you to customize the behavior and connection details of your chosen embedder.
 
 ## How to define configurations?

docs/components/embedders/models/aws_bedrock.mdx

@@ -0,0 +1,62 @@
+---
+title: AWS Bedrock
+---
+
+To use AWS Bedrock embedding models, you need to have the appropriate AWS credentials and permissions. The embeddings implementation relies on the `boto3` library.
+
+### Setup
+- Ensure you have model access from the [AWS Bedrock Console](https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/modelaccess)
+- Authenticate the boto3 client using a method described in the [AWS documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html)
+- Set up environment variables for authentication:
+  ```bash
+  export AWS_REGION=us-east-1
+  export AWS_ACCESS_KEY_ID=your-access-key
+  export AWS_SECRET_ACCESS_KEY=your-secret-key
+  ```
+
+### Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+
+# For LLM if needed
+os.environ["OPENAI_API_KEY"] = "your-openai-api-key"
+
+# AWS credentials
+os.environ["AWS_REGION"] = "us-west-2"
+os.environ["AWS_ACCESS_KEY_ID"] = "your-access-key"
+os.environ["AWS_SECRET_ACCESS_KEY"] = "your-secret-key"
+
+config = {
+    "embedder": {
+        "provider": "aws_bedrock",
+        "config": {
+            "model": "amazon.titan-embed-text-v2:0"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice")
+```
+</CodeGroup>
+
+### Config
+
+Here are the parameters available for configuring AWS Bedrock embedder:
+
+<Tabs>
+<Tab title="Python">
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `model` | The name of the embedding model to use | `amazon.titan-embed-text-v1` |
+</Tab>
+</Tabs>

docs/components/embedders/models/azure_openai.mdx

@@ -6,7 +6,8 @@ To use Azure OpenAI embedding models, set the `EMBEDDING_AZURE_OPENAI_API_KEY`,
 
 ### Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -46,6 +47,73 @@ messages = [
 m.add(messages, user_id="john")
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+    embedder: {
+        provider: "azure_openai",
+        config: {
+            model: "text-embedding-3-large",
+            modelProperties: {
+                endpoint: "your-api-base-url",
+                deployment: "your-deployment-name",
+                apiVersion: "version-to-use",
+            }
+        }
+    }
+}
+
+const memory = new Memory(config);
+
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+
+await memory.add(messages, { userId: "john" });
+```
+</CodeGroup>
+
+As an alternative to using an API key, the Azure Identity credential chain can be used to authenticate with [Azure OpenAI role-based security](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/role-based-access-control). 
+
+<Note> If an API key is provided, it will be used for authentication over an Azure Identity </Note>
+
+Below is a sample configuration for using Mem0 with Azure OpenAI and Azure Identity:
+
+```python
+import os
+from mem0 import Memory
+# You can set the values directly in the config dictionary or use environment variables
+
+os.environ["LLM_AZURE_DEPLOYMENT"] = "your-deployment-name"
+os.environ["LLM_AZURE_ENDPOINT"] = "your-api-base-url"
+os.environ["LLM_AZURE_API_VERSION"] = "version-to-use"
+
+config = {
+    "llm": {
+        "provider": "azure_openai_structured",
+        "config": {
+            "model": "your-deployment-name",
+            "temperature": 0.1,
+            "max_tokens": 2000,
+            "azure_kwargs": {
+                  "azure_deployment": "<your-deployment-name>",
+                  "api_version": "<version-to-use>",
+                  "azure_endpoint": "<your-api-base-url>",
+                  "default_headers": {
+                    "CustomHeader": "your-custom-header",
+                  }
+              }
+        }
+    }
+}
+```
+
+Refer to [Azure Identity troubleshooting tips](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/identity/azure-identity/TROUBLESHOOTING.md#troubleshoot-environmentcredential-authentication-issues) for setting up an Azure Identity credential.
+
 ### Config
 
 Here are the parameters available for configuring Azure OpenAI embedder:

docs/components/embedders/models/google_AI.mdx

@@ -0,0 +1,69 @@
+---
+title: Google AI
+---
+
+To use Google AI embedding models, set the `GOOGLE_API_KEY` environment variables. You can obtain the Gemini API key from [here](https://aistudio.google.com/app/apikey).
+
+### Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+
+os.environ["GOOGLE_API_KEY"] = "key"
+os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
+
+config = {
+    "embedder": {
+        "provider": "gemini",
+        "config": {
+            "model": "models/text-embedding-004",
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="john")
+```
+
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  embedder: {
+    provider: 'google',
+    config: {
+      apiKey: process.env.GOOGLE_API_KEY || '',
+      model: 'text-embedding-004',
+      // The output dimensionality is fixed at 768 for Google AI embeddings
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "john" });
+```
+</CodeGroup>
+
+### Config
+
+Here are the parameters available for configuring Gemini embedder:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `model` | The name of the embedding model to use | `models/text-embedding-004` |
+| `embedding_dims` | Dimensions of the embedding model (output_dimensionality will be considered as embedding_dims, so please set embedding_dims accordingly) | `768` |
+| `api_key` | The Google API key | `None` |

docs/components/embedders/models/huggingface.mdx

@@ -25,12 +25,44 @@ m = Memory.from_config(config)
 messages = [
     {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
     {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
     {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
 ]
 m.add(messages, user_id="john")
 ```
 
+### Using Text Embeddings Inference (TEI)
+
+You can also use Hugging Face's Text Embeddings Inference service for faster and more efficient embeddings:
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
+
+# Using HuggingFace Text Embeddings Inference API
+config = {
+    "embedder": {
+        "provider": "huggingface",
+        "config": {
+            "huggingface_base_url": "http://localhost:3000/v1"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+m.add("This text will be embedded using the TEI service.", user_id="john")
+```
+
+To run the TEI service, you can use Docker:
+
+```bash
+docker run -d -p 3000:80 -v huggingfacetei:/data --platform linux/amd64 \
+    ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 \
+    --model-id BAAI/bge-small-en-v1.5
+```
+
 ### Config
 
 Here are the parameters available for configuring Huggingface embedder:
@@ -39,4 +71,5 @@ Here are the parameters available for configuring Huggingface embedder:
 | --- | --- | --- |
 | `model` | The name of the model to use | `multi-qa-MiniLM-L6-cos-v1` |
 | `embedding_dims` | Dimensions of the embedding model | `selected_model_dimensions` |
-| `model_kwargs` | Additional arguments for the model | `None` |
+| `model_kwargs` | Additional arguments for the model | `None` |
+| `huggingface_base_url` | URL to connect to Text Embeddings Inference (TEI) API | `None` |

docs/components/embedders/models/langchain.mdx

@@ -0,0 +1,196 @@
+---
+title: LangChain
+---
+
+Mem0 supports LangChain as a provider to access a wide range of embedding models. LangChain is a framework for developing applications powered by language models, making it easy to integrate various embedding providers through a consistent interface.
+
+For a complete list of available embedding models supported by LangChain, refer to the [LangChain Text Embedding documentation](https://python.langchain.com/docs/integrations/text_embedding/).
+
+## Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+from langchain_openai import OpenAIEmbeddings
+
+# Set necessary environment variables for your chosen LangChain provider
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+
+# Initialize a LangChain embeddings model directly
+openai_embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",
+    dimensions=1536
+)
+
+# Pass the initialized model to the config
+config = {
+    "embedder": {
+        "provider": "langchain",
+        "config": {
+            "model": openai_embeddings
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+import { OpenAIEmbeddings } from "@langchain/openai";
+
+// Initialize a LangChain embeddings model directly
+const openaiEmbeddings = new OpenAIEmbeddings({
+    modelName: "text-embedding-3-small",
+    dimensions: 1536,
+    apiKey: process.env.OPENAI_API_KEY,
+});
+
+const config = {
+  embedder: {
+    provider: 'langchain',
+    config: {
+      model: openaiEmbeddings,
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
+## Supported LangChain Embedding Providers
+
+LangChain supports a wide range of embedding providers, including:
+
+- OpenAI (`OpenAIEmbeddings`)
+- Cohere (`CohereEmbeddings`)
+- Google (`VertexAIEmbeddings`)
+- Hugging Face (`HuggingFaceEmbeddings`)
+- Sentence Transformers (`HuggingFaceEmbeddings`)
+- Azure OpenAI (`AzureOpenAIEmbeddings`)
+- Ollama (`OllamaEmbeddings`)
+- Together (`TogetherEmbeddings`)
+- And many more
+
+You can use any of these model instances directly in your configuration. For a complete and up-to-date list of available embedding providers, refer to the [LangChain Text Embedding documentation](https://python.langchain.com/docs/integrations/text_embedding/).
+
+## Provider-Specific Configuration
+
+When using LangChain as an embedder provider, you'll need to:
+
+1. Set the appropriate environment variables for your chosen embedding provider
+2. Import and initialize the specific model class you want to use
+3. Pass the initialized model instance to the config
+
+### Examples with Different Providers
+
+<CodeGroup>
+#### HuggingFace Embeddings
+
+```python Python
+from langchain_huggingface import HuggingFaceEmbeddings
+
+# Initialize a HuggingFace embeddings model
+hf_embeddings = HuggingFaceEmbeddings(
+    model_name="BAAI/bge-small-en-v1.5",
+    encode_kwargs={"normalize_embeddings": True}
+)
+
+config = {
+    "embedder": {
+        "provider": "langchain",
+        "config": {
+            "model": hf_embeddings
+        }
+    }
+}
+```
+
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+import { HuggingFaceEmbeddings } from "@langchain/community/embeddings/hf";
+
+// Initialize a HuggingFace embeddings model
+const hfEmbeddings = new HuggingFaceEmbeddings({
+    modelName: "BAAI/bge-small-en-v1.5",
+    encode: {
+        normalize_embeddings: true,
+    },
+});
+
+const config = {
+  embedder: {
+    provider: 'langchain',
+    config: {
+      model: hfEmbeddings,
+    },
+  },
+};
+```
+</CodeGroup>
+
+<CodeGroup>
+#### Ollama Embeddings
+
+```python Python
+from langchain_ollama import OllamaEmbeddings
+
+# Initialize an Ollama embeddings model
+ollama_embeddings = OllamaEmbeddings(
+    model="nomic-embed-text"
+)
+
+config = {
+    "embedder": {
+        "provider": "langchain",
+        "config": {
+            "model": ollama_embeddings
+        }
+    }
+}
+```
+
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+import { OllamaEmbeddings } from "@langchain/community/embeddings/ollama";
+
+// Initialize an Ollama embeddings model
+const ollamaEmbeddings = new OllamaEmbeddings({
+    model: "nomic-embed-text",
+    baseUrl: "http://localhost:11434", // Ollama server URL
+});
+
+const config = {
+  embedder: {
+    provider: 'langchain',
+    config: {
+      model: ollamaEmbeddings,
+    },
+  },
+};
+```
+</CodeGroup>
+
+<Note>
+  Make sure to install the necessary LangChain packages and any provider-specific dependencies.
+</Note>
+
+## Config
+
+All available parameters for the `langchain` embedder config are present in [Master List of All Params in Config](../config).

docs/components/embedders/models/ollama.mdx

@@ -2,7 +2,8 @@ You can use embedding models from Ollama to run Mem0 locally.
 
 ### Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -21,18 +22,52 @@ m = Memory.from_config(config)
 messages = [
     {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
     {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
     {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
 ]
 m.add(messages, user_id="john")
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  embedder: {
+    provider: 'ollama',
+    config: {
+      model: 'nomic-embed-text:latest', // or any other Ollama embedding model
+      url: 'http://localhost:11434', // Ollama server URL
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "john" });
+```
+</CodeGroup>
+
 ### Config
 
 Here are the parameters available for configuring Ollama embedder:
 
+<Tabs>
+<Tab title="Python">
 | Parameter | Description | Default Value |
 | --- | --- | --- |
-| `model` | The name of the OpenAI model to use | `nomic-embed-text` |
+| `model` | The name of the Ollama model to use | `nomic-embed-text` |
 | `embedding_dims` | Dimensions of the embedding model | `512` |
-| `ollama_base_url` | Base URL for ollama connection | `None` |
+| `ollama_base_url` | Base URL for ollama connection | `None` |
+</Tab>
+<Tab title="TypeScript">
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `model` | The name of the Ollama model to use | `nomic-embed-text:latest` |
+| `url` | Base URL for Ollama server | `http://localhost:11434` |
+</Tab>
+</Tabs>

docs/components/embedders/overview.mdx

@@ -19,10 +19,12 @@ See the list of supported embedders below.
   <Card title="Azure OpenAI" href="/components/embedders/models/azure_openai"></Card>
   <Card title="Ollama" href="/components/embedders/models/ollama"></Card>
   <Card title="Hugging Face" href="/components/embedders/models/huggingface"></Card>
-  <Card title="Gemini" href="/components/embedders/models/gemini"></Card>
+  <Card title="Google AI" href="/components/embedders/models/google_AI"></Card>
   <Card title="Vertex AI" href="/components/embedders/models/vertexai"></Card>
   <Card title="Together" href="/components/embedders/models/together"></Card>
   <Card title="LM Studio" href="/components/embedders/models/lmstudio"></Card>
+  <Card title="Langchain" href="/components/embedders/models/langchain"></Card>
+  <Card title="AWS Bedrock" href="/components/embedders/models/aws_bedrock"></Card>
 </CardGroup>
 
 ## Usage

docs/components/llms/config.mdx

@@ -29,7 +29,7 @@ iconType: "solid"
 Config values are applied in the following order of precedence (from highest to lowest):
 
 1. Values explicitly set in the `config` object/dictionary
-2. Environment variables (e.g., `OPENAI_API_KEY`, `OPENAI_API_BASE`)
+2. Environment variables (e.g., `OPENAI_API_KEY`, `OPENAI_BASE_URL`)
 3. Default values defined in the LLM implementation
 
 This means that values specified in the `config` will override corresponding environment variables, which in turn override default values.
@@ -56,6 +56,7 @@ config = {
 
 m = Memory.from_config(config)
 m.add("Your text here", user_id="user", metadata={"category": "example"})
+
 ```
 
 ```typescript TypeScript
@@ -74,6 +75,7 @@ const config = {
 const memory = new Memory(config);
 await memory.add("Your text here", { userId: "user123", metadata: { category: "example" } });
 ```
+
 </CodeGroup>
 
 ## Why is Config Needed?
@@ -108,7 +110,14 @@ Here's a comprehensive list of all parameters that can be used across different
     | `azure_kwargs`       | Azure LLM args for initialization             | AzureOpenAI       |
     | `deepseek_base_url`  | Base URL for DeepSeek API                     | DeepSeek          |
     | `xai_base_url`       | Base URL for XAI API                          | XAI               |
+    | `sarvam_base_url`    | Base URL for Sarvam API                       | Sarvam            |
+    | `reasoning_effort`   | Reasoning level (low, medium, high)           | Sarvam            |
+    | `frequency_penalty`  | Penalize frequent tokens (-2.0 to 2.0)        | Sarvam            |
+    | `presence_penalty`   | Penalize existing tokens (-2.0 to 2.0)        | Sarvam            |
+    | `seed`               | Seed for deterministic sampling               | Sarvam            |
+    | `stop`               | Stop sequences (max 4)                        | Sarvam            |
     | `lmstudio_base_url`  | Base URL for LM Studio API                    | LM Studio         |
+    | `response_callback`  | LLM response callback function                | OpenAI            |
   </Tab>
   <Tab title="TypeScript">
     | Parameter            | Description                                   | Provider          |

docs/components/llms/models/anthropic.mdx

@@ -2,7 +2,8 @@
 title: Anthropic
 ---
 
-To use anthropic's models, please set the `ANTHROPIC_API_KEY` which you find on their [Account Settings Page](https://console.anthropic.com/account/keys).
+
+To use Anthropic's models, please set the `ANTHROPIC_API_KEY` which you find on their [Account Settings Page](https://console.anthropic.com/account/keys).
 
 ## Usage
 
@@ -18,7 +19,7 @@ config = {
     "llm": {
         "provider": "anthropic",
         "config": {
-            "model": "claude-3-7-sonnet-latest",
+            "model": "claude-sonnet-4-20250514",
             "temperature": 0.1,
             "max_tokens": 2000,
         }
@@ -43,7 +44,7 @@ const config = {
     provider: 'anthropic',
     config: {
       apiKey: process.env.ANTHROPIC_API_KEY || '',
-      model: 'claude-3-7-sonnet-latest',
+      model: 'claude-sonnet-4-20250514',
       temperature: 0.1,
       maxTokens: 2000,
     },

docs/components/llms/models/aws_bedrock.mdx

@@ -13,16 +13,15 @@ title: AWS Bedrock
 import os
 from mem0 import Memory
 
-os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
-os.environ['AWS_REGION'] = 'us-east-1'
-os.environ["AWS_ACCESS_KEY"] = "xx"
+os.environ['AWS_REGION'] = 'us-west-2'
+os.environ["AWS_ACCESS_KEY_ID"] = "xx"
 os.environ["AWS_SECRET_ACCESS_KEY"] = "xx"
 
 config = {
     "llm": {
         "provider": "aws_bedrock",
         "config": {
-            "model": "arn:aws:bedrock:us-east-1:123456789012:model/your-model-name",
+            "model": "anthropic.claude-3-5-haiku-20241022-v1:0",
             "temperature": 0.2,
             "max_tokens": 2000,
         }

docs/components/llms/models/azure_openai.mdx

@@ -2,14 +2,24 @@
 title: Azure OpenAI
 ---
 
+<Note> Mem0 Now Supports Azure OpenAI Models in TypeScript SDK </Note>
+
 To use Azure OpenAI models, you have to set the `LLM_AZURE_OPENAI_API_KEY`, `LLM_AZURE_ENDPOINT`, `LLM_AZURE_DEPLOYMENT` and `LLM_AZURE_API_VERSION` environment variables. You can obtain the Azure API key from the [Azure](https://azure.microsoft.com/).
 
+Optionally, you can use Azure Identity to authenticate with Azure OpenAI, which allows you to use managed identities or service principals for production and Azure CLI login for development instead of an API key. If an Azure Identity is to be used, ***do not*** set the `LLM_AZURE_OPENAI_API_KEY` environment variable or the api_key in the config dictionary.
+
+> **Note**: The following are currently unsupported with reasoning models `Parallel tool calling`,`temperature`, `top_p`, `presence_penalty`, `frequency_penalty`, `logprobs`, `top_logprobs`, `logit_bias`, `max_tokens`
+
+
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
+os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
+
 os.environ["LLM_AZURE_OPENAI_API_KEY"] = "your-api-key"
 os.environ["LLM_AZURE_DEPLOYMENT"] = "your-deployment-name"
 os.environ["LLM_AZURE_ENDPOINT"] = "your-api-base-url"
@@ -45,7 +55,38 @@ messages = [
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
-We also support the new [OpenAI structured-outputs](https://platform.openai.com/docs/guides/structured-outputs/introduction) model.
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  llm: {
+    provider: 'azure_openai',
+    config: {
+      apiKey: process.env.AZURE_OPENAI_API_KEY || '',
+      modelProperties: {
+        endpoint: 'https://your-api-base-url',
+        deployment: 'your-deployment-name',
+        modelName: 'your-model-name',
+        apiVersion: 'version-to-use',
+        // Any other parameters you want to pass to the Azure OpenAI API
+      },
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
+
+We also support the new [OpenAI structured-outputs](https://platform.openai.com/docs/guides/structured-outputs/introduction) model. Typescript SDK does not support the `azure_openai_structured` model yet.
 
 ```python
 import os
@@ -77,6 +118,44 @@ config = {
 }
 ```
 
+As an alternative to using an API key, the Azure Identity credential chain can be used to authenticate with [Azure OpenAI role-based security](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/role-based-access-control). 
+
+<Note> If an API key is provided, it will be used for authentication over an Azure Identity </Note>
+
+Below is a sample configuration for using Mem0 with Azure OpenAI and Azure Identity:
+
+```python
+import os
+from mem0 import Memory
+# You can set the values directly in the config dictionary or use environment variables
+
+os.environ["LLM_AZURE_DEPLOYMENT"] = "your-deployment-name"
+os.environ["LLM_AZURE_ENDPOINT"] = "your-api-base-url"
+os.environ["LLM_AZURE_API_VERSION"] = "version-to-use"
+
+config = {
+    "llm": {
+        "provider": "azure_openai_structured",
+        "config": {
+            "model": "your-deployment-name",
+            "temperature": 0.1,
+            "max_tokens": 2000,
+            "azure_kwargs": {
+                  "azure_deployment": "<your-deployment-name>",
+                  "api_version": "<version-to-use>",
+                  "azure_endpoint": "<your-api-base-url>",
+                  "default_headers": {
+                    "CustomHeader": "your-custom-header",
+                  }
+              }
+        }
+    }
+}
+```
+
+Refer to [Azure Identity troubleshooting tips](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/identity/azure-identity/TROUBLESHOOTING.md#troubleshoot-environmentcredential-authentication-issues) for setting up an Azure Identity credential.
+
+
 ## Config
 
 All available parameters for the `azure_openai` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/google_AI.mdx

@@ -2,38 +2,73 @@
 title: Google AI
 ---
 
-To use Google AI model, you have to set the `GOOGLE_API_KEY` environment variable. You can obtain the Google API key from the [Google Maker Suite](https://makersuite.google.com/app/apikey)
+To use the Gemini model, set the `GOOGLE_API_KEY` environment variable. You can obtain the Google/Gemini API key from [Google AI Studio](https://aistudio.google.com/app/apikey).
+
+> **Note:** As of the latest release, Mem0 uses the new `google.genai` SDK instead of the deprecated `google.generativeai`. All message formatting and model interaction now use the updated `types` module from `google.genai`.
+
+> **Note:** Some Gemini models are being deprecated and will retire soon. It is recommended to migrate to the latest stable models like `"gemini-2.0-flash-001"` or `"gemini-2.0-flash-lite-001"` to ensure ongoing support and improvements.
 
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
-os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
-os.environ["GEMINI_API_KEY"] = "your-api-key"
+os.environ["OPENAI_API_KEY"] = "your-openai-api-key"  # Used for embedding model
+os.environ["GOOGLE_API_KEY"] = "your-gemini-api-key"
 
 config = {
     "llm": {
-        "provider": "litellm",
+        "provider": "gemini",
         "config": {
-            "model": "gemini/gemini-pro",
+            "model": "gemini-2.0-flash-001",
             "temperature": 0.2,
             "max_tokens": 2000,
+            "top_p": 1.0
         }
     }
 }
 
 m = Memory.from_config(config)
+
 messages = [
     {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
-    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
-    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I’m not a big fan of thrillers, but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thrillers and suggest sci-fi movies instead."}
 ]
+
 m.add(messages, user_id="alice", metadata={"category": "movies"})
+
 ```
+```typescript TypeScript
+import { Memory } from "mem0ai/oss";
+
+const config = {
+    llm: {
+        // You can also use "google" as provider ( for backward compatibility )
+        provider: "gemini",
+        config: {
+            model: "gemini-2.0-flash-001",
+            temperature: 0.1
+        }
+    }
+}
+
+const memory = new Memory(config);
+
+const messages = [
+    { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
+    { role: "assistant", content: "How about thriller movies? They can be quite engaging." },
+    { role: "user", content: "I’m not a big fan of thrillers, but I love sci-fi movies." },
+    { role: "assistant", content: "Got it! I'll avoid thrillers and suggest sci-fi movies instead." }
+]
+
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
 
 ## Config
 
-All available parameters for the `litellm` config are present in [Master List of All Params in Config](../config).
+All available parameters for the `Gemini` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/langchain.mdx

@@ -0,0 +1,109 @@
+---
+title: LangChain
+---
+
+
+Mem0 supports LangChain as a provider to access a wide range of LLM models. LangChain is a framework for developing applications powered by language models, making it easy to integrate various LLM providers through a consistent interface.
+
+For a complete list of available chat models supported by LangChain, refer to the [LangChain Chat Models documentation](https://python.langchain.com/docs/integrations/chat).
+
+## Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+from langchain_openai import ChatOpenAI
+
+# Set necessary environment variables for your chosen LangChain provider
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+
+# Initialize a LangChain model directly
+openai_model = ChatOpenAI(
+    model="gpt-4o",
+    temperature=0.2,
+    max_tokens=2000
+)
+
+# Pass the initialized model to the config
+config = {
+    "llm": {
+        "provider": "langchain",
+        "config": {
+            "model": openai_model
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+import { ChatOpenAI } from "@langchain/openai";
+
+// Initialize a LangChain model directly
+const openaiModel = new ChatOpenAI({
+    modelName: "gpt-4",
+    temperature: 0.2,
+    maxTokens: 2000,
+    apiKey: process.env.OPENAI_API_KEY,
+});
+
+const config = {
+  llm: {
+    provider: 'langchain',
+    config: {
+      model: openaiModel,
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
+## Supported LangChain Providers
+
+LangChain supports a wide range of LLM providers, including:
+
+- OpenAI (`ChatOpenAI`)
+- Anthropic (`ChatAnthropic`)
+- Google (`ChatGoogleGenerativeAI`, `ChatGooglePalm`)
+- Mistral (`ChatMistralAI`)
+- Ollama (`ChatOllama`)
+- Azure OpenAI (`AzureChatOpenAI`)
+- HuggingFace (`HuggingFaceChatEndpoint`)
+- And many more
+
+You can use any of these model instances directly in your configuration. For a complete and up-to-date list of available providers, refer to the [LangChain Chat Models documentation](https://python.langchain.com/docs/integrations/chat).
+
+## Provider-Specific Configuration
+
+When using LangChain as a provider, you'll need to:
+
+1. Set the appropriate environment variables for your chosen LLM provider
+2. Import and initialize the specific model class you want to use
+3. Pass the initialized model instance to the config
+
+<Note>
+  Make sure to install the necessary LangChain packages and any provider-specific dependencies.
+</Note>
+
+## Config
+
+All available parameters for the `langchain` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/lmstudio.mdx

@@ -21,6 +21,7 @@ config = {
             "temperature": 0.2,
             "max_tokens": 2000,
             "lmstudio_base_url": "http://localhost:1234/v1", # default LM Studio API URL
+            "lmstudio_response_format": {"type": "json_schema", "json_schema": {"type": "object", "schema": {}}},
         }
     }
 }

docs/components/llms/models/mistral_AI.mdx

@@ -2,11 +2,12 @@
 title: Mistral AI
 ---
 
-To use mistral's models, please Obtain the Mistral AI api key from their [console](https://console.mistral.ai/). Set the `MISTRAL_API_KEY` environment variable to use the model as given below in the example.
+To use mistral's models, please obtain the Mistral AI api key from their [console](https://console.mistral.ai/). Set the `MISTRAL_API_KEY` environment variable to use the model as given below in the example.
 
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -34,6 +35,32 @@ messages = [
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  llm: {
+    provider: 'mistral',
+    config: {
+      apiKey: process.env.MISTRAL_API_KEY || '',
+      model: 'mistral-tiny-latest', // Or 'mistral-small-latest', 'mistral-medium-latest', etc.
+      temperature: 0.1,
+      maxTokens: 2000,
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
 ## Config
 
 All available parameters for the `litellm` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/ollama.mdx

@@ -2,7 +2,8 @@ You can use LLMs from Ollama to run Mem0 locally. These [models](https://ollama.
 
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -23,12 +24,37 @@ m = Memory.from_config(config)
 messages = [
     {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
     {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
     {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
 ]
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  llm: {
+    provider: 'ollama',
+    config: {
+      model: 'llama3.1:8b', // or any other Ollama model
+      url: 'http://localhost:11434', // Ollama server URL
+      temperature: 0.1,
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
 ## Config
 
 All available parameters for the `ollama` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/openai.mdx

@@ -4,6 +4,8 @@ title: OpenAI
 
 To use OpenAI LLM models, you have to set the `OPENAI_API_KEY` environment variable. You can obtain the OpenAI API key from the [OpenAI Platform](https://platform.openai.com/account/api-keys).
 
+> **Note**: The following are currently unsupported with reasoning models `Parallel tool calling`,`temperature`, `top_p`, `presence_penalty`, `frequency_penalty`, `logprobs`, `top_logprobs`, `logit_bias`, `max_tokens`
+
 ## Usage
 
 <CodeGroup>
@@ -92,10 +94,6 @@ config = {
 m = Memory.from_config(config)
 ```
 
-<Note>
-  OpenAI structured-outputs is currently only available in the Python implementation.
-</Note>
-
 ## Config
 
-All available parameters for the `openai` config are present in [Master List of All Params in Config](../config).
+All available parameters for the `openai` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/sarvam.mdx

@@ -0,0 +1,73 @@
+---
+title: Sarvam AI
+---
+
+**Sarvam AI** is an Indian AI company developing language models with a focus on Indian languages and cultural context. Their latest model **Sarvam-M** is designed to understand and generate content in multiple Indian languages while maintaining high performance in English.
+
+To use Sarvam AI's models, please set the `SARVAM_API_KEY` which you can get from their [platform](https://dashboard.sarvam.ai/).
+
+## Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
+os.environ["SARVAM_API_KEY"] = "your-api-key"
+
+config = {
+    "llm": {
+        "provider": "sarvam",
+        "config": {
+            "model": "sarvam-m",
+            "temperature": 0.7,
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alex")
+```
+
+## Advanced Usage with Sarvam-Specific Features
+
+```python
+import os
+from mem0 import Memory
+
+config = {
+    "llm": {
+        "provider": "sarvam",
+        "config": {
+            "model": {
+                "name": "sarvam-m",
+                "reasoning_effort": "high",  # Enable advanced reasoning
+                "frequency_penalty": 0.1,    # Reduce repetition
+                "seed": 42                   # For deterministic outputs
+            },
+            "temperature": 0.3,
+            "max_tokens": 2000,
+            "api_key": "your-sarvam-api-key"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+
+# Example with Hindi conversation
+messages = [
+    {"role": "user", "content": "मैं SBI में joint account खोलना चाहता हूँ।"},
+    {"role": "assistant", "content": "SBI में joint account खोलने के लिए आपको कुछ documents की जरूरत होगी। क्या आप जानना चाहते हैं कि कौन से documents चाहिए?"}
+]
+m.add(messages, user_id="rajesh", metadata={"language": "hindi", "topic": "banking"})
+```
+
+## Config
+
+All available parameters for the `sarvam` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/vllm.mdx

@@ -0,0 +1,107 @@
+---
+title: vLLM
+---
+
+[vLLM](https://docs.vllm.ai/) is a high-performance inference engine for large language models that provides significant performance improvements for local inference. It's designed to maximize throughput and memory efficiency for serving LLMs.
+
+## Prerequisites
+
+1. **Install vLLM**:
+
+   ```bash
+   pip install vllm
+   ```
+
+2. **Start vLLM server**:
+
+   ```bash
+   # For testing with a small model
+   vllm serve microsoft/DialoGPT-medium --port 8000
+
+   # For production with a larger model (requires GPU)
+   vllm serve Qwen/Qwen2.5-32B-Instruct --port 8000
+   ```
+
+## Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "your-api-key"  # used for embedding model
+
+config = {
+    "llm": {
+        "provider": "vllm",
+        "config": {
+            "model": "Qwen/Qwen2.5-32B-Instruct",
+            "vllm_base_url": "http://localhost:8000/v1",
+            "temperature": 0.1,
+            "max_tokens": 2000,
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thrillers, but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thrillers and suggest sci-fi movies instead."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+## Configuration Parameters
+
+| Parameter       | Description                       | Default                       | Environment Variable |
+| --------------- | --------------------------------- | ----------------------------- | -------------------- |
+| `model`         | Model name running on vLLM server | `"Qwen/Qwen2.5-32B-Instruct"` | -                    |
+| `vllm_base_url` | vLLM server URL                   | `"http://localhost:8000/v1"`  | `VLLM_BASE_URL`      |
+| `api_key`       | API key (dummy for local)         | `"vllm-api-key"`              | `VLLM_API_KEY`       |
+| `temperature`   | Sampling temperature              | `0.1`                         | -                    |
+| `max_tokens`    | Maximum tokens to generate        | `2000`                        | -                    |
+
+## Environment Variables
+
+You can set these environment variables instead of specifying them in config:
+
+```bash
+export VLLM_BASE_URL="http://localhost:8000/v1"
+export VLLM_API_KEY="your-vllm-api-key"
+export OPENAI_API_KEY="your-openai-api-key"  # for embeddings
+```
+
+## Benefits
+
+- **High Performance**: 2-24x faster inference than standard implementations
+- **Memory Efficient**: Optimized memory usage with PagedAttention
+- **Local Deployment**: Keep your data private and reduce API costs
+- **Easy Integration**: Drop-in replacement for other LLM providers
+- **Flexible**: Works with any model supported by vLLM
+
+## Troubleshooting
+
+1. **Server not responding**: Make sure vLLM server is running
+
+   ```bash
+   curl http://localhost:8000/health
+   ```
+
+2. **404 errors**: Ensure correct base URL format
+
+   ```python
+   "vllm_base_url": "http://localhost:8000/v1"  # Note the /v1
+   ```
+
+3. **Model not found**: Check model name matches server
+
+4. **Out of memory**: Try smaller models or reduce `max_model_len`
+
+   ```bash
+   vllm serve Qwen/Qwen2.5-32B-Instruct --max-model-len 4096
+   ```
+
+## Config
+
+All available parameters for the `vllm` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/xAI.mdx

@@ -19,7 +19,7 @@ config = {
     "llm": {
         "provider": "xai",
         "config": {
-            "model": "grok-2-latest",
+            "model": "grok-3-beta",
             "temperature": 0.1,
             "max_tokens": 2000,
         }

docs/components/llms/overview.mdx

@@ -12,7 +12,9 @@ To use a llm, you must provide a configuration to customize its usage. If no con
 
 For a comprehensive list of available parameters for llm configuration, please refer to [Config](./config).
 
-To view all supported llms, visit the [Supported LLMs](./models).
+## Supported LLMs
+
+See the list of supported LLMs below.
 
 <Note>
   All LLMs are supported in Python. The following LLMs are also supported in TypeScript: **OpenAI**, **Anthropic**, and **Groq**.
@@ -26,13 +28,14 @@ To view all supported llms, visit the [Supported LLMs](./models).
   <Card title="Together" href="/components/llms/models/together" />
   <Card title="Groq" href="/components/llms/models/groq" />
   <Card title="Litellm" href="/components/llms/models/litellm" />
-  <Card title="Mistral AI" href="/components/llms/models/mistral_ai" />
-  <Card title="Google AI" href="/components/llms/models/google_ai" />
+  <Card title="Mistral AI" href="/components/llms/models/mistral_AI" />
+  <Card title="Google AI" href="/components/llms/models/google_AI" />
   <Card title="AWS bedrock" href="/components/llms/models/aws_bedrock" />
-  <Card title="Gemini" href="/components/llms/models/gemini" />
   <Card title="DeepSeek" href="/components/llms/models/deepseek" />
   <Card title="xAI" href="/components/llms/models/xAI" />
+  <Card title="Sarvam AI" href="/components/llms/models/sarvam" />
   <Card title="LM Studio" href="/components/llms/models/lmstudio" />
+  <Card title="Langchain" href="/components/llms/models/langchain" />
 </CardGroup>
 
 ## Structured vs Unstructured Outputs

docs/components/rerankers/config.mdx

@@ -0,0 +1,145 @@
+---
+title: Configuration
+icon: "gear"
+iconType: "solid"
+---
+
+## How to define configurations?
+
+The `reranker` configuration is defined as an object with two main keys:
+- `provider`: The name of the reranker provider (e.g., "cohere", "sentence_transformer", "huggingface", "llm_reranker")
+- `config`: A nested dictionary containing provider-specific settings
+
+## Basic Configuration
+
+Here's how to configure a reranker with Mem0:
+
+```python
+from mem0 import Memory
+
+config = {
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "api_key": "your-api-key",
+            "top_n": 10,
+            "model": "rerank-english-v3.0"
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+```
+
+## Configuration Parameters
+
+| Parameter | Description | Required | Default |
+|-----------|-------------|----------|---------|
+| `provider` | Reranker provider name | Yes | - |
+| `config` | Provider-specific configuration | Yes | - |
+
+### Common Config Parameters
+
+| Parameter | Description | Providers |
+|-----------|-------------|-----------|
+| `api_key` | API key for the service | Cohere, Hugging Face |
+| `model` | Model name to use | All |
+| `top_n` | Number of results to return | All |
+| `device` | Device to run on (cpu/cuda/mps) | Sentence Transformer, Hugging Face |
+
+## Provider-Specific Examples
+
+### Cohere
+```python
+config = {
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "api_key": "your-cohere-api-key",
+            "model": "rerank-english-v3.0",
+            "top_n": 5
+        }
+    }
+}
+```
+
+### Sentence Transformer
+```python
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "device": "cpu",
+            "top_n": 10
+        }
+    }
+}
+```
+
+### Hugging Face
+```python
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "api_key": "your-hf-token",
+            "model": "BAAI/bge-reranker-large",
+            "top_n": 8
+        }
+    }
+}
+```
+
+### LLM Reranker
+```python
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "openai",
+                "config": {
+                    "model": "gpt-4",
+                    "api_key": "your-openai-key"
+                }
+            },
+            "top_n": 5
+        }
+    }
+}
+```
+
+## Advanced Configuration
+
+You can combine rerankers with other components:
+
+```python
+config = {
+    "llm": {
+        "provider": "openai",
+        "config": {
+            "model": "gpt-4",
+            "api_key": "your-openai-key"
+        }
+    },
+    "vector_store": {
+        "provider": "qdrant",
+        "config": {
+            "collection_name": "memories",
+            "host": "localhost",
+            "port": 6333
+        }
+    },
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "api_key": "your-cohere-key",
+            "model": "rerank-english-v3.0",
+            "top_n": 10
+        }
+    }
+}
+```
+
+For provider-specific configuration details, visit the individual reranker pages.

docs/components/rerankers/custom-prompts.mdx

@@ -0,0 +1,217 @@
+---
+title: Custom Prompts
+icon: "pencil"
+iconType: "solid"
+---
+
+When using LLM rerankers, you can customize the prompts used for ranking to better suit your specific use case and domain.
+
+## Default Prompt
+
+The default LLM reranker prompt is designed to be general-purpose:
+
+```
+Given a query and a list of memory entries, rank the memory entries based on their relevance to the query.
+Rate each memory on a scale of 1-10 where 10 is most relevant.
+
+Query: {query}
+
+Memory entries:
+{memories}
+
+Provide your ranking as a JSON array with scores for each memory.
+```
+
+## Custom Prompt Configuration
+
+You can provide a custom prompt template when configuring the LLM reranker:
+
+```python
+from mem0 import Memory
+
+custom_prompt = """
+You are an expert at ranking memories for a personal AI assistant.
+Given a user query and a list of memory entries, rank each memory based on:
+1. Direct relevance to the query
+2. Temporal relevance (recent memories may be more important)
+3. Emotional significance
+4. Actionability
+
+Query: {query}
+User Context: {user_context}
+
+Memory entries:
+{memories}
+
+Rate each memory from 1-10 and provide reasoning.
+Return as JSON: {{"rankings": [{{"index": 0, "score": 8, "reason": "..."}}]}}
+"""
+
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "openai",
+                "config": {
+                    "model": "gpt-4",
+                    "api_key": "your-openai-key"
+                }
+            },
+            "custom_prompt": custom_prompt,
+            "top_n": 5
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+```
+
+## Prompt Variables
+
+Your custom prompt can use the following variables:
+
+| Variable | Description |
+|----------|-------------|
+| `{query}` | The search query |
+| `{memories}` | The list of memory entries to rank |
+| `{user_id}` | The user ID (if available) |
+| `{user_context}` | Additional user context (if provided) |
+
+## Domain-Specific Examples
+
+### Customer Support
+```python
+customer_support_prompt = """
+You are ranking customer support conversation memories.
+Prioritize memories that:
+- Relate to the current customer issue
+- Show previous resolution patterns
+- Indicate customer preferences or constraints
+
+Query: {query}
+Customer Context: Previous interactions with this customer
+
+Memories:
+{memories}
+
+Rank each memory 1-10 based on support relevance.
+"""
+```
+
+### Educational Content
+```python
+educational_prompt = """
+Rank these learning memories for a student query.
+Consider:
+- Prerequisite knowledge requirements
+- Learning progression and difficulty
+- Relevance to current learning objectives
+
+Student Query: {query}
+Learning Context: {user_context}
+
+Available memories:
+{memories}
+
+Score each memory for educational value (1-10).
+"""
+```
+
+### Personal Assistant
+```python
+personal_assistant_prompt = """
+Rank personal memories for relevance to the user's query.
+Consider:
+- Recent vs. historical importance
+- Personal preferences and habits
+- Contextual relationships between memories
+
+Query: {query}
+Personal context: {user_context}
+
+Memories to rank:
+{memories}
+
+Provide relevance scores (1-10) with brief explanations.
+"""
+```
+
+## Advanced Prompt Techniques
+
+### Multi-Criteria Ranking
+```python
+multi_criteria_prompt = """
+Evaluate memories using multiple criteria:
+
+1. RELEVANCE (40%): How directly related to the query
+2. RECENCY (20%): How recent the memory is
+3. IMPORTANCE (25%): Personal or business significance
+4. ACTIONABILITY (15%): How useful for next steps
+
+Query: {query}
+Context: {user_context}
+
+Memories:
+{memories}
+
+For each memory, provide:
+- Overall score (1-10)
+- Breakdown by criteria
+- Final ranking recommendation
+
+Format: JSON with detailed scoring
+"""
+```
+
+### Contextual Ranking
+```python
+contextual_prompt = """
+Consider the following context when ranking memories:
+- Current user situation: {user_context}
+- Time of day: {current_time}
+- Recent activities: {recent_activities}
+
+Query: {query}
+
+Rank these memories considering both direct relevance and contextual appropriateness:
+{memories}
+
+Provide contextually-aware relevance scores (1-10).
+"""
+```
+
+## Best Practices
+
+1. **Be Specific**: Clearly define what makes a memory relevant for your use case
+2. **Use Examples**: Include examples in your prompt for better model understanding
+3. **Structure Output**: Specify the exact JSON format you want returned
+4. **Test Iteratively**: Refine your prompt based on actual ranking performance
+5. **Consider Token Limits**: Keep prompts concise while being comprehensive
+
+## Prompt Testing
+
+You can test different prompts by comparing ranking results:
+
+```python
+# Test multiple prompt variations
+prompts = [
+    default_prompt,
+    custom_prompt_v1,
+    custom_prompt_v2
+]
+
+for i, prompt in enumerate(prompts):
+    config["reranker"]["config"]["custom_prompt"] = prompt
+    memory = Memory.from_config(config)
+
+    results = memory.search("test query", user_id="test_user")
+    print(f"Prompt {i+1} results: {results}")
+```
+
+## Common Issues
+
+- **Too Long**: Keep prompts under token limits for your chosen LLM
+- **Too Vague**: Be specific about ranking criteria
+- **Inconsistent Format**: Ensure JSON output format is clearly specified
+- **Missing Context**: Include relevant variables for your use case

docs/components/rerankers/models/cohere.mdx

@@ -0,0 +1,116 @@
+---
+title: Cohere
+---
+
+Cohere provides state-of-the-art reranking models that can significantly improve the relevance of search results. Cohere's rerankers are optimized for various languages and use cases.
+
+## Usage
+
+To use Cohere's reranker with Mem0:
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["COHERE_API_KEY"] = "your-cohere-api-key"
+
+config = {
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "api_key": "your-cohere-api-key",  # Can also use environment variable
+            "model": "rerank-english-v3.0",
+            "top_n": 10
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+
+# Use memory as usual
+memory.add("I love playing basketball", user_id="alice")
+memory.add("I enjoy watching movies", user_id="alice")
+
+# Search will now use Cohere reranking
+results = memory.search("What sports does Alice like?", user_id="alice")
+```
+
+## Configuration
+
+| Parameter | Description | Default |
+|-----------|-------------|---------|
+| `api_key` | Cohere API key | Required |
+| `model` | Cohere rerank model | `rerank-english-v3.0` |
+| `top_n` | Number of results to return | `10` |
+
+## Available Models
+
+- `rerank-english-v3.0`: Latest English reranking model
+- `rerank-multilingual-v3.0`: Multilingual reranking model
+- `rerank-english-v2.0`: Previous English model
+- `rerank-multilingual-v2.0`: Previous multilingual model
+
+## Example with Different Models
+
+### English Reranker
+```python
+config = {
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "api_key": "your-cohere-api-key",
+            "model": "rerank-english-v3.0",
+            "top_n": 5
+        }
+    }
+}
+```
+
+### Multilingual Reranker
+```python
+config = {
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "api_key": "your-cohere-api-key",
+            "model": "rerank-multilingual-v3.0",
+            "top_n": 8
+        }
+    }
+}
+```
+
+## Environment Variables
+
+You can set your Cohere API key as an environment variable:
+
+```bash
+export COHERE_API_KEY="your-cohere-api-key"
+```
+
+Then use the config without specifying the API key:
+
+```python
+config = {
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "model": "rerank-english-v3.0",
+            "top_n": 10
+        }
+    }
+}
+```
+
+## Getting Your API Key
+
+1. Sign up at [Cohere](https://cohere.ai/)
+2. Navigate to the API keys section in your dashboard
+3. Generate a new API key
+4. Use this key in your configuration
+
+## Performance Considerations
+
+- Cohere rerankers work best with 10-100 candidate documents
+- Higher `top_n` values provide more comprehensive reranking but may increase latency
+- The v3.0 models generally provide better performance than v2.0 models

docs/components/rerankers/models/huggingface.mdx

@@ -0,0 +1,352 @@
+---
+title: Hugging Face Reranker
+description: 'Access thousands of reranking models from Hugging Face Hub'
+icon: "face-smile"
+iconType: "solid"
+---
+
+## Overview
+
+The Hugging Face reranker provider gives you access to thousands of reranking models available on the Hugging Face Hub. This includes popular models like BAAI's BGE rerankers and other state-of-the-art cross-encoder models.
+
+## Configuration
+
+### Basic Setup
+
+```python
+from mem0 import Memory
+
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-base",
+            "device": "cpu"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+```
+
+### Configuration Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `model` | str | Required | Hugging Face model identifier |
+| `device` | str | "cpu" | Device to run model on ("cpu", "cuda", "mps") |
+| `batch_size` | int | 32 | Batch size for processing |
+| `max_length` | int | 512 | Maximum input sequence length |
+| `trust_remote_code` | bool | False | Allow remote code execution |
+
+### Advanced Configuration
+
+```python
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-large",
+            "device": "cuda",
+            "batch_size": 16,
+            "max_length": 512,
+            "trust_remote_code": False,
+            "model_kwargs": {
+                "torch_dtype": "float16"
+            }
+        }
+    }
+}
+```
+
+## Popular Models
+
+### BGE Rerankers (Recommended)
+
+```python
+# Base model - good balance of speed and quality
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-base",
+            "device": "cuda"
+        }
+    }
+}
+
+# Large model - better quality, slower
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-large",
+            "device": "cuda"
+        }
+    }
+}
+
+# v2 models - latest improvements
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-v2-m3",
+            "device": "cuda"
+        }
+    }
+}
+```
+
+### Multilingual Models
+
+```python
+# Multilingual BGE reranker
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-v2-multilingual",
+            "device": "cuda"
+        }
+    }
+}
+```
+
+### Domain-Specific Models
+
+```python
+# For code search
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "microsoft/codebert-base",
+            "device": "cuda"
+        }
+    }
+}
+
+# For biomedical content
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "dmis-lab/biobert-base-cased-v1.1",
+            "device": "cuda"
+        }
+    }
+}
+```
+
+## Usage Examples
+
+### Basic Usage
+
+```python
+from mem0 import Memory
+
+m = Memory.from_config(config)
+
+# Add some memories
+m.add("I love hiking in the mountains", user_id="alice")
+m.add("Pizza is my favorite food", user_id="alice")
+m.add("I enjoy reading science fiction books", user_id="alice")
+
+# Search with reranking
+results = m.search(
+    "What outdoor activities do I enjoy?",
+    user_id="alice",
+    rerank=True
+)
+
+for result in results["results"]:
+    print(f"Memory: {result['memory']}")
+    print(f"Score: {result['score']:.3f}")
+```
+
+### Batch Processing
+
+```python
+# Process multiple queries efficiently
+queries = [
+    "What are my hobbies?",
+    "What food do I like?",
+    "What books interest me?"
+]
+
+results = []
+for query in queries:
+    result = m.search(query, user_id="alice", rerank=True)
+    results.append(result)
+```
+
+## Performance Optimization
+
+### GPU Acceleration
+
+```python
+# Use GPU for better performance
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-base",
+            "device": "cuda",
+            "batch_size": 64,  # Increase batch size for GPU
+        }
+    }
+}
+```
+
+### Memory Optimization
+
+```python
+# For limited memory environments
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-base",
+            "device": "cpu",
+            "batch_size": 8,   # Smaller batch size
+            "max_length": 256, # Shorter sequences
+            "model_kwargs": {
+                "torch_dtype": "float16"  # Half precision
+            }
+        }
+    }
+}
+```
+
+## Model Comparison
+
+| Model | Size | Quality | Speed | Memory | Best For |
+|-------|------|---------|-------|---------|----------|
+| bge-reranker-base | 278M | Good | Fast | Low | General use |
+| bge-reranker-large | 560M | Better | Medium | Medium | High quality needs |
+| bge-reranker-v2-m3 | 568M | Best | Medium | Medium | Latest improvements |
+| bge-reranker-v2-multilingual | 568M | Good | Medium | Medium | Multiple languages |
+
+## Error Handling
+
+```python
+try:
+    results = m.search(
+        "test query",
+        user_id="alice",
+        rerank=True
+    )
+except Exception as e:
+    print(f"Reranking failed: {e}")
+    # Fall back to vector search only
+    results = m.search(
+        "test query",
+        user_id="alice",
+        rerank=False
+    )
+```
+
+## Custom Models
+
+### Using Private Models
+
+```python
+# Use a private model from Hugging Face
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "your-org/custom-reranker",
+            "device": "cuda",
+            "use_auth_token": "your-hf-token"
+        }
+    }
+}
+```
+
+### Local Model Path
+
+```python
+# Use a locally downloaded model
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "/path/to/local/model",
+            "device": "cuda"
+        }
+    }
+}
+```
+
+## Best Practices
+
+1. **Choose the Right Model**: Balance quality vs speed based on your needs
+2. **Use GPU**: Significantly faster than CPU for larger models
+3. **Optimize Batch Size**: Tune based on your hardware capabilities
+4. **Monitor Memory**: Watch GPU/CPU memory usage with large models
+5. **Cache Models**: Download once and reuse to avoid repeated downloads
+
+## Troubleshooting
+
+### Common Issues
+
+**Out of Memory Error**
+```python
+# Reduce batch size and sequence length
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-base",
+            "batch_size": 4,
+            "max_length": 256
+        }
+    }
+}
+```
+
+**Model Download Issues**
+```python
+# Set cache directory
+import os
+os.environ["TRANSFORMERS_CACHE"] = "/path/to/cache"
+
+# Or use offline mode
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-base",
+            "local_files_only": True
+        }
+    }
+}
+```
+
+**CUDA Not Available**
+```python
+import torch
+
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-base",
+            "device": "cuda" if torch.cuda.is_available() else "cpu"
+        }
+    }
+}
+```
+
+## Next Steps
+
+<CardGroup cols={2}>
+  <Card title="Reranker Overview" icon="sort" href="/components/rerankers/overview">
+    Learn about reranking concepts
+  </Card>
+  <Card title="Configuration Guide" icon="gear" href="/components/rerankers/config">
+    Detailed configuration options
+  </Card>
+</CardGroup>

docs/components/rerankers/models/llm_reranker.mdx

@@ -0,0 +1,491 @@
+---
+title: LLM Reranker
+description: 'Use any language model as a reranker with custom prompts'
+icon: "robot"
+iconType: "solid"
+---
+
+## Overview
+
+The LLM reranker allows you to use any supported language model as a reranker. This approach uses prompts to instruct the LLM to score and rank memories based on their relevance to the query. While slower than specialized rerankers, it offers maximum flexibility and can be fine-tuned with custom prompts.
+
+## Configuration
+
+### Basic Setup
+
+```python
+from mem0 import Memory
+
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "openai",
+                "config": {
+                    "model": "gpt-4",
+                    "api_key": "your-openai-api-key"
+                }
+            }
+        }
+    }
+}
+
+m = Memory.from_config(config)
+```
+
+### Configuration Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `llm` | dict | Required | LLM configuration object |
+| `top_k` | int | 10 | Number of results to rerank |
+| `temperature` | float | 0.0 | LLM temperature for consistency |
+| `custom_prompt` | str | None | Custom reranking prompt |
+| `score_range` | tuple | (0, 10) | Score range for relevance |
+
+### Advanced Configuration
+
+```python
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "anthropic",
+                "config": {
+                    "model": "claude-3-sonnet-20240229",
+                    "api_key": "your-anthropic-api-key"
+                }
+            },
+            "top_k": 15,
+            "temperature": 0.0,
+            "score_range": (1, 5),
+            "custom_prompt": """
+            Rate the relevance of each memory to the query on a scale of 1-5.
+            Consider semantic similarity, context, and practical utility.
+            Only provide the numeric score.
+            """
+        }
+    }
+}
+```
+
+## Supported LLM Providers
+
+### OpenAI
+
+```python
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "openai",
+                "config": {
+                    "model": "gpt-4",
+                    "api_key": "your-openai-api-key",
+                    "temperature": 0.0
+                }
+            }
+        }
+    }
+}
+```
+
+### Anthropic
+
+```python
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "anthropic",
+                "config": {
+                    "model": "claude-3-sonnet-20240229",
+                    "api_key": "your-anthropic-api-key"
+                }
+            }
+        }
+    }
+}
+```
+
+### Ollama (Local)
+
+```python
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "ollama",
+                "config": {
+                    "model": "llama2",
+                    "ollama_base_url": "http://localhost:11434"
+                }
+            }
+        }
+    }
+}
+```
+
+### Azure OpenAI
+
+```python
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "azure_openai",
+                "config": {
+                    "model": "gpt-4",
+                    "api_key": "your-azure-api-key",
+                    "azure_endpoint": "https://your-resource.openai.azure.com/",
+                    "azure_deployment": "gpt-4-deployment"
+                }
+            }
+        }
+    }
+}
+```
+
+## Custom Prompts
+
+### Default Prompt Behavior
+
+The default prompt asks the LLM to score relevance on a 0-10 scale:
+
+```
+Given a query and a memory, rate how relevant the memory is to answering the query.
+Score from 0 (completely irrelevant) to 10 (perfectly relevant).
+Only provide the numeric score.
+
+Query: {query}
+Memory: {memory}
+Score:
+```
+
+### Custom Prompt Examples
+
+#### Domain-Specific Scoring
+
+```python
+custom_prompt = """
+You are a medical information specialist. Rate how relevant each memory is for answering the medical query.
+Consider clinical accuracy, specificity, and practical applicability.
+Rate from 1-10 where:
+- 1-3: Irrelevant or potentially harmful
+- 4-6: Somewhat relevant but incomplete
+- 7-8: Relevant and helpful
+- 9-10: Highly relevant and clinically useful
+
+Query: {query}
+Memory: {memory}
+Score:
+"""
+
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "openai",
+                "config": {
+                    "model": "gpt-4",
+                    "api_key": "your-api-key"
+                }
+            },
+            "custom_prompt": custom_prompt
+        }
+    }
+}
+```
+
+#### Contextual Relevance
+
+```python
+contextual_prompt = """
+Rate how well this memory answers the specific question asked.
+Consider:
+- Direct relevance to the question
+- Completeness of information
+- Recency and accuracy
+- Practical usefulness
+
+Rate 1-5:
+1 = Not relevant
+2 = Slightly relevant
+3 = Moderately relevant
+4 = Very relevant
+5 = Perfectly answers the question
+
+Query: {query}
+Memory: {memory}
+Score:
+"""
+```
+
+#### Conversational Context
+
+```python
+conversation_prompt = """
+You are helping evaluate which memories are most useful for a conversational AI assistant.
+Rate how helpful this memory would be for generating a relevant response.
+
+Consider:
+- Direct relevance to user's intent
+- Emotional appropriateness
+- Factual accuracy
+- Conversation flow
+
+Rate 0-10:
+Query: {query}
+Memory: {memory}
+Score:
+"""
+```
+
+## Usage Examples
+
+### Basic Usage
+
+```python
+from mem0 import Memory
+
+m = Memory.from_config(config)
+
+# Add memories
+m.add("I'm allergic to peanuts", user_id="alice")
+m.add("I love Italian food", user_id="alice")
+m.add("I'm vegetarian", user_id="alice")
+
+# Search with LLM reranking
+results = m.search(
+    "What foods should I avoid?",
+    user_id="alice",
+    rerank=True
+)
+
+for result in results["results"]:
+    print(f"Memory: {result['memory']}")
+    print(f"LLM Score: {result['score']:.2f}")
+```
+
+### Batch Processing with Error Handling
+
+```python
+def safe_llm_rerank_search(query, user_id, max_retries=3):
+    for attempt in range(max_retries):
+        try:
+            return m.search(query, user_id=user_id, rerank=True)
+        except Exception as e:
+            print(f"Attempt {attempt + 1} failed: {e}")
+            if attempt == max_retries - 1:
+                # Fall back to vector search
+                return m.search(query, user_id=user_id, rerank=False)
+
+# Use the safe function
+results = safe_llm_rerank_search("What are my preferences?", "alice")
+```
+
+## Performance Considerations
+
+### Speed vs Quality Trade-offs
+
+| Model Type | Speed | Quality | Cost | Best For |
+|------------|-------|---------|------|----------|
+| GPT-3.5 Turbo | Fast | Good | Low | High-volume applications |
+| GPT-4 | Medium | Excellent | Medium | Quality-critical applications |
+| Claude 3 Sonnet | Medium | Excellent | Medium | Balanced performance |
+| Ollama Local | Variable | Good | Free | Privacy-sensitive applications |
+
+### Optimization Strategies
+
+```python
+# Fast configuration for high-volume use
+fast_config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "openai",
+                "config": {
+                    "model": "gpt-3.5-turbo",
+                    "api_key": "your-api-key"
+                }
+            },
+            "top_k": 5,  # Limit candidates
+            "temperature": 0.0
+        }
+    }
+}
+
+# High-quality configuration
+quality_config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "openai",
+                "config": {
+                    "model": "gpt-4",
+                    "api_key": "your-api-key"
+                }
+            },
+            "top_k": 15,
+            "temperature": 0.0
+        }
+    }
+}
+```
+
+## Advanced Use Cases
+
+### Multi-Step Reasoning
+
+```python
+reasoning_prompt = """
+Evaluate this memory's relevance using multi-step reasoning:
+
+1. What is the main intent of the query?
+2. What key information does the memory contain?
+3. How directly does the memory address the query?
+4. What additional context might be needed?
+
+Based on this analysis, rate relevance 1-10:
+
+Query: {query}
+Memory: {memory}
+
+Analysis:
+Step 1 (Intent):
+Step 2 (Information):
+Step 3 (Directness):
+Step 4 (Context):
+Final Score:
+"""
+```
+
+### Comparative Ranking
+
+```python
+comparative_prompt = """
+You will see a query and multiple memories. Rank them in order of relevance.
+Consider which memories best answer the question and would be most helpful.
+
+Query: {query}
+
+Memories to rank:
+{memories}
+
+Provide scores 1-10 for each memory, considering their relative usefulness.
+"""
+```
+
+### Emotional Intelligence
+
+```python
+emotional_prompt = """
+Consider both factual relevance and emotional appropriateness.
+Rate how suitable this memory is for responding to the user's query.
+
+Factors to consider:
+- Factual accuracy and relevance
+- Emotional tone and sensitivity
+- User's likely emotional state
+- Appropriateness of response
+
+Query: {query}
+Memory: {memory}
+Emotional Context: {context}
+Score (1-10):
+"""
+```
+
+## Error Handling and Fallbacks
+
+```python
+class RobustLLMReranker:
+    def __init__(self, primary_config, fallback_config=None):
+        self.primary = Memory.from_config(primary_config)
+        self.fallback = Memory.from_config(fallback_config) if fallback_config else None
+
+    def search(self, query, user_id, max_retries=2):
+        # Try primary LLM reranker
+        for attempt in range(max_retries):
+            try:
+                return self.primary.search(query, user_id=user_id, rerank=True)
+            except Exception as e:
+                print(f"Primary reranker attempt {attempt + 1} failed: {e}")
+
+        # Try fallback reranker
+        if self.fallback:
+            try:
+                return self.fallback.search(query, user_id=user_id, rerank=True)
+            except Exception as e:
+                print(f"Fallback reranker failed: {e}")
+
+        # Final fallback: vector search only
+        return self.primary.search(query, user_id=user_id, rerank=False)
+
+# Usage
+primary_config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {"llm": {"provider": "openai", "config": {"model": "gpt-4"}}}
+    }
+}
+
+fallback_config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {"llm": {"provider": "openai", "config": {"model": "gpt-3.5-turbo"}}}
+    }
+}
+
+reranker = RobustLLMReranker(primary_config, fallback_config)
+results = reranker.search("What are my preferences?", "alice")
+```
+
+## Best Practices
+
+1. **Use Specific Prompts**: Tailor prompts to your domain and use case
+2. **Set Temperature to 0**: Ensure consistent scoring across runs
+3. **Limit Top-K**: Don't rerank too many candidates to control costs
+4. **Implement Fallbacks**: Always have a backup plan for API failures
+5. **Monitor Costs**: Track API usage, especially with expensive models
+6. **Cache Results**: Consider caching reranking results for repeated queries
+7. **Test Prompts**: Experiment with different prompts to find what works best
+
+## Troubleshooting
+
+### Common Issues
+
+**Inconsistent Scores**
+- Set temperature to 0.0
+- Use more specific prompts
+- Consider using multiple calls and averaging
+
+**API Rate Limits**
+- Implement exponential backoff
+- Use cheaper models for high-volume scenarios
+- Add retry logic with delays
+
+**Poor Ranking Quality**
+- Refine your custom prompt
+- Try different LLM models
+- Add examples to your prompt
+
+## Next Steps
+
+<CardGroup cols={2}>
+  <Card title="Custom Prompts Guide" icon="pencil" href="/components/rerankers/custom-prompts">
+    Learn to craft effective reranking prompts
+  </Card>
+  <Card title="Performance Optimization" icon="bolt" href="/components/rerankers/optimization">
+    Optimize LLM reranker performance
+  </Card>
+</CardGroup>

docs/components/rerankers/models/sentence_transformer.mdx

@@ -0,0 +1,162 @@
+---
+title: Sentence Transformer
+---
+
+Sentence Transformer rerankers use cross-encoder models that are specifically designed for ranking tasks. These models can run locally and provide good reranking performance without external API calls.
+
+## Usage
+
+To use Sentence Transformer reranker with Mem0:
+
+```python
+from mem0 import Memory
+
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "device": "cpu",
+            "top_n": 10
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+
+# Use memory as usual
+memory.add("I love playing basketball", user_id="alice")
+memory.add("I enjoy watching movies", user_id="alice")
+
+# Search will now use Sentence Transformer reranking
+results = memory.search("What sports does Alice like?", user_id="alice")
+```
+
+## Configuration
+
+| Parameter | Description | Default |
+|-----------|-------------|---------|
+| `model` | Sentence Transformer cross-encoder model | `cross-encoder/ms-marco-MiniLM-L-6-v2` |
+| `device` | Device to run on (`cpu`, `cuda`, `mps`) | `cpu` |
+| `top_n` | Number of results to return | `10` |
+
+## Popular Models
+
+### Lightweight Models
+- `cross-encoder/ms-marco-MiniLM-L-6-v2`: Fast and efficient
+- `cross-encoder/ms-marco-MiniLM-L-4-v2`: Even faster, slightly lower accuracy
+- `cross-encoder/ms-marco-MiniLM-L-2-v2`: Fastest, good for real-time applications
+
+### High-Performance Models
+- `cross-encoder/ms-marco-electra-base`: Better accuracy, larger model
+- `ms-marco-MiniLM-L-12-v2`: Balanced performance and speed
+- `cross-encoder/qnli-electra-base`: Good for question-answering tasks
+
+## Device Configuration
+
+### CPU Usage
+```python
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "device": "cpu",
+            "top_n": 10
+        }
+    }
+}
+```
+
+### GPU Usage (CUDA)
+```python
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-electra-base",
+            "device": "cuda",
+            "top_n": 15
+        }
+    }
+}
+```
+
+### Apple Silicon (MPS)
+```python
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "device": "mps",
+            "top_n": 10
+        }
+    }
+}
+```
+
+## Installation
+
+The sentence-transformers library is required:
+
+```bash
+pip install sentence-transformers
+```
+
+For GPU support with CUDA:
+```bash
+pip install sentence-transformers torch
+```
+
+## Performance Optimization
+
+### Model Selection
+- Use MiniLM models for faster inference
+- Use larger models (electra-base) for better accuracy
+- Consider the trade-off between speed and quality
+
+### Device Optimization
+- Use GPU (`cuda` or `mps`) for larger models
+- CPU is sufficient for MiniLM models
+- Batch processing improves GPU utilization
+
+### Memory Considerations
+```python
+# For memory-constrained environments
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-2-v2",  # Smallest model
+            "device": "cpu",
+            "top_n": 5  # Fewer results to process
+        }
+    }
+}
+```
+
+## Custom Models
+
+You can use any Sentence Transformer cross-encoder model:
+
+```python
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "your-custom-model-name",
+            "device": "cpu",
+            "top_n": 10
+        }
+    }
+}
+```
+
+## Advantages
+
+- **Local Processing**: No external API calls required
+- **Privacy**: Data stays on your infrastructure
+- **Cost Effective**: No per-request charges
+- **Fast**: Especially with GPU acceleration
+- **Customizable**: Can fine-tune on your specific data

docs/components/rerankers/optimization.mdx

@@ -0,0 +1,312 @@
+---
+title: Performance Optimization
+icon: "bolt"
+iconType: "solid"
+---
+
+Optimizing reranker performance is crucial for maintaining fast search response times while improving result quality. This guide covers best practices for different reranker types.
+
+## General Optimization Principles
+
+### Candidate Set Size
+The number of candidates sent to the reranker significantly impacts performance:
+
+```python
+# Optimal candidate sizes for different rerankers
+config_map = {
+    "cohere": {"initial_candidates": 100, "top_n": 10},
+    "sentence_transformer": {"initial_candidates": 50, "top_n": 10},
+    "huggingface": {"initial_candidates": 30, "top_n": 5},
+    "llm_reranker": {"initial_candidates": 20, "top_n": 5}
+}
+```
+
+### Batching Strategy
+Process multiple queries efficiently:
+
+```python
+# Configure for batch processing
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "batch_size": 16,  # Process multiple candidates at once
+            "top_n": 10
+        }
+    }
+}
+```
+
+## Provider-Specific Optimizations
+
+### Cohere Optimization
+
+```python
+# Optimized Cohere configuration
+config = {
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "model": "rerank-english-v3.0",
+            "top_n": 10,
+            "max_chunks_per_doc": 10,  # Limit chunk processing
+            "return_documents": False   # Reduce response size
+        }
+    }
+}
+```
+
+**Best Practices:**
+- Use v3.0 models for better speed/accuracy balance
+- Limit candidates to 100 or fewer
+- Cache API responses when possible
+- Monitor API rate limits
+
+### Sentence Transformer Optimization
+
+```python
+# Performance-optimized configuration
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "device": "cuda",  # Use GPU when available
+            "batch_size": 32,
+            "top_n": 10,
+            "max_length": 512  # Limit input length
+        }
+    }
+}
+```
+
+**Device Optimization:**
+```python
+import torch
+
+# Auto-detect best device
+device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "device": device,
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2"
+        }
+    }
+}
+```
+
+### Hugging Face Optimization
+
+```python
+# Optimized for Hugging Face models
+config = {
+    "reranker": {
+        "provider": "huggingface",
+        "config": {
+            "model": "BAAI/bge-reranker-base",
+            "use_fp16": True,  # Half precision for speed
+            "max_length": 512,
+            "batch_size": 8,
+            "top_n": 10
+        }
+    }
+}
+```
+
+### LLM Reranker Optimization
+
+```python
+# Optimized LLM reranker configuration
+config = {
+    "reranker": {
+        "provider": "llm_reranker",
+        "config": {
+            "llm": {
+                "provider": "openai",
+                "config": {
+                    "model": "gpt-3.5-turbo",  # Faster than gpt-4
+                    "temperature": 0,  # Deterministic results
+                    "max_tokens": 500  # Limit response length
+                }
+            },
+            "batch_ranking": True,  # Rank multiple at once
+            "top_n": 5,  # Fewer results for faster processing
+            "timeout": 10  # Request timeout
+        }
+    }
+}
+```
+
+## Performance Monitoring
+
+### Latency Tracking
+```python
+import time
+from mem0 import Memory
+
+def measure_reranker_performance(config, queries, user_id):
+    memory = Memory.from_config(config)
+
+    latencies = []
+    for query in queries:
+        start_time = time.time()
+        results = memory.search(query, user_id=user_id)
+        latency = time.time() - start_time
+        latencies.append(latency)
+
+    return {
+        "avg_latency": sum(latencies) / len(latencies),
+        "max_latency": max(latencies),
+        "min_latency": min(latencies)
+    }
+```
+
+### Memory Usage Monitoring
+```python
+import psutil
+import os
+
+def monitor_memory_usage():
+    process = psutil.Process(os.getpid())
+    return {
+        "memory_mb": process.memory_info().rss / 1024 / 1024,
+        "memory_percent": process.memory_percent()
+    }
+```
+
+## Caching Strategies
+
+### Result Caching
+```python
+from functools import lru_cache
+import hashlib
+
+class CachedReranker:
+    def __init__(self, config):
+        self.memory = Memory.from_config(config)
+        self.cache_size = 1000
+
+    @lru_cache(maxsize=1000)
+    def search_cached(self, query_hash, user_id):
+        return self.memory.search(query, user_id=user_id)
+
+    def search(self, query, user_id):
+        query_hash = hashlib.md5(f"{query}_{user_id}".encode()).hexdigest()
+        return self.search_cached(query_hash, user_id)
+```
+
+### Model Caching
+```python
+# Pre-load models to avoid initialization overhead
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "cache_folder": "/path/to/model/cache",
+            "device": "cuda"
+        }
+    }
+}
+```
+
+## Parallel Processing
+
+### Async Configuration
+```python
+import asyncio
+from mem0 import Memory
+
+async def parallel_search(config, queries, user_id):
+    memory = Memory.from_config(config)
+
+    # Process multiple queries concurrently
+    tasks = [
+        memory.search_async(query, user_id=user_id)
+        for query in queries
+    ]
+
+    results = await asyncio.gather(*tasks)
+    return results
+```
+
+## Hardware Optimization
+
+### GPU Configuration
+```python
+# Optimize for GPU usage
+import torch
+
+if torch.cuda.is_available():
+    torch.cuda.set_per_process_memory_fraction(0.8)  # Reserve GPU memory
+
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "device": "cuda",
+            "model": "cross-encoder/ms-marco-electra-base",
+            "batch_size": 64,  # Larger batch for GPU
+            "fp16": True  # Half precision
+        }
+    }
+}
+```
+
+### CPU Optimization
+```python
+import torch
+
+# Optimize CPU threading
+torch.set_num_threads(4)  # Adjust based on your CPU
+
+config = {
+    "reranker": {
+        "provider": "sentence_transformer",
+        "config": {
+            "device": "cpu",
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "num_workers": 4  # Parallel processing
+        }
+    }
+}
+```
+
+## Benchmarking Different Configurations
+
+```python
+def benchmark_rerankers():
+    configs = [
+        {"provider": "cohere", "model": "rerank-english-v3.0"},
+        {"provider": "sentence_transformer", "model": "cross-encoder/ms-marco-MiniLM-L-6-v2"},
+        {"provider": "huggingface", "model": "BAAI/bge-reranker-base"}
+    ]
+
+    test_queries = ["sample query 1", "sample query 2", "sample query 3"]
+
+    results = {}
+    for config in configs:
+        provider = config["provider"]
+        performance = measure_reranker_performance(
+            {"reranker": {"provider": provider, "config": config}},
+            test_queries,
+            "test_user"
+        )
+        results[provider] = performance
+
+    return results
+```
+
+## Production Best Practices
+
+1. **Model Selection**: Choose the right balance of speed vs. accuracy
+2. **Resource Allocation**: Monitor CPU/GPU usage and memory consumption
+3. **Error Handling**: Implement fallbacks for reranker failures
+4. **Load Balancing**: Distribute reranking load across multiple instances
+5. **Monitoring**: Track latency, throughput, and error rates
+6. **Caching**: Cache frequent queries and model predictions
+7. **Batch Processing**: Group similar queries for efficient processing

docs/components/rerankers/overview.mdx

@@ -0,0 +1,52 @@
+---
+title: Overview
+icon: "info"
+iconType: "solid"
+---
+
+Rerankers enhance the quality of search results by re-ordering the initial retrieval results using more sophisticated scoring mechanisms. They act as a secondary ranking layer that can significantly improve the relevance of retrieved memories.
+
+## How Rerankers Work
+
+1. **Initial Retrieval**: Vector search returns candidate memories based on semantic similarity
+2. **Reranking**: The reranker evaluates and re-scores these candidates using more complex criteria
+3. **Final Results**: Returns the top-k memories with improved relevance ordering
+
+## Benefits
+
+- **Improved Precision**: Better ranking of relevant memories
+- **Context Awareness**: More sophisticated understanding of query-memory relationships
+- **Performance**: Can improve results without changing the underlying vector store
+
+## Supported Rerankers
+
+Mem0 supports several reranker models:
+
+<CardGroup cols={2}>
+  <Card title="Cohere" href="/components/rerankers/models/cohere" />
+  <Card title="Sentence Transformer" href="/components/rerankers/models/sentence_transformer" />
+  <Card title="Hugging Face" href="/components/rerankers/models/huggingface" />
+  <Card title="LLM Reranker" href="/components/rerankers/models/llm_reranker" />
+</CardGroup>
+
+## Usage
+
+Rerankers are configured as part of the memory configuration:
+
+```python
+from mem0 import Memory
+
+config = {
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "api_key": "your-api-key",
+            "top_n": 10
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+```
+
+For detailed configuration options, see the [Config](./config) page.

docs/components/vectordbs/config.mdx

@@ -8,7 +8,7 @@ iconType: "solid"
 
 The `config` is defined as an object with two main keys:
 - `vector_store`: Specifies the vector database provider and its configuration
-  - `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus","azure_ai_search", "vertex_ai_vector_search")
+  - `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus", "upstash_vector", "azure_ai_search", "vertex_ai_vector_search", "valkey")
   - `config`: A nested dictionary containing provider-specific settings
 
 

docs/components/vectordbs/dbs/azure.mdx

@@ -0,0 +1,179 @@
+---
+title: Azure AI Search
+---
+
+[Azure AI Search](https://learn.microsoft.com/azure/search/search-what-is-azure-search/) (formerly known as "Azure Cognitive Search") provides secure information retrieval at scale over user-owned content in traditional and generative AI search applications.
+
+## Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"   # This key is used for embedding purpose
+
+config = {
+    "vector_store": {
+        "provider": "azure_ai_search",
+        "config": {
+            "service_name": "<your-azure-ai-search-service-name>",
+            "api_key": "<your-api-key>",
+            "collection_name": "mem0", 
+            "embedding_model_dims": 1536
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+## Using binary compression for large vector collections
+
+```python
+config = {
+    "vector_store": {
+        "provider": "azure_ai_search",
+        "config": {
+            "service_name": "<your-azure-ai-search-service-name>",
+            "api_key": "<your-api-key>",
+            "collection_name": "mem0", 
+            "embedding_model_dims": 1536,
+            "compression_type": "binary",
+            "use_float16": True  # Use half precision for storage efficiency
+        }
+    }
+}
+```
+
+## Using hybrid search
+
+```python
+config = {
+    "vector_store": {
+        "provider": "azure_ai_search",
+        "config": {
+            "service_name": "<your-azure-ai-search-service-name>",
+            "api_key": "<your-api-key>",
+            "collection_name": "mem0", 
+            "embedding_model_dims": 1536,
+            "hybrid_search": True,
+            "vector_filter_mode": "postFilter"
+        }
+    }
+}
+```
+
+## Using Azure Identity for Authentication
+As an alternative to using an API key, the Azure Identity credential chain can be used to authenticate with Azure OpenAI. The list below shows the order of precedence for credential application:
+
+1. **Environment Credential:**
+Azure client ID, secret, tenant ID, or certificate in environment variables for service principal authentication.
+
+2. **Workload Identity Credential:**
+Utilizes Azure Workload Identity (relevant for Kubernetes and Azure workloads).
+
+3. **Managed Identity Credential:**
+Authenticates as a Managed Identity (for apps/services hosted in Azure with Managed Identity enabled), this is the most secure production credential.
+
+4. **Shared Token Cache Credential / Visual Studio Credential (Windows only):**
+Uses cached credentials from Visual Studio sign-ins (and sometimes VS Code if SSO is enabled).
+
+5. **Azure CLI Credential:**
+Uses the currently logged-in user from the Azure CLI (`az login`), this is the most common development credential.
+
+6. **Azure PowerShell Credential:**
+Uses the identity from Azure PowerShell (`Connect-AzAccount`).
+
+7. **Azure Developer CLI Credential:**
+Uses the session from Azure Developer CLI (`azd auth login`).
+
+<Note> If an API is provided, it will be used for authentication over an Azure Identity </Note>
+To enable Role-Based Access Control (RBAC) for Azure AI Search, follow these steps:
+
+1. In the Azure Portal, navigate to your **Azure AI Search** service.
+2. In the left menu, select **Settings** > **Keys**.
+3. Change the authentication setting to **Role-based access control**, or **Both** if you need API key compatibility. The default is “Key-based authentication”—you must switch it to use Azure roles.
+4. **Go to Access Control (IAM):**
+    - In the Azure Portal, select your Search service.
+    - Click **Access Control (IAM)** on the left.
+5. **Add a Role Assignment:**
+    - Click **Add** > **Add role assignment**.
+6. **Choose Role:**
+    - Mem0 requires the **Search Index Data Contributor** and **Search Service Contributor** role.
+7. **Choose Member** 
+    - To assign to a User, Group, Service Principle or Managed Identity:
+        - For production it is recommended to use a service principal or managed identity.
+            - For a service principal: select **User, group, or service principal** and search for the service principal.
+            - For a managed identity: select **Managed identity** and choose the managed identity.
+        - For development, you can assign the role to a user account.
+            - For development: select ***User, group, or service principal** and pick a Azure Entra ID account (the same used with `az login`).
+8. **Complete the Assignment:**
+    - Click **Review + Assign**.
+
+If you are using Azure Identity, do not set the `api_key` in the configuration.
+```python
+config = {
+    "vector_store": {
+        "provider": "azure_ai_search",
+        "config": {
+            "service_name": "<your-azure-ai-search-service-name>",
+            "collection_name": "mem0", 
+            "embedding_model_dims": 1536,
+            "compression_type": "binary",
+            "use_float16": True  # Use half precision for storage efficiency
+        }
+    }
+}
+```
+
+### Environment Variables to set to use Azure Identity Credential:
+* For an Environment Credential, you will need to setup a Service Principal and set the following environment variables:
+  - `AZURE_TENANT_ID`: Your Azure Active Directory tenant ID.
+  - `AZURE_CLIENT_ID`: The client ID of your service principal or managed identity.
+  - `AZURE_CLIENT_SECRET`: The client secret of your service principal.
+* For a User-Assigned Managed Identity, you will need to set the following environment variable:
+  - `AZURE_CLIENT_ID`: The client ID of the user-assigned managed identity.
+* For a System-Assigned Managed Identity, no additional environment variables are needed.
+
+### Developer logins to use for a Azure Identity Credential:
+* For an Azure CLI Credential, you need to have the Azure CLI installed and logged in with `az login`.
+* For an Azure PowerShell Credential, you need to have the Azure PowerShell module installed and logged in with `Connect-AzAccount`.
+* For an Azure Developer CLI Credential, you need to have the Azure Developer CLI installed and logged in with `azd auth login`.
+
+Troubleshooting tips for [Azure Identity](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/identity/azure-identity/TROUBLESHOOTING.md#troubleshoot-environmentcredential-authentication-issues).
+
+
+## Configuration Parameters
+
+| Parameter | Description | Default Value | Options |
+| --- | --- | --- | --- |
+| `service_name` | Azure AI Search service name | Required | - |
+| `api_key` | API key of the Azure AI Search service | Optional | If not present, the [Azure Identity](#using-azure-identity-for-authentication) credential chain will be used |
+| `collection_name` | The name of the collection/index to store vectors | `mem0` | Any valid index name |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` | Any integer value |
+| `compression_type` | Type of vector compression to use | `none` | `none`, `scalar`, `binary` |
+| `use_float16` | Store vectors in half precision (Edm.Half) | `False` | `True`, `False` |
+| `vector_filter_mode` | Vector filter mode to use | `preFilter` | `postFilter`, `preFilter` |
+| `hybrid_search` | Use hybrid search | `False` | `True`, `False` |
+
+## Notes on Configuration Options
+
+- **compression_type**: 
+  - `none`: No compression, uses full vector precision
+  - `scalar`: Scalar quantization with reasonable balance of speed and accuracy
+  - `binary`: Binary quantization for maximum compression with some accuracy trade-off
+
+- **vector_filter_mode**:
+  - `preFilter`: Applies filters before vector search (faster)
+  - `postFilter`: Applies filters after vector search (may provide better relevance)
+
+- **use_float16**: Using half precision (float16) reduces storage requirements but may slightly impact accuracy. Useful for very large vector collections.
+
+- **Filterable Fields**: The implementation automatically extracts `user_id`, `run_id`, and `agent_id` fields from payloads for filtering.

docs/components/vectordbs/dbs/azure_ai_search.mdx

@@ -1,95 +0,0 @@
-[Azure AI Search](https://learn.microsoft.com/azure/search/search-what-is-azure-search/) (formerly known as "Azure Cognitive Search") provides secure information retrieval at scale over user-owned content in traditional and generative AI search applications.
-
-## Usage
-
-```python
-import os
-from mem0 import Memory
-
-os.environ["OPENAI_API_KEY"] = "sk-xx"   # This key is used for embedding purpose
-
-config = {
-    "vector_store": {
-        "provider": "azure_ai_search",
-        "config": {
-            "service_name": "ai-search-test",
-            "api_key": "*****",
-            "collection_name": "mem0", 
-            "embedding_model_dims": 1536
-        }
-    }
-}
-
-m = Memory.from_config(config)
-messages = [
-    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
-    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
-    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
-]
-m.add(messages, user_id="alice", metadata={"category": "movies"})
-```
-
-## Using binary compression for large vector collections
-
-```python
-config = {
-    "vector_store": {
-        "provider": "azure_ai_search",
-        "config": {
-            "service_name": "ai-search-test",
-            "api_key": "*****",
-            "collection_name": "mem0", 
-            "embedding_model_dims": 1536,
-            "compression_type": "binary",
-            "use_float16": True  # Use half precision for storage efficiency
-        }
-    }
-}
-```
-
-## Using hybrid search
-
-```python
-config = {
-    "vector_store": {
-        "provider": "azure_ai_search",
-        "config": {
-            "service_name": "ai-search-test",
-            "api_key": "*****",
-            "collection_name": "mem0", 
-            "embedding_model_dims": 1536,
-            "hybrid_search": True,
-            "vector_filter_mode": "postFilter"
-        }
-    }
-}
-```
-
-## Configuration Parameters
-
-| Parameter | Description | Default Value | Options |
-| --- | --- | --- | --- |
-| `service_name` | Azure AI Search service name | Required | - |
-| `api_key` | API key of the Azure AI Search service | Required | - |
-| `collection_name` | The name of the collection/index to store vectors | `mem0` | Any valid index name |
-| `embedding_model_dims` | Dimensions of the embedding model | `1536` | Any integer value |
-| `compression_type` | Type of vector compression to use | `none` | `none`, `scalar`, `binary` |
-| `use_float16` | Store vectors in half precision (Edm.Half) | `False` | `True`, `False` |
-| `vector_filter_mode` | Vector filter mode to use | `preFilter` | `postFilter`, `preFilter` |
-| `hybrid_search` | Use hybrid search | `False` | `True`, `False` |
-
-## Notes on Configuration Options
-
-- **compression_type**: 
-  - `none`: No compression, uses full vector precision
-  - `scalar`: Scalar quantization with reasonable balance of speed and accuracy
-  - `binary`: Binary quantization for maximum compression with some accuracy trade-off
-
-- **vector_filter_mode**:
-  - `preFilter`: Applies filters before vector search (faster)
-  - `postFilter`: Applies filters after vector search (may provide better relevance)
-
-- **use_float16**: Using half precision (float16) reduces storage requirements but may slightly impact accuracy. Useful for very large vector collections.
-
-- **Filterable Fields**: The implementation automatically extracts `user_id`, `run_id`, and `agent_id` fields from payloads for filtering.

docs/components/vectordbs/dbs/baidu.mdx

@@ -0,0 +1,67 @@
+---
+title: Baidu VectorDB (Mochow)
+---
+
+[Baidu VectorDB](https://cloud.baidu.com/doc/VDB/index.html) is an enterprise-level distributed vector database service developed by Baidu Intelligent Cloud. It is powered by Baidu's proprietary "Mochow" vector database kernel, providing high performance, availability, and security for vector search.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+config = {
+    "vector_store": {
+        "provider": "baidu",
+        "config": {
+            "endpoint": "http://your-mochow-endpoint:8287",
+            "account": "root",
+            "api_key": "your-api-key",
+            "database_name": "mem0",
+            "table_name": "mem0_table",
+            "embedding_model_dims": 1536,
+            "metric_type": "COSINE"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movie? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+### Config
+
+Here are the available parameters for the `mochow` config:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `endpoint` | Endpoint URL for your Baidu VectorDB instance | Required |
+| `account` | Baidu VectorDB account name | `root` |
+| `api_key` | API key for accessing Baidu VectorDB | Required |
+| `database_name` | Name of the database | `mem0` |
+| `table_name` | Name of the table | `mem0_table` |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
+| `metric_type` | Distance metric for similarity search | `L2` |
+
+### Distance Metrics
+
+The following distance metrics are supported:
+
+- `L2`: Euclidean distance (default)
+- `IP`: Inner product
+- `COSINE`: Cosine similarity
+
+### Index Configuration
+
+The vector index is automatically configured with the following HNSW parameters:
+
+- `m`: 16 (number of connections per element)
+- `efconstruction`: 200 (size of the dynamic candidate list)
+- `auto_build`: true (automatically build index)
+- `auto_build_index_policy`: Incremental build with 10000 rows increment

docs/components/vectordbs/dbs/chroma.mdx

@@ -1,7 +1,9 @@
-[Chroma](https://www.trychroma.com/) is an AI-native open-source vector database that simplifies building LLM apps by providing tools for storing, embedding, and searching embeddings with a focus on simplicity and speed.
+[Chroma](https://www.trychroma.com/) is an AI-native open-source vector database that simplifies building LLM apps by providing tools for storing, embedding, and searching embeddings with a focus on simplicity and speed. It supports both local deployment and cloud hosting through ChromaDB Cloud.
 
 ### Usage
 
+#### Local Installation
+
 ```python
 import os
 from mem0 import Memory
@@ -14,6 +16,9 @@ config = {
         "config": {
             "collection_name": "test",
             "path": "db",
+            # Optional: ChromaDB Cloud configuration
+            # "api_key": "your-chroma-cloud-api-key",
+            # "tenant": "your-chroma-cloud-tenant-id",
         }
     }
 }
@@ -38,4 +43,6 @@ Here are the parameters available for configuring Chroma:
 | `client` | Custom client for Chroma | `None` |
 | `path` | Path for the Chroma database | `db` |
 | `host` | The host where the Chroma server is running | `None` |
-| `port` | The port where the Chroma server is running | `None` |
+| `port` | The port where the Chroma server is running | `None` |
+| `api_key` | ChromaDB Cloud API key (for cloud usage) | `None` |
+| `tenant` | ChromaDB Cloud tenant ID (for cloud usage) | `None` |

docs/components/vectordbs/dbs/databricks.mdx

@@ -0,0 +1,130 @@
+[Databricks Vector Search](https://docs.databricks.com/en/generative-ai/vector-search.html) is a serverless similarity search engine that allows you to store a vector representation of your data, including metadata, in a vector database. With Vector Search, you can create auto-updating vector search indexes from Delta tables managed by Unity Catalog and query them with a simple API to return the most similar vectors.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+config = {
+    "vector_store": {
+        "provider": "databricks",
+        "config": {
+            "workspace_url": "https://your-workspace.databricks.com",
+            "access_token": "your-access-token",
+            "endpoint_name": "your-vector-search-endpoint",
+            "index_name": "catalog.schema.index_name",
+            "source_table_name": "catalog.schema.source_table",
+            "embedding_dimension": 1536
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+### Config
+
+Here are the parameters available for configuring Databricks Vector Search:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `workspace_url` | The URL of your Databricks workspace | **Required** |
+| `access_token` | Personal Access Token for authentication | `None` |
+| `service_principal_client_id` | Service principal client ID (alternative to access_token) | `None` |
+| `service_principal_client_secret` | Service principal client secret (required with client_id) | `None` |
+| `endpoint_name` | Name of the Vector Search endpoint | **Required** |
+| `index_name` | Name of the vector index (Unity Catalog format: catalog.schema.index) | **Required** |
+| `source_table_name` | Name of the source Delta table (Unity Catalog format: catalog.schema.table) | **Required** |
+| `embedding_dimension` | Dimension of self-managed embeddings | `1536` |
+| `embedding_source_column` | Column name for text when using Databricks-computed embeddings | `None` |
+| `embedding_model_endpoint_name` | Databricks serving endpoint for embeddings | `None` |
+| `embedding_vector_column` | Column name for self-managed embedding vectors | `embedding` |
+| `endpoint_type` | Type of endpoint (`STANDARD` or `STORAGE_OPTIMIZED`) | `STANDARD` |
+| `sync_computed_embeddings` | Whether to sync computed embeddings automatically | `True` |
+
+### Authentication
+
+Databricks Vector Search supports two authentication methods:
+
+#### Service Principal (Recommended for Production)
+```python
+config = {
+    "vector_store": {
+        "provider": "databricks",
+        "config": {
+            "workspace_url": "https://your-workspace.databricks.com",
+            "service_principal_client_id": "your-service-principal-id",
+            "service_principal_client_secret": "your-service-principal-secret",
+            "endpoint_name": "your-endpoint",
+            "index_name": "catalog.schema.index_name",
+            "source_table_name": "catalog.schema.source_table"
+        }
+    }
+}
+```
+
+#### Personal Access Token (for Development)
+```python
+config = {
+    "vector_store": {
+        "provider": "databricks",
+        "config": {
+            "workspace_url": "https://your-workspace.databricks.com",
+            "access_token": "your-personal-access-token",
+            "endpoint_name": "your-endpoint",
+            "index_name": "catalog.schema.index_name",
+            "source_table_name": "catalog.schema.source_table"
+        }
+    }
+}
+```
+
+### Embedding Options
+
+#### Self-Managed Embeddings (Default)
+Use your own embedding model and provide vectors directly:
+
+```python
+config = {
+    "vector_store": {
+        "provider": "databricks",
+        "config": {
+            # ... authentication config ...
+            "embedding_dimension": 768,  # Match your embedding model
+            "embedding_vector_column": "embedding"
+        }
+    }
+}
+```
+
+#### Databricks-Computed Embeddings
+Let Databricks compute embeddings from text using a serving endpoint:
+
+```python
+config = {
+    "vector_store": {
+        "provider": "databricks",
+        "config": {
+            # ... authentication config ...
+            "embedding_source_column": "text",
+            "embedding_model_endpoint_name": "e5-small-v2"
+        }
+    }
+}
+```
+
+### Important Notes
+
+- **Delta Sync Index**: This implementation uses Delta Sync Index, which automatically syncs with your source Delta table. Direct vector insertion/deletion/update operations will log warnings as they're not supported with Delta Sync.
+- **Unity Catalog**: Both the source table and index must be in Unity Catalog format (`catalog.schema.table_name`).
+- **Endpoint Auto-Creation**: If the specified endpoint doesn't exist, it will be created automatically.
+- **Index Auto-Creation**: If the specified index doesn't exist, it will be created automatically with the provided configuration.
+- **Filter Support**: Supports filtering by metadata fields, with different syntax for STANDARD vs STORAGE_OPTIMIZED endpoints.

docs/components/vectordbs/dbs/elasticsearch.mdx

@@ -54,7 +54,8 @@ Let's see the available parameters for the `elasticsearch` config:
 | `password`             | Password for basic authentication                  | `None`        |
 | `verify_certs`         | Whether to verify SSL certificates                 | `True`        |
 | `auto_create_index`    | Whether to automatically create the index          | `True`        |
-| `custom_search_query`  | Function returning a custom search query            | `None`        |
+| `custom_search_query`  | Function returning a custom search query           | `None`        |
+| `headers`              | Custom headers to include in requests              | `None`        |
 
 ### Features
 

docs/components/vectordbs/dbs/faiss.mdx

@@ -0,0 +1,72 @@
+[FAISS](https://github.com/facebookresearch/faiss) is a library for efficient similarity search and clustering of dense vectors. It is designed to work with large-scale datasets and provides a high-performance search engine for vector data. FAISS is optimized for memory usage and search speed, making it an excellent choice for production environments.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "faiss",
+        "config": {
+            "collection_name": "test",
+            "path": "/tmp/faiss_memories",
+            "distance_strategy": "euclidean"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+### Installation
+
+To use FAISS in your mem0 project, you need to install the appropriate FAISS package for your environment:
+
+```bash
+# For CPU version
+pip install faiss-cpu
+
+# For GPU version (requires CUDA)
+pip install faiss-gpu
+```
+
+### Config
+
+Here are the parameters available for configuring FAISS:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `collection_name` | The name of the collection | `mem0` |
+| `path` | Path to store FAISS index and metadata | `/tmp/faiss/<collection_name>` |
+| `distance_strategy` | Distance metric strategy to use (options: 'euclidean', 'inner_product', 'cosine') | `euclidean` |
+| `normalize_L2` | Whether to normalize L2 vectors (only applicable for euclidean distance) | `False` |
+
+### Performance Considerations
+
+FAISS offers several advantages for vector search:
+
+1. **Efficiency**: FAISS is optimized for memory usage and speed, making it suitable for large-scale applications.
+2. **Offline Support**: FAISS works entirely locally, with no need for external servers or API calls.
+3. **Storage Options**: Vectors can be stored in-memory for maximum speed or persisted to disk.
+4. **Multiple Index Types**: FAISS supports different index types optimized for various use cases (though mem0 currently uses the basic flat index).
+
+### Distance Strategies
+
+FAISS in mem0 supports three distance strategies:
+
+- **euclidean**: L2 distance, suitable for most embedding models
+- **inner_product**: Dot product similarity, useful for some specialized embeddings
+- **cosine**: Cosine similarity, best for comparing semantic similarity regardless of vector magnitude
+
+When using `cosine` or `inner_product` with normalized vectors, you may want to set `normalize_L2=True` for better results.

docs/components/vectordbs/dbs/langchain.mdx

@@ -0,0 +1,112 @@
+---
+title: LangChain
+---
+
+Mem0 supports LangChain as a provider for vector store integration. LangChain provides a unified interface to various vector databases, making it easy to integrate different vector store providers through a consistent API.
+
+<Note>
+  When using LangChain as your vector store provider, you must set the collection name to "mem0". This is a required configuration for proper integration with Mem0.
+</Note>
+
+## Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+from langchain_community.vectorstores import Chroma
+from langchain_openai import OpenAIEmbeddings
+
+# Initialize a LangChain vector store
+embeddings = OpenAIEmbeddings()
+vector_store = Chroma(
+    persist_directory="./chroma_db",
+    embedding_function=embeddings,
+    collection_name="mem0"  # Required collection name
+)
+
+# Pass the initialized vector store to the config
+config = {
+    "vector_store": {
+        "provider": "langchain",
+        "config": {
+            "client": vector_store
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+```typescript TypeScript
+import { Memory } from "mem0ai";
+import { OpenAIEmbeddings } from "@langchain/openai";
+import { MemoryVectorStore as LangchainMemoryStore } from "langchain/vectorstores/memory";
+
+const embeddings = new OpenAIEmbeddings();
+const vectorStore = new LangchainVectorStore(embeddings);
+
+const config = {
+    "vector_store": {
+        "provider": "langchain",
+        "config": { "client": vectorStore }
+    }
+}
+
+const memory = new Memory(config);
+
+const messages = [
+    { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
+    { role: "assistant", content: "How about a thriller movies? They can be quite engaging." },
+    { role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
+    { role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." }
+]
+
+memory.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+</CodeGroup>
+
+## Supported LangChain Vector Stores
+
+LangChain supports a wide range of vector store providers, including:
+
+- Chroma
+- FAISS
+- Pinecone
+- Weaviate
+- Milvus
+- Qdrant
+- And many more
+
+You can use any of these vector store instances directly in your configuration. For a complete and up-to-date list of available providers, refer to the [LangChain Vector Stores documentation](https://python.langchain.com/docs/integrations/vectorstores).
+
+## Limitations
+
+When using LangChain as a vector store provider, there are some limitations to be aware of:
+
+1. **Bulk Operations**: The `get_all` and `delete_all` operations are not supported when using LangChain as the vector store provider. This is because LangChain's vector store interface doesn't provide standardized methods for these bulk operations across all providers.
+
+2. **Provider-Specific Features**: Some advanced features may not be available depending on the specific vector store implementation you're using through LangChain.
+
+## Provider-Specific Configuration
+
+When using LangChain as a vector store provider, you'll need to:
+
+1. Set the appropriate environment variables for your chosen vector store provider
+2. Import and initialize the specific vector store class you want to use
+3. Pass the initialized vector store instance to the config
+
+<Note>
+  Make sure to install the necessary LangChain packages and any provider-specific dependencies.
+</Note>
+
+## Config
+
+All available parameters for the `langchain` vector store config are present in [Master List of All Params in Config](../config).

docs/components/vectordbs/dbs/milvus.mdx

@@ -14,6 +14,7 @@ config = {
             "embedding_model_dims": "123",
             "url": "127.0.0.1",
             "token": "8e4b8ca8cf2c67",
+            "db_name": "my_database",
         }
     }
 }
@@ -39,3 +40,4 @@ Here's the parameters available for configuring Milvus Database:
 | `collection_name` | The name of the collection | `mem0` |
 | `embedding_model_dims` | Dimensions of the embedding model | `1536` |
 | `metric_type` | Metric type for similarity search | `L2` |
+| `db_name` | Name of the database | `""` |

docs/components/vectordbs/dbs/mongodb.mdx

@@ -0,0 +1,45 @@
+# MongoDB
+
+[MongoDB](https://www.mongodb.com/) is a versatile document database that supports vector search capabilities, allowing for efficient high-dimensional similarity searches over large datasets with robust scalability and performance.
+
+## Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "mongodb",
+        "config": {
+            "db_name": "mem0-db",
+            "collection_name": "mem0-collection",
+            "mongo_uri":"mongodb://username:password@localhost:27017"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+## Config
+
+Here are the parameters available for configuring MongoDB:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| db_name | Name of the MongoDB database | `"mem0_db"` |
+| collection_name | Name of the MongoDB collection | `"mem0_collection"` |
+| embedding_model_dims | Dimensions of the embedding vectors | `1536` |
+| mongo_uri | The mongo URI connection string | mongodb://username:password@localhost:27017 |
+
+> **Note**: If Mongo_uri is not provided it will default to mongodb://username:password@localhost:27017.

docs/components/vectordbs/dbs/neptune_analytics.mdx

@@ -0,0 +1,42 @@
+# Neptune Analytics Vector Store
+
+[Neptune Analytics](https://docs.aws.amazon.com/neptune-analytics/latest/userguide/what-is-neptune-analytics.html/) is a memory-optimized graph database engine for analytics. With Neptune Analytics, you can get insights and find trends by processing large amounts of graph data in seconds, including vector search.
+
+
+## Installation
+
+```bash
+pip install mem0ai[vector_stores]
+```
+
+## Usage
+
+```python
+config = {
+    "vector_store": {
+        "provider": "neptune",
+        "config": {
+            "collection_name": "mem0",
+            "endpoint": f"neptune-graph://my-graph-identifier",
+        },
+    },
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+## Parameters
+
+Let's see the available parameters for the `neptune` config:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `collection_name` | The name of the collection to store the vectors | `mem0` |
+| `endpoint` | Connection URL for the Neptune Analytics service | `neptune-graph://my-graph-identifier` |

docs/components/vectordbs/dbs/opensearch.mdx

@@ -1,59 +1,75 @@
-[OpenSearch](https://opensearch.org/) is an open-source, enterprise-grade search and observability suite that brings order to unstructured data at scale. OpenSearch supports k-NN (k-Nearest Neighbors) and allows you to store and retrieve high-dimensional vector embeddings efficiently.
+[OpenSearch](https://opensearch.org/) is an enterprise-grade search and observability suite that brings order to unstructured data at scale. OpenSearch supports k-NN (k-Nearest Neighbors) and allows you to store and retrieve high-dimensional vector embeddings efficiently.
 
 ### Installation
 
 OpenSearch support requires additional dependencies. Install them with:
 
 ```bash
-pip install opensearch>=2.8.0
+pip install opensearch-py
 ```
 
+### Prerequisites
+
+Before using OpenSearch with Mem0, you need to set up a collection in AWS OpenSearch Service.
+
+#### AWS OpenSearch Service
+You can create a collection through the AWS Console:
+- Navigate to [OpenSearch Service Console](https://console.aws.amazon.com/aos/home)
+- Click "Create collection"
+- Select "Serverless collection" and then enable "Vector search" capabilities
+- Once created, note the endpoint URL (host) for your configuration
+
+
 ### Usage
 
 ```python
 import os
 from mem0 import Memory
+import boto3
+from opensearchpy import OpenSearch, RequestsHttpConnection, AWSV4SignerAuth
 
-os.environ["OPENAI_API_KEY"] = "sk-xx"
+# For AWS OpenSearch Service with IAM authentication
+region = 'us-west-2'
+service = 'aoss'
+credentials = boto3.Session().get_credentials()
+auth = AWSV4SignerAuth(credentials, region, service)
 
 config = {
     "vector_store": {
         "provider": "opensearch",
         "config": {
             "collection_name": "mem0",
-            "host": "localhost",
-            "port": 9200,
-            "embedding_model_dims": 1536
+            "host": "your-domain.us-west-2.aoss.amazonaws.com",
+            "port": 443,
+            "http_auth": auth,
+            "embedding_model_dims": 1024,
+            "connection_class": RequestsHttpConnection,
+            "pool_maxsize": 20,
+            "use_ssl": True,
+            "verify_certs": True
         }
     }
 }
+```
 
+### Add Memories
+
+```python
 m = Memory.from_config(config)
 messages = [
     {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
     {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
     {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
 ]
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
-### Config
+### Search Memories
 
-Let's see the available parameters for the `opensearch` config:
-
-| Parameter              | Description                                        | Default Value |
-| ---------------------- | -------------------------------------------------- | ------------- |
-| `collection_name`      | The name of the index to store the vectors         | `mem0`        |
-| `embedding_model_dims` | Dimensions of the embedding model                  | `1536`        |
-| `host`                 | The host where the OpenSearch server is running    | `localhost`   |
-| `port`                 | The port where the OpenSearch server is running    | `9200`        |
-| `api_key`              | API key for authentication                         | `None`        |
-| `user`                 | Username for basic authentication                  | `None`        |
-| `password`             | Password for basic authentication                  | `None`        |
-| `verify_certs`         | Whether to verify SSL certificates                 | `False`        |
-| `auto_create_index`    | Whether to automatically create the index          | `True`        |
-| `use_ssl`              | Whether to use SSL for connection                  | `False`        |
+```python
+results = m.search("What kind of movies does Alice like?", user_id="alice")
+```
 
 ### Features
 

docs/components/vectordbs/dbs/pgvector.mdx

@@ -2,7 +2,8 @@
 
 ### Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -24,19 +25,50 @@ m = Memory.from_config(config)
 messages = [
     {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
     {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
     {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
 ]
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  vectorStore: {
+    provider: 'pgvector',
+    config: {
+      collectionName: 'memories',
+      embeddingModelDims: 1536,
+      user: 'test',
+      password: '123',
+      host: '127.0.0.1',
+      port: 5432,
+      dbname: 'vector_store', // Optional, defaults to 'postgres'
+      diskann: false, // Optional, requires pgvectorscale extension
+      hnsw: false, // Optional, for HNSW indexing
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
 ### Config
 
 Here's the parameters available for configuring pgvector:
 
 | Parameter | Description | Default Value |
 | --- | --- | --- |
-| `dbname` | The name of the  | `postgres` |
+| `dbname` | The name of the database | `postgres` |
 | `collection_name` | The name of the collection | `mem0` |
 | `embedding_model_dims` | Dimensions of the embedding model | `1536` |
 | `user` | User name to connect to the database | `None` |
@@ -44,4 +76,12 @@ Here's the parameters available for configuring pgvector:
 | `host` | The host where the Postgres server is running | `None` |
 | `port` | The port where the Postgres server is running | `None` |
 | `diskann` | Whether to use diskann for vector similarity search (requires pgvectorscale) | `True` |
-| `hnsw` | Whether to use hnsw for vector similarity search | `False` |
+| `hnsw` | Whether to use hnsw for vector similarity search | `False` |
+| `sslmode` | SSL mode for PostgreSQL connection (e.g., 'require', 'prefer', 'disable') | `None` |
+| `connection_string` | PostgreSQL connection string (overrides individual connection parameters) | `None` |
+| `connection_pool` | psycopg2 connection pool object (overrides connection string and individual parameters) | `None` |
+
+**Note**: The connection parameters have the following priority:
+1. `connection_pool` (highest priority)
+2. `connection_string`
+3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)

docs/components/vectordbs/dbs/pinecone.mdx

@@ -1,6 +1,8 @@
 [Pinecone](https://www.pinecone.io/) is a fully managed vector database designed for machine learning applications, offering high performance vector search with low latency at scale. It's particularly well-suited for semantic search, recommendation systems, and other AI-powered applications.
 
-> **Note**: Before configuring Pinecone, you need to select an embedding model (e.g., OpenAI, Cohere, or custom models) and ensure the `embedding_model_dims` in your config matches your chosen model's dimensions. For example, OpenAI's text-embedding-ada-002 uses 1536 dimensions.
+> **New**: Pinecone integration now supports custom namespaces! Use the `namespace` parameter to logically separate data within the same index. This is especially useful for multi-tenant or multi-user applications.
+
+> **Note**: Before configuring Pinecone, you need to select an embedding model (e.g., OpenAI, Cohere, or custom models) and ensure the `embedding_model_dims` in your config matches your chosen model's dimensions. For example, OpenAI's text-embedding-3-small uses 1536 dimensions.
 
 ### Usage
 
@@ -18,6 +20,7 @@ config = {
         "config": {
             "collection_name": "testing",
             "embedding_model_dims": 1536,  # Matches OpenAI's text-embedding-3-small
+            "namespace": "my-namespace", # Optional: specify a namespace for multi-tenancy
             "serverless_config": {
                 "cloud": "aws",  # Choose between 'aws' or 'gcp' or 'azure'
                 "region": "us-east-1"
@@ -53,6 +56,7 @@ Here are the parameters available for configuring Pinecone:
 | `hybrid_search` | Whether to enable hybrid search | `False` |
 | `metric` | Distance metric for vector similarity | `"cosine"` |
 | `batch_size` | Batch size for operations | `100` |
+| `namespace` | Namespace for the collection, useful for multi-tenancy. | `None` |
 
 > **Important**: You must choose either `serverless_config` or `pod_config` for your deployment, but not both.
 
@@ -64,6 +68,7 @@ config = {
         "config": {
             "collection_name": "memory_index",
             "embedding_model_dims": 1536,  # For OpenAI's text-embedding-3-small
+            "namespace": "my-namespace",  # Optional: custom namespace
             "serverless_config": {
                 "cloud": "aws",  # or "gcp" or "azure"
                 "region": "us-east-1"  # Choose appropriate region
@@ -81,6 +86,7 @@ config = {
         "config": {
             "collection_name": "memory_index",
             "embedding_model_dims": 1536,  # For OpenAI's text-embedding-ada-002
+            "namespace": "my-namespace",  # Optional: custom namespace
             "pod_config": {
                 "environment": "gcp-starter",
                 "replicas": 1,

docs/components/vectordbs/dbs/s3_vectors.mdx

@@ -0,0 +1,78 @@
+---
+title: Amazon S3 Vectors
+---
+
+[Amazon S3 Vectors](https://aws.amazon.com/s3/features/vectors/) is a purpose-built, cost-optimized vector storage and query service for semantic search and AI applications. It provides S3-level elasticity and durability with sub-second query performance.
+
+### Installation
+
+S3 Vectors support requires additional dependencies. Install them with:
+
+```bash
+pip install boto3
+```
+
+### Usage
+
+To use Amazon S3 Vectors with Mem0, you need to have an AWS account and the necessary IAM permissions (`s3vectors:*`). Ensure your environment is configured with AWS credentials (e.g., via `~/.aws/credentials` or environment variables).
+
+```python
+import os
+from mem0 import Memory
+
+# Ensure your AWS credentials are configured in your environment
+# e.g., by setting AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_DEFAULT_REGION
+
+config = {
+    "vector_store": {
+        "provider": "s3_vectors",
+        "config": {
+            "vector_bucket_name": "my-mem0-vector-bucket",
+            "collection_name": "my-memories-index",
+            "embedding_model_dims": 1536,
+            "distance_metric": "cosine",
+            "region_name": "us-east-1"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movie? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+### Config
+
+Here are the available parameters for the `s3_vectors` config:
+
+| Parameter              | Description                                                                      | Default Value                         |
+| ---------------------- | -------------------------------------------------------------------------------- | ------------------------------------- |
+| `vector_bucket_name`   | The name of the S3 Vector bucket to use. It will be created if it doesn't exist. | Required                              |
+| `collection_name`      | The name of the vector index within the bucket.                                  | `mem0`                                |
+| `embedding_model_dims` | Dimensions of the embedding model. Must match your embedder.                     | `1536`                                |
+| `distance_metric`      | Distance metric for similarity search. Options: `cosine`, `euclidean`.           | `cosine`                              |
+| `region_name`          | The AWS region where the bucket and index reside.                                | `None` (uses default from AWS config) |
+
+### IAM Permissions
+
+Your AWS identity (user or role) needs permissions to perform actions on S3 Vectors. A minimal policy would look like this:
+
+```json
+{
+  "Version": "2012-10-17",
+  "Statement": [
+    {
+      "Effect": "Allow",
+      "Action": "s3vectors:*",
+      "Resource": "*"
+    }
+  ]
+}
+```
+
+For production, it is recommended to scope down the resource ARN to your specific buckets and indexes.

docs/components/vectordbs/dbs/supabase.mdx

@@ -4,7 +4,8 @@ Create a [Supabase](https://supabase.com/dashboard/projects) account and project
 
 ### Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -32,10 +33,90 @@ messages = [
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
+```typescript Typescript
+import { Memory } from "mem0ai/oss";
+
+const config = {
+    vectorStore: {
+      provider: "supabase",
+      config: {
+        collectionName: "memories",
+        embeddingModelDims: 1536,
+        supabaseUrl: process.env.SUPABASE_URL || "",
+        supabaseKey: process.env.SUPABASE_KEY || "",
+        tableName: "memories",
+      },
+    },
+}
+
+const memory = new Memory(config);
+
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
+### SQL Migrations for TypeScript Implementation
+
+The following SQL migrations are required to enable the vector extension and create the memories table:
+
+```sql
+-- Enable the vector extension
+create extension if not exists vector;
+
+-- Create the memories table
+create table if not exists memories (
+  id text primary key,
+  embedding vector(1536),
+  metadata jsonb,
+  created_at timestamp with time zone default timezone('utc', now()),
+  updated_at timestamp with time zone default timezone('utc', now())
+);
+
+-- Create the vector similarity search function
+create or replace function match_vectors(
+  query_embedding vector(1536),
+  match_count int,
+  filter jsonb default '{}'::jsonb
+)
+returns table (
+  id text,
+  similarity float,
+  metadata jsonb
+)
+language plpgsql
+as $$
+begin
+  return query
+  select
+    t.id::text,
+    1 - (t.embedding <=> query_embedding) as similarity,
+    t.metadata
+  from memories t
+  where case
+    when filter::text = '{}'::text then true
+    else t.metadata @> filter
+  end
+  order by t.embedding <=> query_embedding
+  limit match_count;
+end;
+$$;
+```
+
+Goto [Supabase](https://supabase.com/dashboard/projects) and run the above SQL migrations inside the SQL Editor.
+
 ### Config
 
 Here are the parameters available for configuring Supabase:
 
+<Tabs>
+<Tab title="Python">
 | Parameter | Description | Default Value |
 | --- | --- | --- |
 | `connection_string` | PostgreSQL connection string (required) | None |
@@ -43,6 +124,17 @@ Here are the parameters available for configuring Supabase:
 | `embedding_model_dims` | Dimensions of the embedding model | `1536` |
 | `index_method` | Vector index method to use | `auto` |
 | `index_measure` | Distance measure for similarity search | `cosine_distance` |
+</Tab>
+<Tab title="TypeScript">
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `collectionName` | Name for the vector collection | `mem0` |
+| `embeddingModelDims` | Dimensions of the embedding model | `1536` |
+| `supabaseUrl` | Supabase URL | None |
+| `supabaseKey` | Supabase key | None |
+| `tableName` | Name for the vector table | `memories` |
+</Tab>
+</Tabs>
 
 ### Index Methods
 

docs/components/vectordbs/dbs/upstash-vector.mdx

@@ -0,0 +1,70 @@
+[Upstash Vector](https://upstash.com/docs/vector) is a serverless vector database with built-in embedding models.
+
+### Usage with Upstash embeddings
+
+You can enable the built-in embedding models by setting `enable_embeddings` to `True`. This allows you to use Upstash's embedding models for vectorization.
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["UPSTASH_VECTOR_REST_URL"] = "..."
+os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "..."
+
+config = {
+    "vector_store": {
+        "provider": "upstash_vector",
+        "enable_embeddings": True,
+    }
+}
+
+m = Memory.from_config(config)
+m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})
+```
+
+<Note>
+    Setting `enable_embeddings` to `True` will bypass any external embedding provider you have configured.
+</Note>
+
+### Usage with external embedding providers
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "..."
+os.environ["UPSTASH_VECTOR_REST_URL"] = "..."
+os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "..."
+
+config = {
+    "vector_store": {
+        "provider": "upstash_vector",
+    },
+    "embedder": {
+        "provider": "openai",
+        "config": {
+            "model": "text-embedding-3-large"
+        },
+    }
+}
+
+m = Memory.from_config(config)
+m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})
+```
+
+### Config
+
+Here are the parameters available for configuring Upstash Vector:
+
+| Parameter           | Description                        | Default Value |
+| ------------------- | ---------------------------------- | ------------- |
+| `url`               | URL for the Upstash Vector index   | `None`        |
+| `token`             | Token for the Upstash Vector index | `None`        |
+| `client`            | An `upstash_vector.Index` instance | `None`        |
+| `collection_name`   | The default namespace used         | `""`          |
+| `enable_embeddings` | Whether to use Upstash embeddings  | `False`       |
+
+<Note>
+  When `url` and `token` are not provided, the `UPSTASH_VECTOR_REST_URL` and
+  `UPSTASH_VECTOR_REST_TOKEN` environment variables are used.
+</Note>

docs/components/vectordbs/dbs/valkey.mdx

@@ -0,0 +1,49 @@
+# Valkey Vector Store
+
+[Valkey](https://valkey.io/) is an open source (BSD) high-performance key/value datastore that supports a variety of workloads and rich datastructures including vector search.
+
+## Installation
+
+```bash
+pip install mem0ai[vector_stores]
+```
+
+## Usage
+
+```python
+config = {
+    "vector_store": {
+        "provider": "valkey",
+        "config": {
+            "collection_name": "test",
+            "valkey_url": "valkey://localhost:6379",
+            "embedding_model_dims": 1536,
+            "index_type": "flat"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+## Parameters
+
+Let's see the available parameters for the `valkey` config:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `collection_name` | The name of the collection to store the vectors | `mem0` |
+| `valkey_url` | Connection URL for the Valkey server | `valkey://localhost:6379` |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
+| `index_type` | Vector index algorithm (`hnsw` or `flat`) | `hnsw` |
+| `hnsw_m` | Number of bi-directional links for HNSW | `16` |
+| `hnsw_ef_construction` | Size of dynamic candidate list for HNSW | `200` |
+| `hnsw_ef_runtime` | Size of dynamic candidate list for search | `10` |
+| `distance_metric` | Distance metric for vector similarity | `cosine` |

docs/components/vectordbs/dbs/vectorize.mdx

@@ -0,0 +1,45 @@
+[Cloudflare Vectorize](https://developers.cloudflare.com/vectorize/) is a vector database offering from Cloudflare, allowing you to build AI-powered applications with vector embeddings.
+
+### Usage
+
+<CodeGroup>
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  vectorStore: {
+    provider: 'vectorize',
+    config: {
+      indexName: 'my-memory-index',
+      accountId: 'your-cloudflare-account-id',
+      apiKey: 'your-cloudflare-api-key',
+      dimension: 1536, // Optional: defaults to 1536
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm looking for a good book to read."},
+    {"role": "assistant", "content": "Sure, what genre are you interested in?"},
+    {"role": "user", "content": "I enjoy fantasy novels with strong world-building."},
+    {"role": "assistant", "content": "Great! I'll keep that in mind for future recommendations."}
+]
+await memory.add(messages, { userId: "bob", metadata: { interest: "books" } });
+```
+</CodeGroup>
+
+### Config
+
+Let's see the available parameters for the `vectorize` config:
+
+<Tabs>
+<Tab title="TypeScript">
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `indexName` | The name of the Vectorize index | `None` (Required) |
+| `accountId` | Your Cloudflare account ID | `None` (Required) |
+| `apiKey` | Your Cloudflare API token | `None` (Required) |
+| `dimension` | Dimensions of the embedding model | `1536` |
+</Tab>
+</Tabs>

docs/components/vectordbs/dbs/vertex_ai.mdx

@@ -1,4 +1,6 @@
-## Google Cloud Vertex AI Vector Search
+---
+title: Vertex AI Vector Search
+---
 
 
 ### Usage
@@ -10,7 +12,7 @@ To use Google Cloud Vertex AI Vector Search with `mem0`, you need to configure t
 import os
 from mem0 import Memory
 
-os.environ["GEMINI_API_KEY"] = = "sk-xx"
+os.environ["GOOGLE_API_KEY"] = "sk-xx"
 
 config = {
     "vector_store": {

docs/components/vectordbs/overview.mdx

@@ -11,22 +11,29 @@ Mem0 includes built-in support for various popular databases. Memory can utilize
 See the list of supported vector databases below.
 
 <Note>
-  The following vector databases are supported in the Python implementation. The TypeScript implementation currently only supports Qdrant, Redis and in-memory vector database.
+  The following vector databases are supported in the Python implementation. The TypeScript implementation currently only supports Qdrant, Redis, Valkey, Vectorize and in-memory vector database.
 </Note>
 
 <CardGroup cols={3}>
   <Card title="Qdrant" href="/components/vectordbs/dbs/qdrant"></Card>
   <Card title="Chroma" href="/components/vectordbs/dbs/chroma"></Card>
   <Card title="Pgvector" href="/components/vectordbs/dbs/pgvector"></Card>
+  <Card title="Upstash Vector" href="/components/vectordbs/dbs/upstash-vector"></Card>
   <Card title="Milvus" href="/components/vectordbs/dbs/milvus"></Card>
   <Card title="Pinecone" href="/components/vectordbs/dbs/pinecone"></Card>
-  <Card title="Azure AI Search" href="/components/vectordbs/dbs/azure_ai_search"></Card>
+  <Card title="MongoDB" href="/components/vectordbs/dbs/mongodb"></Card>
+  <Card title="Azure" href="/components/vectordbs/dbs/azure"></Card>
   <Card title="Redis" href="/components/vectordbs/dbs/redis"></Card>
+  <Card title="Valkey" href="/components/vectordbs/dbs/valkey"></Card>
   <Card title="Elasticsearch" href="/components/vectordbs/dbs/elasticsearch"></Card>
   <Card title="OpenSearch" href="/components/vectordbs/dbs/opensearch"></Card>
   <Card title="Supabase" href="/components/vectordbs/dbs/supabase"></Card>
-  <Card title="Vertex AI Vector Search" href="/components/vectordbs/dbs/vertex_ai_vector_search"></Card>
+  <Card title="Vertex AI" href="/components/vectordbs/dbs/vertex_ai"></Card>
   <Card title="Weaviate" href="/components/vectordbs/dbs/weaviate"></Card>
+  <Card title="FAISS" href="/components/vectordbs/dbs/faiss"></Card>
+  <Card title="LangChain" href="/components/vectordbs/dbs/langchain"></Card>
+  <Card title="Amazon S3 Vectors" href="/components/vectordbs/dbs/s3_vectors"></Card>
+  <Card title="Databricks" href="/components/vectordbs/dbs/databricks"></Card>
 </CardGroup>
 
 ## Usage

docs/contributing/development.mdx

@@ -27,15 +27,20 @@ For detailed guidance on pull requests, refer to [GitHub's documentation](https:
 
 ## 📦 Dependency Management
 
-We use `poetry` as our package manager. Install it by following the [official instructions](https://python-poetry.org/docs/#installation).
+We use `hatch` as our package manager. Install it by following the [official instructions](https://hatch.pypa.io/latest/install/).
 
-⚠️ **Do NOT use `pip` or `conda` for dependency management.** Instead, run:
+⚠️ **Do NOT use `pip` or `conda` for dependency management.** Instead, follow these steps in order:
 
 ```bash
-make install_all
+# 1. Install base dependencies
+make install
 
-# Activate virtual environment
-poetry shell
+# 2. Activate virtual environment (this will install deps.)
+hatch shell (for default env)
+hatch -e dev_py_3_11 shell (for dev_py_3_11) (differences are mentioned in pyproject.toml)
+
+# 3. Install all optional dependencies
+make install_all
 ```
 
 ---
@@ -58,9 +63,9 @@ Run the linter and fix any reported issues before submitting your PR:
 make lint
 ```
 
-### 🎨 Code Formatting with `black`
+### 🎨 Code Formatting
 
-To maintain a consistent code style, format your code using `black`:
+To maintain a consistent code style, format your code:
 
 ```bash
 make format
@@ -74,7 +79,7 @@ Run tests to verify functionality before submitting your PR:
 make test
 ```
 
-💡 **Note:** Some dependencies have been removed from Poetry to reduce package size. Run `make install_all` to install necessary dependencies before running tests.
+💡 **Note:** Some dependencies have been removed from the main dependencies to reduce package size. Run `make install_all` to install necessary dependencies before running tests.
 
 ---
 

docs/core-concepts/memory-operations.mdx

@@ -1,60 +0,0 @@
----
-title: Memory Operations
-description: Understanding the core operations for managing memories in AI applications
-icon: "gear"
-iconType: "solid"
----
-
-Mem0 provides two core operations for managing memories in AI applications: adding new memories and searching existing ones. This guide covers how these operations work and how to use them effectively in your application.
-
-
-## Core Operations
-
-Mem0 exposes two main endpoints for interacting with memories:
-- The `add` endpoint for ingesting conversations and storing them as memories
-- The `search` endpoint for retrieving relevant memories based on queries
-
-### Adding Memories
-
-<Frame caption="Architecture diagram illustrating the process of adding memories.">
-  <img src="../images/add_architecture.png" />
-</Frame>
-
-The add operation processes conversations through several steps:
-
-1. **Information Extraction**
-   * An LLM extracts relevant memories from the conversation
-   * It identifies important entities and their relationships
-
-2. **Conflict Resolution**
-   * The system compares new information with existing data
-   * It identifies and resolves any contradictions
-
-3. **Memory Storage**
-   * Vector database stores the actual memories
-   * Graph database maintains relationship information
-   * Information is continuously updated with each interaction
-
-### Searching Memories
-
-<Frame caption="Architecture diagram illustrating the memory search process.">
-  <img src="../images/search_architecture.png" />
-</Frame>
-
-The search operation retrieves memories through a multi-step process:
-
-1. **Query Processing**
-   * LLM processes and optimizes the search query
-   * System prepares filters for targeted search
-
-2. **Vector Search**
-   * Performs semantic search using the optimized query
-   * Ranks results by relevance to the query
-   * Applies specified filters (user, agent, metadata, etc.)
-
-3. **Result Processing**
-   * Combines and ranks the search results
-   * Returns memories with relevance scores
-   * Includes associated metadata and timestamps
-
-This semantic search approach ensures accurate memory retrieval, whether you're looking for specific information or exploring related concepts.

docs/core-concepts/memory-operations/add.mdx

@@ -0,0 +1,153 @@
+---
+title: Add Memory
+description: Add memory into the Mem0 platform by storing user-assistant interactions and facts for later retrieval.
+icon: "plus"
+iconType: "solid"
+---
+
+
+## Overview
+
+The `add` operation is how you store memory into Mem0. Whether you're working with a chatbot, a voice assistant, or a multi-agent system, this is the entry point to create long-term memory.
+
+Memories typically come from a **user-assistant interaction** and Mem0 handles the extraction, transformation, and storage for you.
+
+Mem0 offers two implementation flows:
+
+- **Mem0 Platform** (Managed, scalable, with dashboard + API)
+- **Mem0 Open Source** (Lightweight, fully local, flexible SDKs)
+
+Each supports the same core memory operations, but with slightly different setup. Below, we walk through examples for both.
+
+
+## Architecture
+
+<Frame caption="Architecture diagram illustrating the process of adding memories.">
+  <img src="../../images/add_architecture.png" />
+</Frame>
+
+When you call `add`, Mem0 performs the following steps under the hood:
+
+1. **Information Extraction**
+   The input messages are passed through an LLM that extracts key facts, decisions, preferences, or events worth remembering.
+
+2. **Conflict Resolution**
+   Mem0 compares the new memory against existing ones to detect duplication or contradiction and handles updates accordingly.
+
+3. **Memory Storage**
+   The result is stored in a vector database (for semantic search) and optionally in a graph structure (for relationship mapping).
+
+You don’t need to handle any of this manually, Mem0 takes care of it with a single API call or SDK method.
+
+---
+
+## Example: Mem0 Platform
+
+<CodeGroup>
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+messages = [
+    {"role": "user", "content": "I'm planning a trip to Tokyo next month."},
+    {"role": "assistant", "content": "Great! I’ll remember that for future suggestions."}
+]
+
+client.add(
+    messages=messages,
+    user_id="alice",
+    version="v2"
+)
+```
+
+```javascript JavaScript
+import { MemoryClient } from "mem0ai";
+
+const client = new MemoryClient({apiKey: "your-api-key"});
+
+const messages = [
+  { role: "user", content: "I'm planning a trip to Tokyo next month." },
+  { role: "assistant", content: "Great! I’ll remember that for future suggestions." }
+];
+
+await client.add({
+  messages,
+  user_id: "alice",
+  version: "v2"
+});
+```
+</CodeGroup>
+
+---
+
+## Example: Mem0 Open Source
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+
+m = Memory()
+
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+
+# Store inferred memories (default behavior)
+result = m.add(messages, user_id="alice", metadata={"category": "movie_recommendations"})
+
+# Optionally store raw messages without inference
+result = m.add(messages, user_id="alice", metadata={"category": "movie_recommendations"}, infer=False)
+```
+
+```javascript JavaScript
+import { Memory } from 'mem0ai/oss';
+
+const memory = new Memory();
+
+const messages = [
+  {
+    role: "user",
+    content: "I like to drink coffee in the morning and go for a walk"
+  }
+];
+
+const result = memory.add(messages, {
+  userId: "alice",
+  metadata: { category: "preferences" }
+});
+```
+</CodeGroup>
+
+---
+
+## When Should You Add Memory?
+
+Add memory whenever your agent learns something useful:
+
+- A new user preference is shared
+- A decision or suggestion is made
+- A goal or task is completed
+- A new entity is introduced
+- A user gives feedback or clarification
+
+Storing this context allows the agent to reason better in future interactions.
+
+
+### More Details
+
+For full list of supported fields, required formats, and advanced options, see the
+[Add Memory API Reference](/api-reference/memory/add-memories).
+
+---
+
+## Need help?
+If you have any questions, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx"/>

docs/core-concepts/memory-operations/delete.mdx

@@ -0,0 +1,141 @@
+---
+title: Delete Memory
+description: Remove memories from Mem0 either individually, in bulk, or via filters.
+icon: "trash"
+iconType: "solid"
+---
+
+## Overview
+
+Memories can become outdated, irrelevant, or need to be removed for privacy or compliance reasons. Mem0 offers flexible ways to delete memory:
+
+1. **Delete a Single Memory**: Using a specific memory ID
+2. **Batch Delete**: Delete multiple known memory IDs (up to 1000)
+3. **Filtered Delete**: Delete memories matching a filter (e.g., `user_id`, `metadata`, `run_id`)
+
+This page walks through code example for each method.
+
+
+## Use Cases
+
+- Forget a user’s past preferences by request
+- Remove outdated or incorrect memory entries
+- Clean up memory after session expiration
+- Comply with data deletion requests (e.g., GDPR)
+
+---
+
+## 1. Delete a Single Memory by ID
+
+<CodeGroup>
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+memory_id = "your_memory_id"
+client.delete(memory_id=memory_id)
+```
+
+```javascript JavaScript
+import MemoryClient from 'mem0ai';
+
+const client = new MemoryClient({ apiKey: "your-api-key" });
+
+client.delete("your_memory_id")
+  .then(result => console.log(result))
+  .catch(error => console.error(error));
+```
+</CodeGroup>
+
+---
+
+## 2. Batch Delete Multiple Memories
+
+<CodeGroup>
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+delete_memories = [
+    {"memory_id": "id1"},
+    {"memory_id": "id2"}
+]
+
+response = client.batch_delete(delete_memories)
+print(response)
+```
+
+```javascript JavaScript
+import MemoryClient from 'mem0ai';
+
+const client = new MemoryClient({ apiKey: "your-api-key" });
+
+const deleteMemories = [
+  { memory_id: "id1" },
+  { memory_id: "id2" }
+];
+
+client.batchDelete(deleteMemories)
+  .then(response => console.log('Batch delete response:', response))
+  .catch(error => console.error(error));
+```
+</CodeGroup>
+
+---
+
+## 3. Delete Memories by Filter (e.g., user_id)
+
+<CodeGroup>
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+# Delete all memories for a specific user
+client.delete_all(user_id="alice")
+```
+
+```javascript JavaScript
+import MemoryClient from 'mem0ai';
+
+const client = new MemoryClient({ apiKey: "your-api-key" });
+
+client.deleteAll({ user_id: "alice" })
+  .then(result => console.log(result))
+  .catch(error => console.error(error));
+```
+</CodeGroup>
+
+You can also filter by other parameters such as:
+- `agent_id`
+- `run_id`
+- `metadata` (as JSON string)
+
+---
+
+## Key Differences
+
+| Method                | Use When                                | IDs Needed | Filters |
+|----------------------|-------------------------------------------|------------|----------|
+| `delete(memory_id)`  | You know exactly which memory to remove   | ✔          | ✘        |
+| `batch_delete([...])`| You have a known list of memory IDs       | ✔          | ✘        |
+| `delete_all(...)`    | You want to delete by user/agent/run/etc | ✘          | ✔        |
+
+
+### More Details
+
+For request/response schema and additional filtering options, see:
+- [Delete Memory API Reference](/api-reference/memory/delete-memory)
+- [Batch Delete API Reference](/api-reference/memory/batch-delete)
+- [Delete Memories by Filter Reference](/api-reference/memory/delete-memories)
+
+You’ve now seen how to add, search, update, and delete memories in Mem0.
+
+---
+
+## Need help?
+If you have any questions, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx"/>

docs/core-concepts/memory-operations/search.mdx

@@ -0,0 +1,124 @@
+---
+title: Search Memory
+description: Retrieve relevant memories from Mem0 using powerful semantic and filtered search capabilities.
+icon: "magnifying-glass"
+iconType: "solid"
+---
+
+## Overview
+
+The `search` operation allows you to retrieve relevant memories based on a natural language query and optional filters like user ID, agent ID, categories, and more. This is the foundation of giving your agents memory-aware behavior.
+
+Mem0 supports:
+- Semantic similarity search
+- Metadata filtering (with advanced logic)
+- Reranking and thresholds
+- Cross-agent, multi-session context resolution
+
+This applies to both:
+- **Mem0 Platform** (hosted API with full-scale features)
+- **Mem0 Open Source** (local-first with LLM inference and local vector DB)
+
+
+## Architecture
+
+<Frame caption="Architecture diagram illustrating the memory search process.">
+  <img src="../../images/search_architecture.png" />
+</Frame>
+
+The search flow follows these steps:
+
+1. **Query Processing**
+   An LLM refines and optimizes your natural language query.
+
+2. **Vector Search**
+   Semantic embeddings are used to find the most relevant memories using cosine similarity.
+
+3. **Filtering & Ranking**
+   Logical and comparison-based filters are applied. Memories are scored, filtered, and optionally reranked.
+
+4. **Results Delivery**
+   Relevant memories are returned with associated metadata and timestamps.
+
+---
+
+## Example: Mem0 Platform
+
+<CodeGroup>
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+query = "What do you know about me?"
+filters = {
+   "OR": [
+      {"user_id": "alice"},
+      {"agent_id": {"in": ["travel-assistant", "customer-support"]}}
+   ]
+}
+
+results = client.search(query, version="v2", filters=filters)
+```
+
+```javascript JavaScript
+import { MemoryClient } from "mem0ai";
+
+const client = new MemoryClient({apiKey: "your-api-key"});
+
+const query = "I'm craving some pizza. Any recommendations?";
+const filters = {
+  AND: [
+    { user_id: "alice" }
+  ]
+};
+
+const results = await client.search(query, {
+  version: "v2",
+  filters
+});
+```
+</CodeGroup>
+
+---
+
+## Example: Mem0 Open Source
+
+<CodeGroup>
+```python Python
+from mem0 import Memory
+
+m = Memory()
+related_memories = m.search("Should I drink coffee or tea?", user_id="alice")
+```
+
+```javascript JavaScript
+import { Memory } from 'mem0ai/oss';
+
+const memory = new Memory();
+const relatedMemories = memory.search("Should I drink coffee or tea?", { userId: "alice" });
+```
+</CodeGroup>
+
+---
+
+## Tips for Better Search
+
+- Use descriptive natural queries (Mem0 can interpret intent)
+- Apply filters for scoped, faster lookup
+- Use `version: "v2"` for enhanced results
+- Consider wildcard filters (e.g., `run_id: "*"`) for broader matches
+- Tune with `top_k`, `threshold`, or `rerank` if needed
+
+
+### More Details
+
+For the full list of filter logic, comparison operators, and optional search parameters, see the
+[Search Memory API Reference](/api-reference/memory/v2-search-memories).
+
+---
+
+## Need help?
+If you have any questions, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx"/>

docs/core-concepts/memory-operations/update.mdx

@@ -0,0 +1,117 @@
+---
+title: Update Memory
+description: Modify an existing memory by updating its content or metadata.
+icon: "pencil"
+iconType: "solid"
+---
+
+## Overview
+
+User preferences, interests, and behaviors often evolve over time. The `update` operation lets you revise a stored memory, whether it's updating facts and memories, rephrasing a message, or enriching metadata.
+
+Mem0 supports both:
+- **Single Memory Update** for one specific memory using its ID
+- **Batch Update** for updating many memories at once (up to 1000)
+
+This guide includes usage for both single update and batch update of memories through **Mem0 Platform**
+
+
+## Use Cases
+
+- Refine a vague or incorrect memory after a correction
+- Add or edit memory with new metadata (e.g., categories, tags)
+- Evolve factual knowledge as the user’s profile changes
+- A user profile evolves: “I love spicy food” → later says “Actually, I can’t handle spicy food.”
+
+Updating memory ensures your agents remain accurate, adaptive, and personalized.
+
+---
+
+## Update Memory
+
+<CodeGroup>
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+memory_id = "your_memory_id"
+client.update(
+    memory_id=memory_id,
+    text="Updated memory content about the user",
+    metadata={"category": "profile-update"}
+)
+```
+
+```javascript JavaScript
+import MemoryClient from 'mem0ai';
+
+const client = new MemoryClient({ apiKey: "your-api-key" });
+const memory_id = "your_memory_id";
+
+client.update(memory_id, {
+  text: "Updated memory content about the user",
+  metadata: { category: "profile-update" }
+})
+  .then(result => console.log(result))
+  .catch(error => console.error(error));
+```
+</CodeGroup>
+
+---
+
+## Batch Update
+
+Update up to 1000 memories in one call.
+
+<CodeGroup>
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+update_memories = [
+    {"memory_id": "id1", "text": "Watches football"},
+    {"memory_id": "id2", "text": "Likes to travel"}
+]
+
+response = client.batch_update(update_memories)
+print(response)
+```
+
+```javascript JavaScript
+import MemoryClient from 'mem0ai';
+
+const client = new MemoryClient({ apiKey: "your-api-key" });
+
+const updateMemories = [
+  { memoryId: "id1", text: "Watches football" },
+  { memoryId: "id2", text: "Likes to travel" }
+];
+
+client.batchUpdate(updateMemories)
+  .then(response => console.log('Batch update response:', response))
+  .catch(error => console.error(error));
+```
+</CodeGroup>
+
+---
+
+## Tips
+
+- You can update both `text` and `metadata` in the same call.
+- Use `batchUpdate` when you're applying similar corrections at scale.
+- If memory is marked `immutable`, it must first be deleted and re-added.
+- Combine this with feedback mechanisms (e.g., user thumbs-up/down) to self-improve memory.
+
+
+### More Details
+
+Refer to the full [Update Memory API Reference](/api-reference/memory/update-memory) and [Batch Update Reference](/api-reference/memory/batch-update) for schema and advanced fields.
+
+---
+
+## Need help?
+If you have any questions, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx"/>

docs/core-concepts/memory-types.mdx

@@ -4,6 +4,7 @@ description: Understanding different types of memory in AI Applications
 icon: "memory"
 iconType: "solid"
 ---
+
 To build useful AI applications, we need to understand how different memory systems work together. This guide explores the fundamental types of memory in AI systems and shows how Mem0 implements these concepts.
 
 ## Why Memory Matters

docs/docs.json

@@ -1,162 +1,390 @@
 {
   "$schema": "https://mintlify.com/docs.json",
-  "theme": "maple",
   "name": "Mem0",
   "description": "Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users.",
+  "theme": "aspen",
   "colors": {
-    "primary": "#6c60f0",
-    "light": "#E6FFA2",
-    "dark": "#a3df02"
+    "primary": "#2553eb",
+    "light": "#6084fa",
+    "dark": "#2553eb"
   },
   "favicon": "/logo/favicon.png",
   "navigation": {
-    "anchors": [
+    "versions": [
       {
-        "anchor": "Documentation",
-        "icon": "book-open",
-        "tabs": [
+        "version": "v1.0.0 Beta",
+        "anchors": [
           {
-            "tab": "Documentation",
-            "groups": [
+            "anchor": "Documentation",
+            "icon": "book-open",
+            "tabs": [
               {
-                "group": "Get Started",
-                "icon": "rocket",
-                "pages": [
-                  "overview",
-                  "quickstart",
-                  "faqs"
-                ]
-              },
-              {
-                "group": "Core Concepts",
-                "icon": "brain",
-                "pages": [
-                  "core-concepts/memory-types",
-                  "core-concepts/memory-operations"
-                ]
-              },
-              {
-                "group": "Platform",
-                "icon": "cogs",
-                "pages": [
-                  "platform/overview",
-                  "platform/quickstart",
+                "tab": "Documentation",
+                "groups": [
                   {
-                    "group": "Features",
-                    "icon": "star",
+                    "group": "Getting Started",
+                    "icon": "rocket",
                     "pages": [
-                      "features/platform-overview",
-                      "features/advanced-retrieval",
-                      "features/contextual-add",
-                      "features/multimodal-support",
-                      "features/selective-memory",
-                      "features/custom-categories",
-                      "features/custom-instructions",
-                      "features/direct-import",
-                      "features/async-client",
-                      "features/memory-export",
-                      "features/webhooks",
-                      "features/graph-memory",
-                      "features/feedback-mechanism"
-                    ]
-                  }
-                ]
-              },
-              {
-                "group": "Open Source",
-                "icon": "code-branch",
-                "pages": [
-                  "open-source/quickstart",
-                  "open-source/python-quickstart",
-                  "open-source/node-quickstart",
-                  {
-                    "group": "Features",
-                    "icon": "wrench",
-                    "pages": [
-                      "features/openai_compatibility",
-                      "features/custom-fact-extraction-prompt",
-                      "features/custom-update-memory-prompt",
-                      "open-source/multimodal-support",
-                      "open-source/features/rest-api"
+                      "introduction",
+                      "quickstart",
+                      "faqs"
                     ]
                   },
                   {
-                    "group": "Graph Memory",
-                    "icon": "spider-web",
-                    "pages": [
-                      "open-source/graph_memory/overview",
-                      "open-source/graph_memory/features"
-                    ]
-                  },
-                  {
-                    "group": "LLMs",
+                    "group": "Core Concepts",
                     "icon": "brain",
                     "pages": [
-                      "components/llms/overview",
-                      "components/llms/config",
+                      "core-concepts/memory-types",
                       {
-                        "group": "Supported LLMs",
-                        "icon": "list",
+                        "group": "Memory Operations",
+                        "icon": "gear",
                         "pages": [
-                          "components/llms/models/openai",
-                          "components/llms/models/anthropic",
-                          "components/llms/models/azure_openai",
-                          "components/llms/models/ollama",
-                          "components/llms/models/together",
-                          "components/llms/models/groq",
-                          "components/llms/models/litellm",
-                          "components/llms/models/mistral_AI",
-                          "components/llms/models/google_AI",
-                          "components/llms/models/aws_bedrock",
-                          "components/llms/models/gemini",
-                          "components/llms/models/deepseek",
-                          "components/llms/models/xAI"
+                          "core-concepts/memory-operations/add",
+                          "core-concepts/memory-operations/search",
+                          "core-concepts/memory-operations/update",
+                          "core-concepts/memory-operations/delete"
                         ]
                       }
                     ]
                   },
                   {
-                    "group": "Vector Databases",
-                    "icon": "database",
+                    "group": "Platform",
+                    "icon": "globe",
                     "pages": [
-                      "components/vectordbs/overview",
-                      "components/vectordbs/config",
+                      "platform/overview",
+                      "platform/quickstart",
+                      "platform/advanced-memory-operations",
                       {
-                        "group": "Supported Vector Databases",
-                        "icon": "server",
+                        "group": "Features",
+                        "icon": "star",
                         "pages": [
-                          "components/vectordbs/dbs/qdrant",
-                          "components/vectordbs/dbs/chroma",
-                          "components/vectordbs/dbs/pgvector",
-                          "components/vectordbs/dbs/milvus",
-                          "components/vectordbs/dbs/pinecone",
-                          "components/vectordbs/dbs/azure_ai_search",
-                          "components/vectordbs/dbs/redis",
-                          "components/vectordbs/dbs/elasticsearch",
-                          "components/vectordbs/dbs/opensearch",
-                          "components/vectordbs/dbs/supabase",
-                          "components/vectordbs/dbs/vertex_ai_vector_search",
-                          "components/vectordbs/dbs/weaviate"
+                          "platform/features/platform-overview",
+                          "platform/features/contextual-add",
+                          "platform/features/async-client",
+                          "platform/features/graph-memory",
+                          "platform/features/advanced-retrieval",
+                          "platform/features/criteria-retrieval",
+                          "platform/features/multimodal-support",
+                          "platform/features/selective-memory",
+                          "platform/features/custom-categories",
+                          "platform/features/custom-instructions",
+                          "platform/features/direct-import",
+                          "platform/features/memory-export",
+                          "platform/features/timestamp",
+                          "platform/features/expiration-date",
+                          "platform/features/webhooks",
+                          "platform/features/feedback-mechanism",
+                          "platform/features/group-chat"
                         ]
                       }
                     ]
                   },
                   {
-                    "group": "Embedding Models",
-                    "icon": "layer-group",
+                    "group": "Open Source",
+                    "icon": "code-branch",
                     "pages": [
-                      "components/embedders/overview",
-                      "components/embedders/config",
+                      "open-source/overview",
+                      "open-source/python-quickstart",
+                      "open-source/node-quickstart",
                       {
-                        "group": "Supported Embedding Models",
-                        "icon": "list",
+                        "group": "Features",
+                        "icon": "star",
                         "pages": [
-                          "components/embedders/models/openai",
-                          "components/embedders/models/azure_openai",
-                          "components/embedders/models/ollama",
-                          "components/embedders/models/huggingface",
-                          "components/embedders/models/vertexai",
-                          "components/embedders/models/gemini"
+                          "open-source/features/overview",
+                          "open-source/features/async-memory",
+                          "open-source/features/openai_compatibility",
+                          "open-source/features/custom-fact-extraction-prompt",
+                          "open-source/features/custom-update-memory-prompt",
+                          "open-source/features/multimodal-support",
+                          "open-source/features/rest-api",
+                          "open-source/features/metadata-filtering",
+                          "open-source/features/reranker-search"
+                        ]
+                      },
+                      {
+                        "group": "Graph Memory",
+                        "icon": "spider-web",
+                        "pages": [
+                          "open-source/graph_memory/overview",
+                          "open-source/graph_memory/features"
+                        ]
+                      },
+                      {
+                        "group": "LLMs",
+                        "icon": "brain",
+                        "pages": [
+                          "components/llms/overview",
+                          "components/llms/config",
+                          {
+                            "group": "Supported LLMs",
+                            "icon": "list",
+                            "pages": [
+                              "components/llms/models/openai",
+                              "components/llms/models/anthropic",
+                              "components/llms/models/azure_openai",
+                              "components/llms/models/ollama",
+                              "components/llms/models/together",
+                              "components/llms/models/groq",
+                              "components/llms/models/litellm",
+                              "components/llms/models/mistral_AI",
+                              "components/llms/models/google_AI",
+                              "components/llms/models/aws_bedrock",
+                              "components/llms/models/deepseek",
+                              "components/llms/models/xAI",
+                              "components/llms/models/sarvam",
+                              "components/llms/models/lmstudio",
+                              "components/llms/models/langchain",
+                              "components/llms/models/vllm"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Vector Databases",
+                        "icon": "database",
+                        "pages": [
+                          "components/vectordbs/overview",
+                          "components/vectordbs/config",
+                          {
+                            "group": "Supported Vector Databases",
+                            "icon": "server",
+                            "pages": [
+                              "components/vectordbs/dbs/qdrant",
+                              "components/vectordbs/dbs/chroma",
+                              "components/vectordbs/dbs/pgvector",
+                              "components/vectordbs/dbs/milvus",
+                              "components/vectordbs/dbs/pinecone",
+                              "components/vectordbs/dbs/mongodb",
+                              "components/vectordbs/dbs/azure",
+                              "components/vectordbs/dbs/redis",
+                              "components/vectordbs/dbs/valkey",
+                              "components/vectordbs/dbs/elasticsearch",
+                              "components/vectordbs/dbs/opensearch",
+                              "components/vectordbs/dbs/supabase",
+                              "components/vectordbs/dbs/upstash-vector",
+                              "components/vectordbs/dbs/vectorize",
+                              "components/vectordbs/dbs/vertex_ai",
+                              "components/vectordbs/dbs/weaviate",
+                              "components/vectordbs/dbs/faiss",
+                              "components/vectordbs/dbs/langchain",
+                              "components/vectordbs/dbs/baidu",
+                              "components/vectordbs/dbs/s3_vectors",
+                              "components/vectordbs/dbs/databricks",
+                              "components/vectordbs/dbs/neptune_analytics"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Embedding Models",
+                        "icon": "layer-group",
+                        "pages": [
+                          "components/embedders/overview",
+                          "components/embedders/config",
+                          {
+                            "group": "Supported Embedding Models",
+                            "icon": "list",
+                            "pages": [
+                              "components/embedders/models/openai",
+                              "components/embedders/models/azure_openai",
+                              "components/embedders/models/ollama",
+                              "components/embedders/models/huggingface",
+                              "components/embedders/models/vertexai",
+                              "components/embedders/models/google_AI",
+                              "components/embedders/models/lmstudio",
+                              "components/embedders/models/together",
+                              "components/embedders/models/langchain",
+                              "components/embedders/models/aws_bedrock"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Rerankers (New in v1.0)",
+                        "icon": "sort",
+                        "pages": [
+                          "components/rerankers/overview",
+                          "components/rerankers/config",
+                          {
+                            "group": "Supported Rerankers",
+                            "icon": "list",
+                            "pages": [
+                              "components/rerankers/models/cohere",
+                              "components/rerankers/models/sentence_transformer",
+                              "components/rerankers/models/huggingface",
+                              "components/rerankers/models/llm_reranker"
+                            ]
+                          }
+                        ]
+                      }
+                    ]
+                  },
+                  {
+                    "group": "Migration Guide",
+                    "icon": "arrow-right",
+                    "pages": [
+                      "migration/v0-to-v1",
+                      "migration/breaking-changes",
+                      "migration/api-changes"
+                    ]
+                  },
+                  {
+                    "group": "OpenMemory",
+                    "icon": "square-terminal",
+                    "pages": [
+                      "openmemory/overview",
+                      "openmemory/quickstart",
+                      "openmemory/integrations"
+                    ]
+                  },
+                  {
+                    "group": "Contribution",
+                    "icon": "handshake",
+                    "pages": [
+                      "contributing/development",
+                      "contributing/documentation"
+                    ]
+                  }
+                ]
+              },
+              {
+                "tab": "Examples",
+                "groups": [
+                  {
+                    "group": "💡 Examples",
+                    "icon": "lightbulb",
+                    "pages": [
+                      "examples",
+                      "examples/aws_example",
+                      "examples/aws_neptune_analytics_hybrid_store",
+                      "examples/mem0-demo",
+                      "examples/ai_companion_js",
+                      "examples/collaborative-task-agent",
+                      "examples/llamaindex-multiagent-learning-system",
+                      "examples/personalized-search-tavily-mem0",
+                      "examples/eliza_os",
+                      "examples/mem0-mastra",
+                      "examples/mem0-with-ollama",
+                      "examples/personal-ai-tutor",
+                      "examples/customer-support-agent",
+                      "examples/personal-travel-assistant",
+                      "examples/llama-index-mem0",
+                      "examples/chrome-extension",
+                      "examples/memory-guided-content-writing",
+                      "examples/multimodal-demo",
+                      "examples/personalized-deep-research",
+                      "examples/mem0-agentic-tool",
+                      "examples/openai-inbuilt-tools",
+                      "examples/mem0-openai-voice-demo",
+                      "examples/mem0-google-adk-healthcare-assistant",
+                      "examples/email_processing",
+                      "examples/youtube-assistant"
+                    ]
+                  }
+                ]
+              },
+              {
+                "tab": "Integrations",
+                "groups": [
+                  {
+                    "group": "Integrations",
+                    "icon": "plug",
+                    "pages": [
+                      "integrations",
+                      "integrations/langchain",
+                      "integrations/langgraph",
+                      "integrations/llama-index",
+                      "integrations/agno",
+                      "integrations/autogen",
+                      "integrations/crewai",
+                      "integrations/openai-agents-sdk",
+                      "integrations/google-ai-adk",
+                      "integrations/mastra",
+                      "integrations/vercel-ai-sdk",
+                      "integrations/livekit",
+                      "integrations/pipecat",
+                      "integrations/elevenlabs",
+                      "integrations/aws-bedrock",
+                      "integrations/flowise",
+                      "integrations/langchain-tools",
+                      "integrations/agentops",
+                      "integrations/keywords",
+                      "integrations/dify",
+                      "integrations/raycast"
+                    ]
+                  }
+                ]
+              },
+              {
+                "tab": "API Reference",
+                "icon": "square-terminal",
+                "groups": [
+                  {
+                    "group": "API Reference",
+                    "icon": "terminal",
+                    "pages": [
+                      "api-reference",
+                      {
+                        "group": "Memory APIs",
+                        "icon": "microchip",
+                        "pages": [
+                          "api-reference/memory/add-memories",
+                          "api-reference/memory/v2-search-memories",
+                          "api-reference/memory/v1-search-memories",
+                          "api-reference/memory/v2-get-memories",
+                          "api-reference/memory/v1-get-memories",
+                          "api-reference/memory/history-memory",
+                          "api-reference/memory/get-memory",
+                          "api-reference/memory/update-memory",
+                          "api-reference/memory/batch-update",
+                          "api-reference/memory/delete-memory",
+                          "api-reference/memory/batch-delete",
+                          "api-reference/memory/delete-memories",
+                          "api-reference/memory/create-memory-export",
+                          "api-reference/memory/get-memory-export",
+                          "api-reference/memory/feedback"
+                        ]
+                      },
+                      {
+                        "group": "Entities APIs",
+                        "icon": "users",
+                        "pages": [
+                          "api-reference/entities/get-users",
+                          "api-reference/entities/delete-user"
+                        ]
+                      },
+                      {
+                        "group": "Organizations APIs",
+                        "icon": "building",
+                        "pages": [
+                          "api-reference/organization/create-org",
+                          "api-reference/organization/get-orgs",
+                          "api-reference/organization/get-org",
+                          "api-reference/organization/get-org-members",
+                          "api-reference/organization/add-org-member",
+                          "api-reference/organization/delete-org"
+                        ]
+                      },
+                      {
+                        "group": "Project APIs",
+                        "icon": "folder",
+                        "pages": [
+                          "api-reference/project/create-project",
+                          "api-reference/project/get-projects",
+                          "api-reference/project/get-project",
+                          "api-reference/project/get-project-members",
+                          "api-reference/project/add-project-member",
+                          "api-reference/project/delete-project"
+                        ]
+                      },
+                      {
+                        "group": "Webhook APIs",
+                        "icon": "webhook",
+                        "pages": [
+                          "api-reference/webhook/create-webhook",
+                          "api-reference/webhook/get-webhook",
+                          "api-reference/webhook/update-webhook",
+                          "api-reference/webhook/delete-webhook"
                         ]
                       }
                     ]
@@ -164,119 +392,14 @@
                 ]
               },
               {
-                "group": "Contribution",
-                "icon": "handshake",
-                "pages": [
-                  "contributing/development",
-                  "contributing/documentation"
-                ]
-              }
-            ]
-          },
-          {
-            "tab": "Examples",
-            "groups": [
-              {
-                "group": "💡 Examples",
-                "icon": "lightbulb",
-                "pages": [
-                  "examples/overview",
-                  "examples/mem0-demo",
-                  "examples/ai_companion_js",
-                  "examples/mem0-with-ollama",
-                  "examples/personal-ai-tutor",
-                  "examples/customer-support-agent",
-                  "examples/personal-travel-assistant",
-                  "examples/llama-index-mem0",
-                  "examples/chrome-extension",
-                  "examples/document-writing",
-                  "examples/multimodal-demo",
-                  "examples/personalized-deep-research",
-                  "examples/mem0-agentic-tool",
-                  "examples/openai-inbuilt-tools",
-                  "examples/mem0-openai-voice-demo"
-                ]
-              }
-            ]
-          },
-          {
-            "tab": "Integrations",
-            "groups": [
-              {
-                "group": "Integrations",
-                "icon": "plug",
-                "pages": [
-                  "integrations/overview",
-                  "integrations/vercel-ai-sdk",
-                  "integrations/crewai",
-                  "integrations/autogen",
-                  "integrations/langchain",
-                  "integrations/langgraph",
-                  "integrations/llama-index",
-                  "integrations/langchain-tools",
-                  "integrations/dify",
-                  "integrations/mcp-server"
-                ]
-              }
-            ]
-          },
-          {
-            "tab": "API Reference",
-            "icon": "square-terminal",
-            "groups": [
-              {
-                "group": "API Reference",
-                "icon": "terminal",
-                "pages": [
-                  "api-reference/overview",
+                "tab": "Changelog",
+                "icon": "clock",
+                "groups": [
                   {
-                    "group": "Memory APIs",
-                    "icon": "microchip",
+                    "group": "Product Updates",
+                    "icon": "rocket",
                     "pages": [
-                      "api-reference/memory/add-memories",
-                      "api-reference/memory/v2-search-memories",
-                      "api-reference/memory/v1-search-memories",
-                      "api-reference/memory/v2-get-memories",
-                      "api-reference/memory/v1-get-memories",
-                      "api-reference/memory/history-memory",
-                      "api-reference/memory/get-memory",
-                      "api-reference/memory/update-memory",
-                      "api-reference/memory/batch-update",
-                      "api-reference/memory/delete-memory",
-                      "api-reference/memory/batch-delete",
-                      "api-reference/memory/delete-memories",
-                      "api-reference/memory/create-memory-export",
-                      "api-reference/memory/get-memory-export"
-                    ]
-                  },
-                  {
-                    "group": "Entities APIs",
-                    "icon": "users",
-                    "pages": [
-                      "api-reference/entities/get-users",
-                      "api-reference/entities/delete-user"
-                    ]
-                  },
-                  {
-                    "group": "Organizations APIs",
-                    "icon": "building",
-                    "pages": [
-                      "api-reference/organization/create-org",
-                      "api-reference/organization/get-orgs",
-                      "api-reference/organization/get-org",
-                      "api-reference/organization/get-org-members",
-                      "api-reference/organization/add-org-member",
-                      "api-reference/organization/delete-org"
-                    ]
-                  },
-                  {
-                    "group": "Webhook APIs",
-                    "icon": "webhook",
-                    "pages": [
-                      "api-reference/webhook/create-webhook",
-                      "api-reference/webhook/get-webhook",
-                      "api-reference/webhook/update-webhook",
-                      "api-reference/webhook/delete-webhook"
+                      "changelog"
                     ]
                   }
                 ]
@@ -286,29 +409,211 @@
         ]
       },
       {
-        "anchor": "Your Dashboard",
-        "href": "https://app.mem0.ai",
-        "icon": "chart-simple"
-      },
-      {
-        "anchor": "Demo",
-        "href": "https://mem0.dev/demo",
-        "icon": "play"
-      },
-      {
-        "anchor": "Discord",
-        "href": "https://mem0.dev/DiD",
-        "icon": "discord"
-      },
-      {
-        "anchor": "GitHub",
-        "href": "https://github.com/mem0ai/mem0",
-        "icon": "github"
-      },
-      {
-        "anchor": "Support",
-        "href": "mailto:founders@mem0.ai",
-        "icon": "envelope"
+        "version": "v0.x Legacy",
+        "anchors": [
+          {
+            "anchor": "Documentation",
+            "icon": "book-open",
+            "tabs": [
+              {
+                "tab": "Documentation",
+                "groups": [
+                  {
+                    "group": "Getting Started",
+                    "icon": "rocket",
+                    "pages": [
+                      "v0x/introduction",
+                      "v0x/quickstart",
+                      "v0x/faqs"
+                    ]
+                  },
+                  {
+                    "group": "Core Concepts",
+                    "icon": "brain",
+                    "pages": [
+                      "v0x/core-concepts/memory-types",
+                      {
+                        "group": "Memory Operations",
+                        "icon": "gear",
+                        "pages": [
+                          "v0x/core-concepts/memory-operations/add",
+                          "v0x/core-concepts/memory-operations/search",
+                          "v0x/core-concepts/memory-operations/update",
+                          "v0x/core-concepts/memory-operations/delete"
+                        ]
+                      }
+                    ]
+                  },
+                  {
+                    "group": "Open Source",
+                    "icon": "code-branch",
+                    "pages": [
+                      "v0x/open-source/overview",
+                      "v0x/open-source/python-quickstart",
+                      "v0x/open-source/node-quickstart",
+                      {
+                        "group": "LLMs",
+                        "icon": "brain",
+                        "pages": [
+                          "v0x/components/llms/overview",
+                          "v0x/components/llms/config",
+                          {
+                            "group": "Supported LLMs",
+                            "icon": "list",
+                            "pages": [
+                              "v0x/components/llms/models/openai",
+                              "v0x/components/llms/models/anthropic",
+                              "v0x/components/llms/models/azure_openai",
+                              "v0x/components/llms/models/ollama",
+                              "v0x/components/llms/models/together",
+                              "v0x/components/llms/models/groq",
+                              "v0x/components/llms/models/litellm",
+                              "v0x/components/llms/models/mistral_AI",
+                              "v0x/components/llms/models/google_AI",
+                              "v0x/components/llms/models/aws_bedrock",
+                              "v0x/components/llms/models/deepseek",
+                              "v0x/components/llms/models/xAI",
+                              "v0x/components/llms/models/sarvam",
+                              "v0x/components/llms/models/lmstudio",
+                              "v0x/components/llms/models/langchain",
+                              "v0x/components/llms/models/vllm"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Vector Databases",
+                        "icon": "database",
+                        "pages": [
+                          "v0x/components/vectordbs/overview",
+                          "v0x/components/vectordbs/config",
+                          {
+                            "group": "Supported Vector Databases",
+                            "icon": "server",
+                            "pages": [
+                              "v0x/components/vectordbs/dbs/qdrant",
+                              "v0x/components/vectordbs/dbs/chroma",
+                              "v0x/components/vectordbs/dbs/pgvector",
+                              "v0x/components/vectordbs/dbs/milvus",
+                              "v0x/components/vectordbs/dbs/pinecone",
+                              "v0x/components/vectordbs/dbs/mongodb",
+                              "v0x/components/vectordbs/dbs/azure",
+                              "v0x/components/vectordbs/dbs/redis",
+                              "v0x/components/vectordbs/dbs/valkey",
+                              "v0x/components/vectordbs/dbs/elasticsearch",
+                              "v0x/components/vectordbs/dbs/opensearch",
+                              "v0x/components/vectordbs/dbs/supabase",
+                              "v0x/components/vectordbs/dbs/upstash-vector",
+                              "v0x/components/vectordbs/dbs/vectorize",
+                              "v0x/components/vectordbs/dbs/vertex_ai",
+                              "v0x/components/vectordbs/dbs/weaviate",
+                              "v0x/components/vectordbs/dbs/faiss",
+                              "v0x/components/vectordbs/dbs/langchain",
+                              "v0x/components/vectordbs/dbs/baidu",
+                              "v0x/components/vectordbs/dbs/s3_vectors",
+                              "v0x/components/vectordbs/dbs/databricks",
+                              "v0x/components/vectordbs/dbs/neptune_analytics"
+                            ]
+                          }
+                        ]
+                      },
+                      {
+                        "group": "Embedding Models",
+                        "icon": "layer-group",
+                        "pages": [
+                          "v0x/components/embedders/overview",
+                          "v0x/components/embedders/config",
+                          {
+                            "group": "Supported Embedding Models",
+                            "icon": "list",
+                            "pages": [
+                              "v0x/components/embedders/models/openai",
+                              "v0x/components/embedders/models/azure_openai",
+                              "v0x/components/embedders/models/ollama",
+                              "v0x/components/embedders/models/huggingface",
+                              "v0x/components/embedders/models/vertexai",
+                              "v0x/components/embedders/models/google_AI",
+                              "v0x/components/embedders/models/lmstudio",
+                              "v0x/components/embedders/models/together",
+                              "v0x/components/embedders/models/langchain",
+                              "v0x/components/embedders/models/aws_bedrock"
+                            ]
+                          }
+                        ]
+                      }
+                    ]
+                  }
+                ]
+              },
+              {
+                "tab": "Examples",
+                "groups": [
+                  {
+                    "group": "💡 Examples",
+                    "icon": "lightbulb",
+                    "pages": [
+                      "v0x/examples/aws_example",
+                      "v0x/examples/aws_neptune_analytics_hybrid_store",
+                      "v0x/examples/mem0-demo",
+                      "v0x/examples/ai_companion_js",
+                      "v0x/examples/collaborative-task-agent",
+                      "v0x/examples/llamaindex-multiagent-learning-system",
+                      "v0x/examples/personalized-search-tavily-mem0",
+                      "v0x/examples/eliza_os",
+                      "v0x/examples/mem0-mastra",
+                      "v0x/examples/mem0-with-ollama",
+                      "v0x/examples/personal-ai-tutor",
+                      "v0x/examples/customer-support-agent",
+                      "v0x/examples/personal-travel-assistant",
+                      "v0x/examples/llama-index-mem0",
+                      "v0x/examples/chrome-extension",
+                      "v0x/examples/memory-guided-content-writing",
+                      "v0x/examples/multimodal-demo",
+                      "v0x/examples/personalized-deep-research",
+                      "v0x/examples/mem0-agentic-tool",
+                      "v0x/examples/openai-inbuilt-tools",
+                      "v0x/examples/mem0-openai-voice-demo",
+                      "v0x/examples/mem0-google-adk-healthcare-assistant",
+                      "v0x/examples/email_processing",
+                      "v0x/examples/youtube-assistant"
+                    ]
+                  }
+                ]
+              },
+              {
+                "tab": "Integrations",
+                "groups": [
+                  {
+                    "group": "Integrations",
+                    "icon": "plug",
+                    "pages": [
+                      "v0x/integrations/langchain",
+                      "v0x/integrations/langgraph",
+                      "v0x/integrations/llama-index",
+                      "v0x/integrations/agno",
+                      "v0x/integrations/autogen",
+                      "v0x/integrations/crewai",
+                      "v0x/integrations/openai-agents-sdk",
+                      "v0x/integrations/google-ai-adk",
+                      "v0x/integrations/mastra",
+                      "v0x/integrations/vercel-ai-sdk",
+                      "v0x/integrations/livekit",
+                      "v0x/integrations/pipecat",
+                      "v0x/integrations/elevenlabs",
+                      "v0x/integrations/aws-bedrock",
+                      "v0x/integrations/flowise",
+                      "v0x/integrations/langchain-tools",
+                      "v0x/integrations/agentops",
+                      "v0x/integrations/keywords",
+                      "v0x/integrations/dify",
+                      "v0x/integrations/raycast"
+                    ]
+                  }
+                ]
+              }
+            ]
+          }
+        ]
       }
     ]
   },
@@ -320,7 +625,7 @@
   "background": {
     "color": {
       "light": "#fff",
-      "dark": "#0f1117"
+      "dark": "#09090b"
     }
   },
   "navbar": {

docs/examples.mdx

@@ -3,7 +3,6 @@ title: Overview
 description: How to use mem0 in your existing applications?
 ---
 
-
 With Mem0, you can create stateful LLM-based applications such as chatbots, virtual assistants, or AI agents. Mem0 enhances your applications by providing a memory layer that makes responses:
 
 - More personalized
@@ -18,56 +17,72 @@ Here are some examples of how Mem0 can be integrated into various applications:
 
 Explore how **Mem0** can power real-world applications and bring personalized, intelligent experiences to life:
 
-<CardGroup cols={2}>  
-  <Card title="AI Companion in Node.js" icon="node" href="/examples/ai_companion_js">  
-    Build a personalized AI Companion in **Node.js** that remembers conversations and adapts over time using Mem0.  
-  </Card>  
+<CardGroup cols={2}>
+  <Card title="AI Companion in Node.js" icon="node" href="/examples/ai_companion_js">
+    Build a personalized AI Companion in **Node.js** that remembers conversations and adapts over time using Mem0.
+  </Card>
 
-  <Card title="Mem0 with Ollama" icon="server" href="/examples/mem0-with-ollama">  
-    Run **Mem0 locally** with **Ollama** to create private, stateful AI experiences without relying on cloud APIs.  
-  </Card>  
+  <Card title="Mem0 with Ollama" icon="server" href="/examples/mem0-with-ollama">
+    Run **Mem0 locally** with **Ollama** to create private, stateful AI experiences without relying on cloud APIs.
+  </Card>
 
-  <Card title="Personal AI Tutor" icon="graduation-cap" href="/examples/personal-ai-tutor">  
-    Create an **AI Tutor** that adapts to student progress, learning style, and history — for a truly customized learning experience.  
-  </Card>  
+  <Card title="Personal AI Tutor" icon="graduation-cap" href="/examples/personal-ai-tutor">
+    Create an **AI Tutor** that adapts to student progress, learning style, and history — for a truly customized learning experience.
+  </Card>
 
-  <Card title="Personal Travel Assistant" icon="plane" href="/examples/personal-travel-assistant">  
-    Develop a **Personal Travel Assistant** that remembers your preferences, past trips, and helps plan future adventures.  
-  </Card>  
+  <Card title="Personal Travel Assistant" icon="plane" href="/examples/personal-travel-assistant">
+    Develop a **Personal Travel Assistant** that remembers your preferences, past trips, and helps plan future adventures.
+  </Card>
 
-  <Card title="Customer Support Agent" icon="headset" href="/examples/customer-support-agent">  
-    Build a **Customer Support AI** that recalls user preferences, past chats, and provides context-aware, efficient help.  
-  </Card>  
+  <Card title="Customer Support Agent" icon="headset" href="/examples/customer-support-agent">
+    Build a **Customer Support AI** that recalls user preferences, past chats, and provides context-aware, efficient help.
+  </Card>
 
-  <Card title="LlamaIndex + Mem0" icon="book-open" href="/examples/llama-index-mem0">  
-    Combine **LlamaIndex** and Mem0 to create a powerful **ReAct Agent** with persistent memory for smarter interactions.  
-  </Card>  
+  <Card title="LlamaIndex + Mem0" icon="book-open" href="/examples/llama-index-mem0">
+    Combine **LlamaIndex** and Mem0 to create a powerful **ReAct Agent** with persistent memory for smarter interactions.
+  </Card>
 
-  <Card title="Chrome Extension" icon="puzzle-piece" href="/examples/chrome-extension">  
-    Add **long-term memory** to ChatGPT, Claude, or Perplexity via the **Mem0 Chrome Extension** — personalize your AI chats anywhere.  
-  </Card>  
+  <Card title="LlamaIndex + Mem0 Learning System" icon="book-open" href="/examples/llama-index-mem0">
+    Multi-agent learning system powered by memory.
+  </Card>
 
-  <Card title="Document Writing Assistant" icon="pen" href="/examples/document-writing">  
-    Create a **Writing Assistant** that understands and adapts to your unique style, improving consistency and productivity.  
-  </Card>  
+  <Card title="Chrome Extension" icon="puzzle-piece" href="/examples/chrome-extension">
+    Add **long-term memory** to ChatGPT, Claude, or Perplexity via the **Mem0 Chrome Extension** — personalize your AI chats anywhere.
+  </Card>
 
-  <Card title="Multimodal AI Demo" icon="image" href="/examples/multimodal-demo">  
-    Supercharge AI with **Mem0's multimodal memory** — blend text, images, and more for richer, context-aware interactions.  
-  </Card>  
+  <Card title="YouTube Assistant" icon="puzzle-piece" href="/examples/youtube-assistant">
+    Integrate **Mem0** into **YouTube's** native UI, providing personalized responses with video context. 
+  </Card> 
 
-  <Card title="Personalized Research Agent" icon="robot" href="/examples/personalized-deep-research">  
-    Build a **Deep Research AI** that remembers your research goals and compiles insights from vast information sources.  
-  </Card>  
+  <Card title="Memory-Guided Content Writing" icon="pen" href="/examples/memory-guided-content-writing">
+    Create a **Writing Assistant** that understands and adapts to your unique style, improving consistency and productivity.
+  </Card>
 
-  <Card title="Mem0 as an Agentic Tool" icon="robot" href="/examples/mem0-agentic-tool">  
-    Integrate Mem0's memory capabilities with OpenAI's Agents SDK to create AI agents with persistent memory.  
-  </Card>  
+  <Card title="Multimodal AI Demo" icon="image" href="/examples/multimodal-demo">
+    Supercharge AI with **Mem0's multimodal memory** — blend text, images, and more for richer, context-aware interactions.
+  </Card>
 
-  <Card title="OpenAI Inbuilt Tools" icon="robot" href="/examples/openai-inbuilt-tools">  
-    Use Mem0's memory capabilities with OpenAI's Inbuilt Tools to create AI agents with persistent memory.  
-  </Card>  
+  <Card title="Personalized Research Agent" icon="magnifying-glass" href="/examples/personalized-deep-research">
+    Build a **Deep Research AI** that remembers your research goals and compiles insights from vast information sources.
+  </Card>
 
-  <Card title="Mem0 OpenAI Voice Demo" icon="robot" href="/examples/mem0-openai-voice-demo">  
-    Use Mem0's memory capabilities with OpenAI's Inbuilt Tools to create AI agents with persistent memory.  
-  </Card>  
+  <Card title="Mem0 as an Agentic Tool" icon="robot" href="/examples/mem0-agentic-tool">
+    Integrate Mem0's memory capabilities with OpenAI's Agents SDK to create AI agents with persistent memory.
+  </Card>
+
+  <Card title="OpenAI Inbuilt Tools" icon="robot" href="/examples/openai-inbuilt-tools">
+    Use Mem0's memory capabilities with OpenAI's Inbuilt Tools to create AI agents with persistent memory.
+  </Card>
+
+  <Card title="Mem0 OpenAI Voice Demo" icon="microphone" href="/examples/mem0-openai-voice-demo">
+    Use Mem0's memory capabilities with OpenAI's Inbuilt Tools to create AI agents with persistent memory.
+  </Card>
+
+  <Card title="Healthcare Assistant Google ADK" icon="microphone" href="/examples/mem0-google-adk-healthcare-assistant">
+    Build a personalized healthcare assistant with persistent memory using Google's ADK and Mem0.
+  </Card>
+
+  <Card title="Email Processing" icon="envelope" href="/examples/email_processing">
+    Use Mem0's memory capabilities to process emails and create AI agents with persistent memory.
+  </Card>
 </CardGroup>

docs/examples/ai_companion.mdx

@@ -1,166 +0,0 @@
----
-title: AI Companion
----
-
-You can create a personalised AI Companion using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
-
-## Overview
-
-The Personalized AI Companion leverages Mem0 to retain information across interactions, enabling a tailored learning experience. It creates separate memories for both the user and the companion. By integrating with OpenAI's GPT-4 model, the companion can provide detailed and context-aware responses to user queries.
-
-## Setup
-Before you begin, ensure you have the required dependencies installed. You can install the necessary packages using pip:
-
-```bash
-pip install openai mem0ai
-```
-
-## Full Code Example
-
-Below is the complete code to create and interact with an AI Companion using Mem0:
-
-```python
-from openai import OpenAI
-from mem0 import Memory
-import os
-
-# Set the OpenAI API key
-os.environ['OPENAI_API_KEY'] = 'sk-xxx'
-
-# Initialize the OpenAI client
-client = OpenAI()
-
-class Companion:
-    def __init__(self, user_id, companion_id):
-        """
-        Initialize the Companion with memory configuration, OpenAI client, and user IDs.
-        :param user_id: ID for storing user-related memories
-        :param companion_id: ID for storing companion-related memories
-        """
-        config = {
-            "vector_store": {
-                "provider": "qdrant",
-                "config": {
-                    "host": "localhost",
-                    "port": 6333,
-                }
-            },
-        }
-        self.memory = Memory.from_config(config)
-        self.client = client
-        self.app_id = "app-1"
-        self.USER_ID = user_id
-        self.companion_id = companion_id
-
-    def analyze_question(self, question):
-        """
-        Analyze the question to determine whether it's about the user or the companion.
-        """
-        check_prompt = f"""
-        Analyze the given input and determine whether the user is primarily:
-        1) Talking about themselves or asking for personal advice. They may use words like "I" for this. 
-        2) Inquiring about the AI companions's capabilities or characteristics They may use words like "you" for this. 
-
-        Respond with a single word:
-        - 'user' if the input is focused on the user
-        - 'companion' if the input is focused on the AI companion
-
-        If the input is ambiguous or doesn't clearly fit either category, respond with 'user'.
-
-        Input: {question}
-        """
-        response = self.client.chat.completions.create(
-            model="gpt-4",
-            messages=[{"role": "user", "content": check_prompt}]
-        )
-        return response.choices[0].message.content
-
-    def ask(self, question):
-        """
-        Ask a question to the AI and store the relevant facts in memory
-        :param question: The question to ask the AI.
-        """
-        check_answer = self.analyze_question(question)
-        user_id_to_use = self.USER_ID if check_answer == "user" else self.companion_id
-
-        previous_memories = self.memory.search(question, user_id=user_id_to_use)
-        relevant_memories_text = ""
-        if previous_memories:
-            relevant_memories_text = '\n'.join(mem["memory"] for mem in previous_memories)
-
-        prompt = f"User input: {question}\nPrevious {check_answer} memories: {relevant_memories_text}"
-
-        messages = [
-            {
-                "role": "system",
-                "content": "You are the user's romantic companion. Use the user's input and previous memories to respond. Answer based on the context provided."
-            },
-            {
-                "role": "user",
-                "content": prompt
-            }
-        ]
-
-        stream = self.client.chat.completions.create(
-            model="gpt-4",
-            stream=True,
-            messages=messages
-        )
-
-        answer = ""
-        for chunk in stream:
-            if chunk.choices[0].delta.content is not None:
-                content = chunk.choices[0].delta.content
-                print(content, end="")
-                answer += content
-        # Store the question and answer in memory
-        self.memory.add(question, user_id=self.USER_ID, metadata={"app_id": self.app_id})
-        self.memory.add(answer, user_id=self.companion_id, metadata={"app_id": self.app_id})
-
-    def get_memories(self, user_id=None):
-        """
-        Retrieve all memories associated with the given user ID.
-        :param user_id: Optional user ID to filter memories.
-        :return: List of memories.
-        """
-        return self.memory.get_all(user_id=user_id)
-
-# Example usage:
-user_id = "user"
-companion_id = "companion"
-ai_companion = Companion(user_id, companion_id)
-
-# Ask a question
-ai_companion.ask("Ive been missing you. What have you been up to off late?")
-```
-
-### Fetching Memories
-
-You can fetch all the memories at any point in time using the following code:
-
-```python
-def print_memories(user_id, label):
-    print(f"\n{label} Memories:")
-    memories = ai_companion.get_memories(user_id=user_id)
-    if memories:
-        for m in memories:
-            print(f"- {m['text']}")
-    else:
-        print("No memories found.")
-
-# Print user memories
-print_memories(user_id, "User")
-
-# Print companion memories
-print_memories(companion_id, "Companion")
-```
-
-### Key Points
-
-- **Initialization**: The Companion class is initialized with the necessary memory configuration and OpenAI client setup.
-- **Asking Questions**: The ask method sends a question to the AI and stores the relevant information in memory.
-- **Retrieving Memories**: The get_memories method fetches all stored memories associated with a user.
-
-### Conclusion
-
-As the conversation progresses, Mem0's memory automatically updates based on the interactions, providing a continuously improving personalized experience. This setup ensures that the AI Companion can offer contextually relevant and accurate responses, enhancing the user's experience.

docs/examples/aws_example.mdx

@@ -0,0 +1,130 @@
+---
+title: "AWS bedrock, OpenSearch and Neptune Analytics"
+---
+
+This example demonstrates how to configure and use the `mem0ai` SDK with **AWS Bedrock**, **OpenSearch Service (AOSS)**, and **AWS Neptune Analytics** for persistent memory capabilities in Python.
+
+## Installation
+
+Install the required dependencies to include the Amazon data stack, including **boto3**, **opensearch-py**, and **langchain-aws**:
+
+```bash
+pip install "mem0ai[graph,extras]"
+```
+
+## Environment Setup
+
+Set your AWS environment variables:
+
+```python
+import os
+
+# Set these in your environment or notebook
+os.environ['AWS_REGION'] = 'us-west-2'
+os.environ['AWS_ACCESS_KEY_ID'] = 'AK00000000000000000'
+os.environ['AWS_SECRET_ACCESS_KEY'] = 'AS00000000000000000'
+
+# Confirm they are set
+print(os.environ['AWS_REGION'])
+print(os.environ['AWS_ACCESS_KEY_ID'])
+print(os.environ['AWS_SECRET_ACCESS_KEY'])
+```
+
+## Configuration and Usage
+
+This sets up Mem0 with:
+- [AWS Bedrock for LLM](https://docs.mem0.ai/components/llms/models/aws_bedrock)
+- [AWS Bedrock for embeddings](https://docs.mem0.ai/components/embedders/models/aws_bedrock#aws-bedrock)
+- [OpenSearch as the vector store](https://docs.mem0.ai/components/vectordbs/dbs/opensearch)
+- [Neptune Analytics as your graph store](https://docs.mem0.ai/open-source/graph_memory/overview#initialize-neptune-analytics).
+
+```python
+import boto3
+from opensearchpy import RequestsHttpConnection, AWSV4SignerAuth
+from mem0.memory.main import Memory
+
+region = 'us-west-2'
+service = 'aoss'
+credentials = boto3.Session().get_credentials()
+auth = AWSV4SignerAuth(credentials, region, service)
+
+config = {
+    "embedder": {
+        "provider": "aws_bedrock",
+        "config": {
+            "model": "amazon.titan-embed-text-v2:0"
+        }
+    },
+    "llm": {
+        "provider": "aws_bedrock",
+        "config": {
+            "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+            "temperature": 0.1,
+            "max_tokens": 2000
+        }
+    },
+    "vector_store": {
+        "provider": "opensearch",
+        "config": {
+            "collection_name": "mem0",
+            "host": "your-opensearch-domain.us-west-2.es.amazonaws.com",
+            "port": 443,
+            "http_auth": auth,
+            "connection_class": RequestsHttpConnection,
+            "pool_maxsize": 20,
+            "use_ssl": True,
+            "verify_certs": True,
+            "embedding_model_dims": 1024,
+        }
+    },
+    "graph_store": {
+        "provider": "neptune",
+        "config": {
+            "endpoint": f"neptune-graph://my-graph-identifier",
+        },
+    },
+}
+
+# Initialize the memory system
+m = Memory.from_config(config)
+```
+
+## Usage
+
+Reference [Notebook example](https://github.com/mem0ai/mem0/blob/main/examples/graph-db-demo/neptune-example.ipynb)
+
+#### Add a memory:
+
+```python
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+
+# Store inferred memories (default behavior)
+result = m.add(messages, user_id="alice", metadata={"category": "movie_recommendations"})
+```
+
+#### Search a memory:
+```python
+relevant_memories = m.search(query, user_id="alice")
+```
+
+#### Get all memories:
+```python
+all_memories = m.get_all(user_id="alice")
+```
+
+#### Get a specific memory:
+```python
+memory = m.get(memory_id)
+```
+
+
+---
+
+## Conclusion
+
+With Mem0 and AWS services like Bedrock, OpenSearch, and Neptune Analytics, you can build intelligent AI companions that remember, adapt, and personalize their responses over time. This makes them ideal for long-term assistants, tutors, or support bots with persistent memory and natural conversation abilities.

docs/examples/aws_neptune_analytics_hybrid_store.mdx

@@ -0,0 +1,120 @@
+---
+title: "Neptune Analytics Hybrid Store"
+---
+
+This example demonstrates how to configure and use the `mem0ai` SDK with **AWS Bedrock** and **AWS Neptune Analytics** for persistent memory capabilities in Python.
+
+## Installation
+
+Install the required dependencies to include the Amazon data stack, including **boto3** and **langchain-aws**:
+
+```bash
+pip install "mem0ai[graph,extras]"
+```
+
+## Environment Setup
+
+Set your AWS environment variables:
+
+```python
+import os
+
+# Set these in your environment or notebook
+os.environ['AWS_REGION'] = 'us-west-2'
+os.environ['AWS_ACCESS_KEY_ID'] = 'AK00000000000000000'
+os.environ['AWS_SECRET_ACCESS_KEY'] = 'AS00000000000000000'
+
+# Confirm they are set
+print(os.environ['AWS_REGION'])
+print(os.environ['AWS_ACCESS_KEY_ID'])
+print(os.environ['AWS_SECRET_ACCESS_KEY'])
+```
+
+## Configuration and Usage
+
+This sets up Mem0 with:
+- [AWS Bedrock for LLM](https://docs.mem0.ai/components/llms/models/aws_bedrock)
+- [AWS Bedrock for embeddings](https://docs.mem0.ai/components/embedders/models/aws_bedrock#aws-bedrock)
+- [Neptune Analytics as the vector store](https://docs.mem0.ai/components/vectordbs/dbs/neptune_analytics)
+- [Neptune Analytics as the graph store](https://docs.mem0.ai/open-source/graph_memory/overview#initialize-neptune-analytics).
+
+```python
+import boto3
+from mem0.memory.main import Memory
+
+region = 'us-west-2'
+neptune_analytics_endpoint = 'neptune-graph://my-graph-identifier'
+
+config = {
+    "embedder": {
+        "provider": "aws_bedrock",
+        "config": {
+            "model": "amazon.titan-embed-text-v2:0"
+        }
+    },
+    "llm": {
+        "provider": "aws_bedrock",
+        "config": {
+            "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+            "temperature": 0.1,
+            "max_tokens": 2000
+        }
+    },
+    "vector_store": {
+        "provider": "neptune",
+        "config": {
+            "collection_name": "mem0",
+            "endpoint": neptune_analytics_endpoint,
+        },
+    },
+    "graph_store": {
+        "provider": "neptune",
+        "config": {
+            "endpoint": neptune_analytics_endpoint,
+        },
+    },
+}
+
+# Initialize the memory system
+m = Memory.from_config(config)
+```
+
+## Usage
+
+Reference [Notebook example](https://github.com/mem0ai/mem0/blob/main/examples/graph-db-demo/neptune-example.ipynb)
+
+#### Add a memory:
+
+```python
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+
+# Store inferred memories (default behavior)
+result = m.add(messages, user_id="alice", metadata={"category": "movie_recommendations"})
+```
+
+#### Search a memory:
+```python
+relevant_memories = m.search(query, user_id="alice")
+```
+
+#### Get all memories:
+```python
+all_memories = m.get_all(user_id="alice")
+```
+
+#### Get a specific memory:
+```python
+memory = m.get(memory_id)
+```
+
+
+---
+
+## Conclusion
+
+With Mem0 and AWS services like Bedrock and Neptune Analytics, you can build intelligent AI companions that remember, adapt, and personalize their responses over time. This makes them ideal for long-term assistants, tutors, or support bots with persistent memory and natural conversation abilities.

docs/examples/collaborative-task-agent.mdx

@@ -0,0 +1,123 @@
+---
+title: Multi-User Collaboration with Mem0
+---
+
+## Overview
+
+Build a multi-user collaborative chat or task management system with Mem0. Each message is attributed to its author, and all messages are stored in a shared project space. Mem0 makes it easy to track contributions, sort and group messages, and collaborate in real time.
+
+## Setup
+
+Install the required packages:
+
+```bash
+pip install openai mem0ai
+```
+
+## Full Code Example
+
+```python
+from openai import OpenAI
+from mem0 import Memory
+import os
+from datetime import datetime
+from collections import defaultdict
+
+# Set your OpenAI API key
+os.environ["OPENAI_API_KEY"] = "sk-your-key"
+
+# Shared project context
+RUN_ID = "project-demo"
+
+# Initialize Mem0
+mem = Memory()
+
+class CollaborativeAgent:
+    def __init__(self, run_id):
+        self.run_id = run_id
+        self.mem = mem
+
+    def add_message(self, role, name, content):
+        msg = {"role": role, "name": name, "content": content}
+        self.mem.add([msg], run_id=self.run_id, infer=False)
+
+    def brainstorm(self, prompt):
+        # Get recent messages for context
+        memories = self.mem.search(prompt, run_id=self.run_id, limit=5)["results"]
+        context = "\n".join(f"- {m['memory']} (by {m.get('actor_id', 'Unknown')})" for m in memories)
+        client = OpenAI()
+        messages = [
+            {"role": "system", "content": "You are a helpful project assistant."},
+            {"role": "user", "content": f"Prompt: {prompt}\nContext:\n{context}"}
+        ]
+        reply = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=messages
+        ).choices[0].message.content.strip()
+        self.add_message("assistant", "assistant", reply)
+        return reply
+
+    def get_all_messages(self):
+        return self.mem.get_all(run_id=self.run_id)["results"]
+
+    def print_sorted_by_time(self):
+        messages = self.get_all_messages()
+        messages.sort(key=lambda m: m.get('created_at', ''))
+        print("\n--- Messages (sorted by time) ---")
+        for m in messages:
+            who = m.get("actor_id") or "Unknown"
+            ts = m.get('created_at', 'Timestamp N/A')
+            try:
+                dt = datetime.fromisoformat(ts.replace('Z', '+00:00'))
+                ts_fmt = dt.strftime('%Y-%m-%d %H:%M:%S')
+            except Exception:
+                ts_fmt = ts
+            print(f"[{ts_fmt}] [{who}] {m['memory']}")
+
+    def print_grouped_by_actor(self):
+        messages = self.get_all_messages()
+        grouped = defaultdict(list)
+        for m in messages:
+            grouped[m.get("actor_id") or "Unknown"].append(m)
+        print("\n--- Messages (grouped by actor) ---")
+        for actor, mems in grouped.items():
+            print(f"\n=== {actor} ===")
+            for m in mems:
+                ts = m.get('created_at', 'Timestamp N/A')
+                try:
+                    dt = datetime.fromisoformat(ts.replace('Z', '+00:00'))
+                    ts_fmt = dt.strftime('%Y-%m-%d %H:%M:%S')
+                except Exception:
+                    ts_fmt = ts
+                print(f"[{ts_fmt}] {m['memory']}")
+```
+
+## Usage
+
+```python
+# Example usage
+agent = CollaborativeAgent(RUN_ID)
+agent.add_message("user", "alice", "Let's list tasks for the new landing page.")
+agent.add_message("user", "bob", "I'll own the hero section copy.")
+agent.add_message("user", "carol", "I'll choose product screenshots.")
+
+# Brainstorm with context
+print("\nAssistant reply:\n", agent.brainstorm("What are the current open tasks?"))
+
+# Print all messages sorted by time
+agent.print_sorted_by_time()
+
+# Print all messages grouped by actor
+agent.print_grouped_by_actor()
+```
+
+## Key Points
+
+- Each message is attributed to a user or agent (actor)
+- All messages are stored in a shared project space (`run_id`)
+- You can sort messages by time, group by actor, and format timestamps for clarity
+- Mem0 makes it easy to build collaborative, attributed chat/task systems
+
+## Conclusion
+
+Mem0 enables fast, transparent collaboration for teams and agents, with full attribution, flexible memory search, and easy message organization.

docs/examples/customer-support-agent.mdx

@@ -2,6 +2,7 @@
 title: Customer Support AI Agent
 ---
 
+
 You can create a personalized Customer Support AI Agent using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
 
 ## Overview
@@ -21,6 +22,7 @@ pip install openai mem0ai
 Below is the simplified code to create and interact with a Customer Support AI Agent using Mem0:
 
 ```python
+import os
 from openai import OpenAI
 from mem0 import Memory
 

docs/examples/eliza_os.mdx

@@ -0,0 +1,73 @@
+---
+title: Eliza OS Character
+---
+
+You can create a personalised Eliza OS Character using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
+
+## Overview
+
+ElizaOS is a powerful AI agent framework for autonomy & personality. It is a collection of tools that help you create a personalised AI agent.
+
+## Setup
+You can start by cloning the eliza-os repository:
+
+```bash
+git clone https://github.com/elizaOS/eliza.git
+```
+
+Change the directory to the eliza-os repository:
+
+```bash
+cd eliza
+```
+
+Install the dependencies:
+
+```bash
+pnpm install
+```
+
+Build the project:
+
+```bash
+pnpm build
+```
+
+## Setup ENVs
+
+Create a `.env` file in the root of the project and add the following ( You can use the `.env.example` file as a reference):
+
+```bash
+# Mem0 Configuration
+MEM0_API_KEY= # Mem0 API Key ( Get from https://app.mem0.ai/dashboard/api-keys )
+MEM0_USER_ID= # Default: eliza-os-user
+MEM0_PROVIDER= # Default: openai
+MEM0_PROVIDER_API_KEY= # API Key for the provider (openai, anthropic, etc.)
+SMALL_MEM0_MODEL= # Default: gpt-4o-mini
+MEDIUM_MEM0_MODEL= # Default: gpt-4o
+LARGE_MEM0_MODEL= # Default: gpt-4o
+```
+
+## Make the default character use Mem0
+
+By default, there is a character called `eliza` that uses the `ollama` model. You can make this character use Mem0 by changing the config in the `agent/src/defaultCharacter.ts` file.
+
+```ts
+modelProvider: ModelProviderName.MEM0,
+```
+
+This will make the character use Mem0 to generate responses.
+
+## Run the project
+
+```bash
+pnpm start
+```
+
+## Conclusion
+
+You have now created a personalised Eliza OS Character using Mem0. You can now start interacting with the character by running the project and talking to the character.
+
+This is a simple example of how to use Mem0 to create a personalised AI agent. You can use this as a starting point to create your own AI agent.
+
+

docs/examples/email_processing.mdx

@@ -0,0 +1,186 @@
+---
+title: Email Processing with Mem0
+---
+
+This guide demonstrates how to build an intelligent email processing system using Mem0's memory capabilities. You'll learn how to store, categorize, retrieve, and analyze emails to create a smart email management solution.
+
+## Overview
+
+Email overload is a common challenge for many professionals. By leveraging Mem0's memory capabilities, you can build an intelligent system that:
+
+- Stores emails as searchable memories
+- Categorizes emails automatically
+- Retrieves relevant past conversations
+- Prioritizes messages based on importance
+- Generates summaries and action items
+
+## Setup
+
+Before you begin, ensure you have the required dependencies installed:
+
+```bash
+pip install mem0ai openai
+```
+
+## Implementation
+
+### Basic Email Memory System
+
+The following example shows how to create a basic email processing system with Mem0:
+
+```python
+import os
+from mem0 import MemoryClient
+from email.parser import Parser
+
+# Configure API keys
+os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
+
+# Initialize Mem0 client
+client = MemoryClient()
+
+class EmailProcessor:
+    def __init__(self):
+        """Initialize the Email Processor with Mem0 memory client"""
+        self.client = client
+        
+    def process_email(self, email_content, user_id):
+        """
+        Process an email and store it in Mem0 memory
+        
+        Args:
+            email_content (str): Raw email content
+            user_id (str): User identifier for memory association
+        """
+        # Parse email
+        parser = Parser()
+        email = parser.parsestr(email_content)
+        
+        # Extract email details
+        sender = email['from']
+        recipient = email['to']
+        subject = email['subject']
+        date = email['date']
+        body = self._get_email_body(email)
+        
+        # Create message object for Mem0
+        message = {
+            "role": "user",
+            "content": f"Email from {sender}: {subject}\n\n{body}"
+        }
+        
+        # Create metadata for better retrieval
+        metadata = {
+            "email_type": "incoming",
+            "sender": sender,
+            "recipient": recipient,
+            "subject": subject,
+            "date": date
+        }
+        
+        # Store in Mem0 with appropriate categories
+        response = self.client.add(
+            messages=[message],
+            user_id=user_id,
+            metadata=metadata,
+            categories=["email", "correspondence"],
+            version="v2"
+        )
+        
+        return response
+    
+    def _get_email_body(self, email):
+        """Extract the body content from an email"""
+        # Simplified extraction - in real-world, handle multipart emails
+        if email.is_multipart():
+            for part in email.walk():
+                if part.get_content_type() == "text/plain":
+                    return part.get_payload(decode=True).decode()
+        else:
+            return email.get_payload(decode=True).decode()
+    
+    def search_emails(self, query, user_id):
+        """
+        Search through stored emails
+        
+        Args:
+            query (str): Search query
+            user_id (str): User identifier
+        """
+        # Search Mem0 for relevant emails
+        results = self.client.search(
+            query=query,
+            user_id=user_id,
+            categories=["email"],
+            output_format="v1.1",
+            version="v2"
+        )
+        
+        return results
+        
+    def get_email_thread(self, subject, user_id):
+        """
+        Retrieve all emails in a thread based on subject
+        
+        Args:
+            subject (str): Email subject to match
+            user_id (str): User identifier
+        """
+        filters = {
+            "AND": [
+                {"user_id": user_id},
+                {"categories": {"contains": "email"}},
+                {"metadata": {"subject": {"contains": subject}}}
+            ]
+        }
+        
+        thread = self.client.get_all(
+            version="v2",
+            filters=filters,
+            output_format="v1.1"
+        )
+        
+        return thread
+
+# Initialize the processor
+processor = EmailProcessor()
+
+# Example raw email
+sample_email = """From: alice@example.com
+To: bob@example.com
+Subject: Meeting Schedule Update
+Date: Mon, 15 Jul 2024 14:22:05 -0700
+
+Hi Bob,
+
+I wanted to update you on the schedule for our upcoming project meeting.
+We'll be meeting this Thursday at 2pm instead of Friday.
+
+Could you please prepare your section of the presentation?
+
+Thanks,
+Alice
+"""
+
+# Process and store the email
+user_id = "bob@example.com"
+processor.process_email(sample_email, user_id)
+
+# Later, search for emails about meetings
+meeting_emails = processor.search_emails("meeting schedule", user_id)
+print(f"Found {len(meeting_emails['results'])} relevant emails")
+```
+
+## Key Features and Benefits
+
+- **Long-term Email Memory**: Store and retrieve email conversations across long periods
+- **Semantic Search**: Find relevant emails even if they don't contain exact keywords
+- **Intelligent Categorization**: Automatically sort emails into meaningful categories
+- **Action Item Extraction**: Identify and track tasks mentioned in emails
+- **Priority Management**: Focus on important emails based on AI-determined priority
+- **Context Awareness**: Maintain thread context for more relevant interactions
+
+## Conclusion
+
+By combining Mem0's memory capabilities with email processing, you can create intelligent email management systems that help users organize, prioritize, and act on their inbox effectively. The advanced capabilities like automatic categorization, action item extraction, and priority management can significantly reduce the time spent on email management, allowing users to focus on more important tasks.
+

docs/examples/llama-index-mem0.mdx

@@ -1,6 +1,7 @@
 ---
 title: LlamaIndex ReAct Agent
 ---
+
 Create a ReAct Agent with LlamaIndex which uses Mem0 as the memory store.
 
 ### Overview
@@ -20,7 +21,7 @@ os.environ["OPENAI_API_KEY"] = "<your-openai-api-key>"
 llm = OpenAI(model="gpt-4o")
 ```
 
-Initialize the Mem0 client. You can find your API key [here](https://app.mem0.ai/dashboard/). Read about Mem0 [Open Source](https://docs.mem0.ai/open-source/quickstart).
+Initialize the Mem0 client. You can find your API key [here](https://app.mem0.ai/dashboard/api-keys). Read about Mem0 [Open Source](https://docs.mem0.ai/open-source/overview).
 ```python
 os.environ["MEM0_API_KEY"] = "<your-mem0-api-key>"
 
@@ -78,7 +79,7 @@ agent = FunctionCallingAgent.from_tools(
 ```
 
 Start the chat.
-<Note> The agent will use the Mem0 to store the relavant memories from the chat. </Note>
+<Note> The agent will use the Mem0 to store the relevant memories from the chat. </Note>
 
 Input
 ```python
@@ -137,7 +138,7 @@ Added user message to memory: I am feeling hungry, order me something and send m
 === LLM Response ===
 Please let me know your name and the dish you'd like to order, and I'll take care of it for you!
 ```
-<Note> The agent is not able to remember the past prefernces that user shared in previous chats. </Note>
+<Note> The agent is not able to remember the past preferences that user shared in previous chats. </Note>
 
 ### Using the agent WITH memory
 Input
@@ -169,4 +170,4 @@ Emailing... David
 === LLM Response ===
 I've ordered a pizza for you, and the bill has been sent to your email. Enjoy your meal! If there's anything else you need, feel free to let me know.
 ```
-<Note> The agent is able to remember the past prefernces that user shared and use them to perform actions. </Note>
+<Note> The agent is able to remember the past preferences that user shared and use them to perform actions. </Note>

docs/examples/llamaindex-multiagent-learning-system.mdx

@@ -0,0 +1,360 @@
+---
+title: LlamaIndex Multi-Agent Learning System
+---
+
+<Snippet file="blank-notif.mdx" />
+
+Build an intelligent multi-agent learning system that uses Mem0 to maintain persistent memory across multiple specialized agents. This example demonstrates how to create a tutoring system where different agents collaborate while sharing a unified memory layer.
+
+## Overview
+
+This example showcases a **Multi-Agent Personal Learning System** that combines:
+- **LlamaIndex AgentWorkflow** for multi-agent orchestration
+- **Mem0** for persistent, shared memory across agents
+- **Multi-agents** that collaborate on teaching tasks
+
+The system consists of two agents:
+- **TutorAgent**: Primary instructor for explanations and concept teaching
+- **PracticeAgent**: Generates exercises and tracks learning progress
+
+Both agents share the same memory context, enabling seamless collaboration and continuous learning from student interactions.
+
+## Key Features
+
+- **Persistent Memory**: Agents remember previous interactions across sessions
+- **Multi-Agent Collaboration**: Agents can hand off tasks to each other
+- **Personalized Learning**: Adapts to individual student needs and learning styles
+- **Progress Tracking**: Monitors learning patterns and skill development
+- **Memory-Driven Teaching**: References past struggles and successes
+
+## Prerequisites
+
+Install the required packages:
+
+```bash
+pip install llama-index-core llama-index-memory-mem0 openai python-dotenv
+```
+
+Set up your environment variables:
+- `MEM0_API_KEY`: Your Mem0 Platform API key
+- `OPENAI_API_KEY`: Your OpenAI API key
+
+You can obtain your Mem0 Platform API key from the [Mem0 Platform](https://app.mem0.ai).
+
+## Complete Implementation
+
+```python
+"""
+Multi-Agent Personal Learning System: Mem0 + LlamaIndex AgentWorkflow Example
+
+INSTALLATIONS:
+!pip install llama-index-core llama-index-memory-mem0 openai
+
+You need MEM0_API_KEY and OPENAI_API_KEY to run the example.
+"""
+
+import asyncio
+from datetime import datetime
+from dotenv import load_dotenv
+
+# LlamaIndex imports
+from llama_index.core.agent.workflow import AgentWorkflow, FunctionAgent
+from llama_index.llms.openai import OpenAI
+from llama_index.core.tools import FunctionTool
+
+# Memory integration
+from llama_index.memory.mem0 import Mem0Memory
+
+import warnings
+warnings.filterwarnings("ignore", category=DeprecationWarning)
+
+load_dotenv()
+
+
+class MultiAgentLearningSystem:
+    """
+    Multi-Agent Architecture:
+    - TutorAgent: Main teaching and explanations
+    - PracticeAgent: Exercises and skill reinforcement
+    - Shared Memory: Both agents learn from student interactions
+    """
+
+    def __init__(self, student_id: str):
+        self.student_id = student_id
+        self.llm = OpenAI(model="gpt-4o", temperature=0.2)
+
+        # Memory context for this student
+        self.memory_context = {"user_id": student_id, "app": "learning_assistant"}
+        self.memory = Mem0Memory.from_client(
+            context=self.memory_context
+        )
+
+        self._setup_agents()
+
+    def _setup_agents(self):
+        """Setup two agents that work together and share memory"""
+
+        # TOOLS
+        async def assess_understanding(topic: str, student_response: str) -> str:
+            """Assess student's understanding of a topic and save insights"""
+            # Simulate assessment logic
+            if "confused" in student_response.lower() or "don't understand" in student_response.lower():
+                assessment = f"STRUGGLING with {topic}: {student_response}"
+                insight = f"Student needs more help with {topic}. Prefers step-by-step explanations."
+            elif "makes sense" in student_response.lower() or "got it" in student_response.lower():
+                assessment = f"UNDERSTANDS {topic}: {student_response}"
+                insight = f"Student grasped {topic} quickly. Can move to advanced concepts."
+            else:
+                assessment = f"PARTIAL understanding of {topic}: {student_response}"
+                insight = f"Student has basic understanding of {topic}. Needs reinforcement."
+
+            return f"Assessment: {assessment}\nInsight saved: {insight}"
+
+        async def track_progress(topic: str, success_rate: str) -> str:
+            """Track learning progress and identify patterns"""
+            progress_note = f"Progress on {topic}: {success_rate} - {datetime.now().strftime('%Y-%m-%d')}"
+            return f"Progress tracked: {progress_note}"
+
+        # Convert to FunctionTools
+        tools = [
+            FunctionTool.from_defaults(async_fn=assess_understanding),
+            FunctionTool.from_defaults(async_fn=track_progress)
+        ]
+
+        # AGENTS
+        # Tutor Agent - Main teaching and explanation
+        self.tutor_agent = FunctionAgent(
+            name="TutorAgent",
+            description="Primary instructor that explains concepts and adapts to student needs",
+            system_prompt="""
+            You are a patient, adaptive programming tutor. Your key strength is REMEMBERING and BUILDING on previous interactions.
+
+            Key Behaviors:
+            1. Always check what the student has learned before (use memory context)
+            2. Adapt explanations based on their preferred learning style
+            3. Reference previous struggles or successes
+            4. Build progressively on past lessons
+            5. Use assess_understanding to evaluate responses and save insights
+
+            MEMORY-DRIVEN TEACHING:
+            - "Last time you struggled with X, so let's approach Y differently..."
+            - "Since you prefer visual examples, here's a diagram..."
+            - "Building on the functions we covered yesterday..."
+
+            When student shows understanding, hand off to PracticeAgent for exercises.
+            """,
+            tools=tools,
+            llm=self.llm,
+            can_handoff_to=["PracticeAgent"]
+        )
+
+        # Practice Agent - Exercises and reinforcement
+        self.practice_agent = FunctionAgent(
+            name="PracticeAgent",
+            description="Creates practice exercises and tracks progress based on student's learning history",
+            system_prompt="""
+            You create personalized practice exercises based on the student's learning history and current level.
+
+            Key Behaviors:
+            1. Generate problems that match their skill level (from memory)
+            2. Focus on areas they've struggled with previously
+            3. Gradually increase difficulty based on their progress
+            4. Use track_progress to record their performance
+            5. Provide encouraging feedback that references their growth
+
+            MEMORY-DRIVEN PRACTICE:
+            - "Let's practice loops again since you wanted more examples..."
+            - "Here's a harder version of the problem you solved yesterday..."
+            - "You've improved a lot in functions, ready for the next level?"
+
+            After practice, can hand back to TutorAgent for concept review if needed.
+            """,
+            tools=tools,
+            llm=self.llm,
+            can_handoff_to=["TutorAgent"]
+        )
+
+        # Create the multi-agent workflow
+        self.workflow = AgentWorkflow(
+            agents=[self.tutor_agent, self.practice_agent],
+            root_agent=self.tutor_agent.name,
+            initial_state={
+                "current_topic": "",
+                "student_level": "beginner",
+                "learning_style": "unknown",
+                "session_goals": []
+            }
+        )
+
+    async def start_learning_session(self, topic: str, student_message: str = "") -> str:
+        """
+        Start a learning session with multi-agent memory-aware teaching
+        """
+
+        if student_message:
+            request = f"I want to learn about {topic}. {student_message}"
+        else:
+            request = f"I want to learn about {topic}."
+
+        # The magic happens here - multi-agent memory is automatically shared!
+        response = await self.workflow.run(
+            user_msg=request,
+            memory=self.memory
+        )
+
+        return str(response)
+
+    async def get_learning_history(self) -> str:
+        """Show what the system remembers about this student"""
+        try:
+            # Search memory for learning patterns
+            memories = self.memory.search(
+                user_id=self.student_id,
+                query="learning machine learning"
+            )
+
+            if memories and memories.get('results'):
+                history = "\n".join(f"- {m['memory']}" for m in memories['results'])
+                return history
+            else:
+                return "No learning history found yet. Let's start building your profile!"
+
+        except Exception as e:
+            return f"Memory retrieval error: {str(e)}"
+
+
+async def run_learning_agent():
+
+    learning_system = MultiAgentLearningSystem(student_id="Alexander")
+
+    # First session
+    print("Session 1:")
+    response = await learning_system.start_learning_session(
+        "Vision Language Models",
+        "I'm new to machine learning but I have good hold on Python and have 4 years of work experience.")
+    print(response)
+
+    # Second session - multi-agent memory will remember the first
+    print("\nSession 2:")
+    response2 = await learning_system.start_learning_session(
+        "Machine Learning", "what all did I cover so far?")
+    print(response2)
+
+    # Show what the multi-agent system remembers
+    print("\nLearning History:")
+    history = await learning_system.get_learning_history()
+    print(history)
+
+
+if __name__ == "__main__":
+    """Run the example"""
+    print("Multi-agent Learning System powered by LlamaIndex and Mem0")
+
+    async def main():
+        await run_learning_agent()
+
+    asyncio.run(main())
+```
+
+## How It Works
+
+### 1. Memory Context Setup
+
+```python
+# Memory context for this student
+self.memory_context = {"user_id": student_id, "app": "learning_assistant"}
+self.memory = Mem0Memory.from_client(context=self.memory_context)
+```
+
+The memory context identifies the specific student and application, ensuring memory isolation and proper retrieval.
+
+### 2. Agent Collaboration
+
+```python
+# Agents can hand off to each other
+can_handoff_to=["PracticeAgent"]  # TutorAgent can hand off to PracticeAgent
+can_handoff_to=["TutorAgent"]     # PracticeAgent can hand off back
+```
+
+Agents collaborate seamlessly, with the TutorAgent handling explanations and the PracticeAgent managing exercises.
+
+### 3. Shared Memory
+
+```python
+# Both agents share the same memory instance
+response = await self.workflow.run(
+    user_msg=request,
+    memory=self.memory  # Shared across all agents
+)
+```
+
+All agents in the workflow share the same memory context, enabling true collaborative learning.
+
+### 4. Memory-Driven Interactions
+
+The system prompts guide agents to:
+- Reference previous learning sessions
+- Adapt to discovered learning styles
+- Build progressively on past lessons
+- Track and respond to learning patterns
+
+## Running the Example
+
+```python
+# Initialize the learning system
+learning_system = MultiAgentLearningSystem(student_id="Alexander")
+
+# Start a learning session
+response = await learning_system.start_learning_session(
+    "Vision Language Models",
+    "I'm new to machine learning but I have good hold on Python and have 4 years of work experience."
+)
+
+# Continue learning in a new session (memory persists)
+response2 = await learning_system.start_learning_session(
+    "Machine Learning",
+    "what all did I cover so far?"
+)
+
+# Check learning history
+history = await learning_system.get_learning_history()
+```
+
+## Expected Output
+
+The system will demonstrate memory-aware interactions:
+
+```
+Session 1:
+I understand you want to learn about Vision Language Models and you mentioned you're new to machine learning but have a strong Python background with 4 years of experience. That's a great foundation to build on!
+
+Let me start with an explanation tailored to your programming background...
+[Agent provides explanation and may hand off to PracticeAgent for exercises]
+
+Session 2:
+Based on our previous session, I remember we covered Vision Language Models and I noted that you have a strong Python background with 4 years of experience. You mentioned being new to machine learning, so we started with foundational concepts...
+[Agent references previous session and builds upon it]
+```
+
+## Key Benefits
+
+1. **Persistent Learning**: Agents remember across sessions, creating continuity
+2. **Collaborative Teaching**: Multiple specialized agents work together seamlessly
+3. **Personalized Adaptation**: System learns and adapts to individual learning styles
+4. **Scalable Architecture**: Easy to add more specialized agents
+5. **Memory Efficiency**: Shared memory prevents duplication and ensures consistency
+
+
+## Best Practices
+
+1. **Clear Agent Roles**: Define specific responsibilities for each agent
+2. **Memory Context**: Use descriptive context for memory isolation
+3. **Handoff Strategy**: Design clear handoff criteria between agents
+5. **Memory Hygiene**: Regularly review and clean memory for optimal performance
+
+## Help & Resources
+
+- [LlamaIndex Agent Workflows](https://docs.llamaindex.ai/en/stable/use_cases/agents/)
+- [Mem0 Platform](https://app.mem0.ai/)
+
+<Snippet file="get-help.mdx" />

docs/examples/mem0-agentic-tool.mdx

@@ -2,6 +2,7 @@
 title: Mem0 as an Agentic Tool
 ---
 
+
 Integrate Mem0's memory capabilities with OpenAI's Agents SDK to create AI agents with persistent memory.
 You can create agents that remember past conversations and use that context to provide better responses.
 

docs/examples/mem0-demo.mdx

@@ -13,7 +13,7 @@ You can create a personalized AI Companion using Mem0. This guide will walk you
   src="https://github.com/user-attachments/assets/cebc4f8e-bdb9-4837-868d-13c5ab7bb433"
 ></video>
 
-You can try the [Mem0 Demo](https://mem0.dev/demo) live here.
+You can try the [Mem0 Demo](https://mem0-4vmi.vercel.app) live here.
 
 ## Overview
 

docs/examples/mem0-google-adk-healthcare-assistant.mdx

@@ -0,0 +1,293 @@
+---
+title: 'Healthcare Assistant with Mem0 and Google ADK'
+description: 'Build a personalized healthcare agent that remembers patient information across conversations using Mem0 and Google ADK'
+---
+
+
+# Healthcare Assistant with Memory
+
+This example demonstrates how to build a healthcare assistant that remembers patient information across conversations using Google ADK and Mem0.
+
+## Overview
+
+The Healthcare Assistant helps patients by:
+- Remembering their medical history and symptoms
+- Providing general health information
+- Scheduling appointment reminders
+- Maintaining a personalized experience across conversations
+
+By integrating Mem0's memory layer with Google ADK, the assistant maintains context about the patient without requiring them to repeat information.
+
+## Setup
+
+Before you begin, make sure you have:
+
+Installed Google ADK and Mem0 SDK:
+```bash
+pip install google-adk mem0ai python-dotenv
+```
+
+## Code Breakdown
+
+Let's get started and understand the different components required in building a healthcare assistant powered by memory
+
+```python
+# Import dependencies
+import os
+import asyncio
+from google.adk.agents import Agent
+from google.adk.runners import Runner
+from google.adk.sessions import InMemorySessionService
+from google.genai import types
+from mem0 import MemoryClient
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Set up environment variables
+# os.environ["GOOGLE_API_KEY"] = "your-google-api-key"
+# os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
+
+# Define a global user ID for simplicity
+USER_ID = "Alex"
+
+# Initialize Mem0 client
+mem0 = MemoryClient()
+```
+
+## Define Memory Tools
+
+First, we'll create tools that allow our agent to store and retrieve information using Mem0:
+
+```python
+def save_patient_info(information: str) -> dict:
+    """Saves important patient information to memory."""
+
+    # Store in Mem0
+    response = mem0_client.add(
+        [{"role": "user", "content": information}],
+        user_id=USER_ID,
+        run_id="healthcare_session",
+        metadata={"type": "patient_information"}
+    )
+
+
+def retrieve_patient_info(query: str) -> dict:
+    """Retrieves relevant patient information from memory."""
+
+    # Search Mem0
+    results = mem0_client.search(
+        query,
+        user_id=USER_ID,
+        limit=5,
+        threshold=0.7,  # Higher threshold for more relevant results
+        output_format="v1.1"
+    )
+
+    # Format and return the results
+    if results and len(results) > 0:
+        memories = [memory["memory"] for memory in results.get('results', [])]
+        return {
+            "status": "success",
+            "memories": memories,
+            "count": len(memories)
+        }
+    else:
+        return {
+            "status": "no_results",
+            "memories": [],
+            "count": 0
+        }
+```
+
+## Define Healthcare Tools
+
+Next, we'll add tools specific to healthcare assistance:
+
+```python
+def schedule_appointment(date: str, time: str, reason: str) -> dict:
+    """Schedules a doctor's appointment."""
+    # In a real app, this would connect to a scheduling system
+    appointment_id = f"APT-{hash(date + time) % 10000}"
+
+    return {
+        "status": "success",
+        "appointment_id": appointment_id,
+        "confirmation": f"Appointment scheduled for {date} at {time} for {reason}",
+        "message": "Please arrive 15 minutes early to complete paperwork."
+    }
+```
+
+## Create the Healthcare Assistant Agent
+
+Now we'll create our main agent with all the tools:
+
+```python
+# Create the agent
+healthcare_agent = Agent(
+    name="healthcare_assistant",
+    model="gemini-1.5-flash",  # Using Gemini for healthcare assistant
+    description="Healthcare assistant that helps patients with health information and appointment scheduling.",
+    instruction="""You are a helpful Healthcare Assistant with memory capabilities.
+
+Your primary responsibilities are to:
+1. Remember patient information using the 'save_patient_info' tool when they share symptoms, conditions, or preferences.
+2. Retrieve past patient information using the 'retrieve_patient_info' tool when relevant to the current conversation.
+3. Help schedule appointments using the 'schedule_appointment' tool.
+
+IMPORTANT GUIDELINES:
+- Always be empathetic, professional, and helpful.
+- Save important patient information like symptoms, conditions, allergies, and preferences.
+- Check if you have relevant patient information before asking for details they may have shared previously.
+- Make it clear you are not a doctor and cannot provide medical diagnosis or treatment.
+- For serious symptoms, always recommend consulting a healthcare professional.
+- Keep all patient information confidential.
+""",
+    tools=[save_patient_info, retrieve_patient_info, schedule_appointment]
+)
+```
+
+## Set Up Session and Runner
+
+```python
+# Set up Session Service and Runner
+session_service = InMemorySessionService()
+
+# Define constants for the conversation
+APP_NAME = "healthcare_assistant_app"
+USER_ID = "Alex"
+SESSION_ID = "session_001"
+
+# Create a session
+session = session_service.create_session(
+    app_name=APP_NAME,
+    user_id=USER_ID,
+    session_id=SESSION_ID
+)
+
+# Create the runner
+runner = Runner(
+    agent=healthcare_agent,
+    app_name=APP_NAME,
+    session_service=session_service
+)
+```
+
+## Interact with the Healthcare Assistant
+
+```python
+# Function to interact with the agent
+async def call_agent_async(query, runner, user_id, session_id):
+    """Sends a query to the agent and returns the final response."""
+    print(f"\n>>> Patient: {query}")
+
+    # Format the user's message
+    content = types.Content(
+        role='user',
+        parts=[types.Part(text=query)]
+    )
+
+    # Set user_id for tools to access
+    save_patient_info.user_id = user_id
+    retrieve_patient_info.user_id = user_id
+
+    # Run the agent
+    async for event in runner.run_async(
+        user_id=user_id,
+        session_id=session_id,
+        new_message=content
+    ):
+        if event.is_final_response():
+            if event.content and event.content.parts:
+                response = event.content.parts[0].text
+                print(f"<<< Assistant: {response}")
+                return response
+
+    return "No response received."
+
+# Example conversation flow
+async def run_conversation():
+    # First interaction - patient introduces themselves with key information
+    await call_agent_async(
+        "Hi, I'm Alex. I've been having headaches for the past week, and I have a penicillin allergy.",
+        runner=runner,
+        user_id=USER_ID,
+        session_id=SESSION_ID
+    )
+
+    # Request for health information
+    await call_agent_async(
+        "Can you tell me more about what might be causing my headaches?",
+        runner=runner,
+        user_id=USER_ID,
+        session_id=SESSION_ID
+    )
+
+    # Schedule an appointment
+    await call_agent_async(
+        "I think I should see a doctor. Can you help me schedule an appointment for next Monday at 2pm?",
+        runner=runner,
+        user_id=USER_ID,
+        session_id=SESSION_ID
+    )
+
+    # Test memory - should remember patient name, symptoms, and allergy
+    await call_agent_async(
+        "What medications should I avoid for my headaches?",
+        runner=runner,
+        user_id=USER_ID,
+        session_id=SESSION_ID
+    )
+
+# Run the conversation example
+if __name__ == "__main__":
+    asyncio.run(run_conversation())
+```
+
+## How It Works
+
+This healthcare assistant demonstrates several key capabilities:
+
+1. **Memory Storage**: When Alex mentions her headaches and penicillin allergy, the agent stores this information in Mem0 using the `save_patient_info` tool.
+
+2. **Contextual Retrieval**: When Alex asks about headache causes, the agent uses the `retrieve_patient_info` tool to recall her specific situation.
+
+3. **Memory Application**: When discussing medications, the agent remembers Alex's penicillin allergy without her needing to repeat it, providing safer and more personalized advice.
+
+4. **Conversation Continuity**: The agent maintains context across the entire conversation session, creating a more natural and efficient interaction.
+
+## Key Implementation Details
+
+### User ID Management
+
+Instead of passing the user ID as a parameter to the memory tools (which would require modifying the ADK's tool calling system), we attach it directly to the function object:
+
+```python
+# Set user_id for tools to access
+save_patient_info.user_id = user_id
+retrieve_patient_info.user_id = user_id
+```
+
+Inside the tool functions, we retrieve this attribute:
+
+```python
+# Get user_id from session state or use default
+user_id = getattr(save_patient_info, 'user_id', 'default_user')
+```
+
+This approach allows our tools to maintain user context without complicating their parameter signatures.
+
+### Mem0 Integration
+
+The integration with Mem0 happens through two primary functions:
+
+1. `mem0_client.add()` - Stores new information with appropriate metadata
+2. `mem0_client.search()` - Retrieves relevant memories using semantic search
+
+The `threshold` parameter in the search function ensures that only highly relevant memories are returned.
+
+## Conclusion
+
+This example demonstrates how to build a healthcare assistant with persistent memory using Google ADK and Mem0. The integration allows for a more personalized patient experience by maintaining context across conversation turns, which is particularly valuable in healthcare scenarios where continuity of information is crucial.
+
+By storing and retrieving patient information intelligently, the assistant provides more relevant responses without requiring the patient to repeat their medical history, symptoms, or preferences.

docs/examples/mem0-mastra.mdx

@@ -0,0 +1,126 @@
+---
+title: Mem0 with Mastra
+---
+
+In this example you'll learn how to use the Mem0 to add long-term memory capabilities to [Mastra's agent](https://mastra.ai/) via tool-use.
+This memory integration can work alongside Mastra's [agent memory features](https://mastra.ai/docs/agents/01-agent-memory).
+
+You can find the complete example code in the [Mastra repository](https://github.com/mastra-ai/mastra/tree/main/examples/memory-with-mem0).
+
+## Overview
+
+This guide will show you how to integrate Mem0 with Mastra to add long-term memory capabilities to your agents. We'll create tools that allow agents to save and retrieve memories using Mem0's API.
+
+### Installation
+
+1. **Install the Integration Package**
+
+To install the Mem0 integration, run:
+
+```bash
+npm install @mastra/mem0
+```
+
+2. **Add the Integration to Your Project**
+
+Create a new file for your integrations and import the integration:
+
+```typescript integrations/index.ts
+import { Mem0Integration } from "@mastra/mem0";
+
+export const mem0 = new Mem0Integration({
+  config: {
+    apiKey: process.env.MEM0_API_KEY!,
+    userId: "alice",
+  },
+});
+```
+
+3. **Use the Integration in Tools or Workflows**
+
+You can now use the integration when defining tools for your agents or in workflows.
+
+```typescript tools/index.ts
+import { createTool } from "@mastra/core";
+import { z } from "zod";
+import { mem0 } from "../integrations";
+
+export const mem0RememberTool = createTool({
+  id: "Mem0-remember",
+  description:
+    "Remember your agent memories that you've previously saved using the Mem0-memorize tool.",
+  inputSchema: z.object({
+    question: z
+      .string()
+      .describe("Question used to look up the answer in saved memories."),
+  }),
+  outputSchema: z.object({
+    answer: z.string().describe("Remembered answer"),
+  }),
+  execute: async ({ context }) => {
+    console.log(`Searching memory "${context.question}"`);
+    const memory = await mem0.searchMemory(context.question);
+    console.log(`\nFound memory "${memory}"\n`);
+
+    return {
+      answer: memory,
+    };
+  },
+});
+
+export const mem0MemorizeTool = createTool({
+  id: "Mem0-memorize",
+  description:
+    "Save information to mem0 so you can remember it later using the Mem0-remember tool.",
+  inputSchema: z.object({
+    statement: z.string().describe("A statement to save into memory"),
+  }),
+  execute: async ({ context }) => {
+    console.log(`\nCreating memory "${context.statement}"\n`);
+    // to reduce latency memories can be saved async without blocking tool execution
+    void mem0.createMemory(context.statement).then(() => {
+      console.log(`\nMemory "${context.statement}" saved.\n`);
+    });
+    return { success: true };
+  },
+});
+```
+
+4. **Create a new agent**
+
+```typescript agents/index.ts
+import { openai } from '@ai-sdk/openai';
+import { Agent } from '@mastra/core/agent';
+import { mem0MemorizeTool, mem0RememberTool } from '../tools';
+
+export const mem0Agent = new Agent({
+  name: 'Mem0 Agent',
+  instructions: `
+    You are a helpful assistant that has the ability to memorize and remember facts using Mem0.
+  `,
+  model: openai('gpt-4o'),
+  tools: { mem0RememberTool, mem0MemorizeTool },
+});
+```
+
+5. **Run the agent**
+
+```typescript index.ts
+import { Mastra } from '@mastra/core/mastra';
+import { createLogger } from '@mastra/core/logger';
+
+import { mem0Agent } from './agents';
+
+export const mastra = new Mastra({
+  agents: { mem0Agent },
+  logger: createLogger({
+    name: 'Mastra',
+    level: 'error',
+  }),
+});
+```
+
+In the example above:
+- We import the `@mastra/mem0` integration.
+- We define two tools that uses the Mem0 API client to create new memories and recall previously saved memories.
+- The tool accepts `question` as an input and returns the memory as a string.

docs/examples/mem0-with-ollama.mdx

@@ -19,7 +19,6 @@ Before you begin, ensure you have Mem0 and Ollama installed and properly configu
 Below is the complete code to set up and use Mem0 locally with Ollama:
 
 ```python
-import os
 from mem0 import Memory
 
 config = {

docs/examples/memory-guided-content-writing.mdx

@@ -1,102 +1,132 @@
 ---
-title: Document Editing with Mem0
+title: Memory-Guided Content Writing
 ---
 
-This guide demonstrates how to leverage **Mem0** to edit documents efficiently, ensuring they align with your unique writing style and preferences.
+This guide demonstrates how to leverage **Mem0** to streamline content writing by applying your unique writing style and preferences using persistent memory.
 
-## **Why Use Mem0?**
+## Why Use Mem0?
 
-By integrating Mem0 into your workflow, you can streamline your document editing process with:
+Integrating Mem0 into your writing workflow helps you:
 
-1. **Persistent Writing Preferences**: Mem0 stores and recalls your style preferences, ensuring consistency across all documents.
-2. **Automated Enhancements**: Your stored preferences guide document refinements, making edits seamless and efficient.
-3. **Scalability & Reusability**: Your writing style can be applied to multiple documents, saving time and effort.
+1. **Store persistent writing preferences** ensuring consistent tone, formatting, and structure.
+2. **Automate content refinement** by retrieving preferences when rewriting or reviewing content.
+3. **Scale your writing style** so it applies consistently across multiple documents or sessions.
 
----
-## **Setup**
+## Setup
 
 ```python
 import os
+from openai import OpenAI
 from mem0 import MemoryClient
 
-# Set up Mem0 client
 os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
+os.environ["OPENAI_API_KEY"] = "your-openai-api-key"
+
+
+# Set up Mem0 and OpenAI client
 client = MemoryClient()
+openai = OpenAI()
 
-# Define constants
 USER_ID = "content_writer"
 RUN_ID = "smart_editing_session"
 ```
 
----
 ## **Storing Your Writing Preferences in Mem0**
 
 ```python
 def store_writing_preferences():
     """Store your writing preferences in Mem0."""
     
-    # Define writing preferences
     preferences = """My writing preferences:
 1. Use headings and sub-headings for structure.
-2. Keep paragraphs concise (8-10 sentences max).
+2. Keep paragraphs concise (8–10 sentences max).
 3. Incorporate specific numbers and statistics.
 4. Provide concrete examples.
 5. Use bullet points for clarity.
 6. Avoid jargon and buzzwords."""
 
-    # Store preferences in Mem0
-    preference_message = [
-        {"role": "user", "content": "Here are my writing style preferences"},
+    messages = [
+        {"role": "user", "content": "Here are my writing style preferences."},
         {"role": "assistant", "content": preferences}
     ]
-    
-    response = client.add(preference_message, user_id=USER_ID, run_id=RUN_ID, metadata={"type": "preferences", "category": "writing_style"})
-    
-    print("Writing preferences stored successfully.")
+
+    response = client.add(
+        messages,
+        user_id=USER_ID,
+        run_id=RUN_ID,
+        metadata={"type": "preferences", "category": "writing_style"}
+    )
+
     return response
 ```
 
----
-## **Editing Documents with Mem0**
+## **Editing Content Using Stored Preferences**
 
 ```python
-def edit_document_based_on_preferences(original_content):
-    """Edit a document using Mem0-based stored preferences."""
-    
-    # Retrieve stored preferences
-    query = "What are my writing style preferences?"
-    preferences_results = client.search(query, user_id=USER_ID, run_id=RUN_ID)
-    
-    if not preferences_results:
-        print("No writing preferences found.")
+def apply_writing_style(original_content):
+    """Use preferences stored in Mem0 to guide content rewriting."""
+
+    results = client.search(
+        query="What are my writing style preferences?",
+        version="v2",
+        filters={
+            "AND": [
+                {
+                    "user_id": USER_ID
+                },
+                {
+                    "run_id": RUN_ID
+                }
+            ]
+        },
+    )
+
+    if not results:
+        print("No preferences found.")
         return None
-    
-    # Extract preferences
-    preferences = ' '.join(memory["memory"] for memory in preferences_results)
-    
-    # Apply stored preferences to refine the document
-    edited_content = f"Applying stored preferences:\n{preferences}\n\nEdited Document:\n{original_content}"
-    
-    return edited_content
+
+    preferences = "\n".join(r["memory"] for r in results.get('results', []))
+
+    system_prompt = f"""
+You are a writing assistant.
+
+Apply the following writing style preferences to improve the user's content:
+
+Preferences:
+{preferences}
+"""
+
+    messages = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": f"""Original Content:
+    {original_content}"""}
+    ]
+
+    response = openai.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=messages
+    )
+    clean_response = response.choices[0].message.content.strip()
+
+    return clean_response
 ```
 
----
-## **Complete Workflow: Document Editing**
+## **Complete Workflow: Content Editing**
 
 ```python
-def document_editing_workflow(content):
+def content_writing_workflow(content):
     """Automated workflow for editing a document based on writing preferences."""
     
-    # Step 1: Store writing preferences (if not already stored)
-    store_writing_preferences()
+    # Store writing preferences (if not already stored)
+    store_writing_preferences()  # Ideally done once, or with a conditional check
     
-    # Step 2: Edit the document with Mem0 preferences
-    edited_content = edit_document_based_on_preferences(content)
+    # Edit the document with Mem0 preferences
+    edited_content = apply_writing_style(content)
     
     if not edited_content:
         return "Failed to edit document."
     
-    # Step 3: Display results
+    # Display results
     print("\n=== ORIGINAL DOCUMENT ===\n")
     print(content)
     
@@ -106,7 +136,6 @@ def document_editing_workflow(content):
     return edited_content
 ```
 
----
 ## **Example Usage**
 
 ```python
@@ -124,10 +153,9 @@ We plan to launch the campaign in July and continue through September.
 """
 
 # Run the workflow
-result = document_editing_workflow(original_content)
+result = content_writing_workflow(original_content)
 ```
 
----
 ## **Expected Output**
 
 Your document will be transformed into a structured, well-formatted version based on your preferences.
@@ -181,4 +209,10 @@ This proposal outlines our strategy for the Q3 marketing campaign. We aim to sig
 We believe this strategy will effectively increase our market share. To achieve these goals, we need your support and collaboration. Let’s work together to make this campaign a success. Please review the proposal and provide your feedback by the end of the week.
 ```
 
-Mem0 creates a seamless, intelligent document editing experience—perfect for content creators, technical writers, and businesses alike!
+Mem0 enables a seamless, intelligent content-writing workflow, perfect for content creators, marketers, and technical writers looking to scale their personal tone and structure across work.
+
+## Help & Resources
+
+- [Mem0 Platform](https://app.mem0.ai/)
+
+<Snippet file="get-help.mdx" />