fix: address PR review feedback

1. get_all(): use LIMIT in Cypher query instead of Python slicing
2. _delete_entities/_add_entities: single commit after loop with
   rollback on failure to prevent partial commits
3. _merge_node(): combine agent_id/run_id into single SET query
   (was up to 3 round-trips, now always 1)
4. Add close() method for connection cleanup
5. Extract _get_similar_nodes() helper to deduplicate similarity logic

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.github/workflows/ci.yml

@@ -7,6 +7,8 @@ on:
       - 'mem0/**'
       - 'tests/**'
       - 'embedchain/**'
+      - '.github/workflows/**'
+      - 'pyproject.toml'
   pull_request:
     paths:
       - 'mem0/**'
@@ -28,6 +30,8 @@ jobs:
           mem0:
             - 'mem0/**'
             - 'tests/**'
+            - '.github/workflows/**'
+            - 'pyproject.toml'
           embedchain:
             - 'embedchain/**'
 
@@ -37,13 +41,20 @@ 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: Clean up disk space
+        run: |
+          df -h
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
+          sudo docker image prune --all --force
+          sudo docker builder prune -a
+          df -h
       - name: Install Hatch
         run: pip install hatch
       - name: Load cached venv
@@ -71,7 +82,7 @@ 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 }}

.github/workflows/openclaw-checks.yml

@@ -0,0 +1,100 @@
+name: openclaw checks
+
+on:
+  workflow_dispatch:
+  push:
+    branches: [main]
+    paths:
+      - 'openclaw/**'
+      - '.github/workflows/openclaw-checks.yml'
+  pull_request:
+    paths:
+      - 'openclaw/**'
+      - '.github/workflows/openclaw-checks.yml'
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: 'pnpm'
+          cache-dependency-path: openclaw/pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: cd openclaw && pnpm install --frozen-lockfile
+
+      - name: Type check
+        run: cd openclaw && pnpm exec tsc --noEmit
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        node-version: [20, 22]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Setup Node.js ${{ matrix.node-version }}
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          cache: 'pnpm'
+          cache-dependency-path: openclaw/pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: cd openclaw && pnpm install --frozen-lockfile
+
+      - name: Run tests with coverage
+        run: cd openclaw && pnpm exec vitest run --coverage
+
+      - name: Upload coverage to Codecov
+        if: matrix.node-version == 20
+        uses: codecov/codecov-action@v4
+        with:
+          flags: openclaw
+          directory: openclaw/coverage
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: 'pnpm'
+          cache-dependency-path: openclaw/pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: cd openclaw && pnpm install --frozen-lockfile
+
+      - name: Build
+        run: cd openclaw && pnpm build
+
+      - name: Verify dist output exists
+        run: |
+          test -f openclaw/dist/index.js || (echo "Build output missing: dist/index.js" && exit 1)
+          test -f openclaw/dist/index.d.ts || (echo "Build output missing: dist/index.d.ts" && exit 1)

.github/workflows/ts-sdk-ci.yml

@@ -0,0 +1,110 @@
+name: TypeScript SDK CI
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'mem0-ts/**'
+      - '.github/workflows/ts-sdk-ci.yml'
+  pull_request:
+    paths:
+      - 'mem0-ts/**'
+
+jobs:
+  check_changes:
+    runs-on: ubuntu-latest
+    outputs:
+      ts_sdk_changed: ${{ steps.filter.outputs.ts_sdk }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dorny/paths-filter@v2
+        id: filter
+        with:
+          filters: |
+            ts_sdk:
+              - 'mem0-ts/**'
+
+  build_ts_sdk:
+    needs: check_changes
+    if: needs.check_changes.outputs.ts_sdk_changed == 'true'
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        node-version: [20, 22]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v4
+        with:
+          version: 10
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          cache: 'pnpm'
+          cache-dependency-path: mem0-ts/pnpm-lock.yaml
+
+      - name: Install dependencies
+        working-directory: mem0-ts
+        run: pnpm install --frozen-lockfile
+
+      - name: Lint
+        working-directory: mem0-ts
+        run: npx prettier --check .
+
+      - name: Build
+        working-directory: mem0-ts
+        run: pnpm run build
+
+      - name: Run unit tests
+        working-directory: mem0-ts
+        run: pnpm run test:unit
+
+      - name: Verify package exports
+        working-directory: mem0-ts
+        run: |
+          node -e "const m = require('./dist/index.js'); console.log('Client exports:', Object.keys(m).length)"
+          node -e "const m = require('./dist/oss/index.js'); console.log('OSS exports:', Object.keys(m).length)"
+
+      - name: Upload coverage
+        if: matrix.node-version == 20
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-report
+          path: mem0-ts/coverage/
+
+  integration_ts_sdk:
+    needs: build_ts_sdk
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 1
+      matrix:
+        node-version: [20, 22]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v4
+        with:
+          version: 10
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          cache: 'pnpm'
+          cache-dependency-path: mem0-ts/pnpm-lock.yaml
+
+      - name: Install dependencies
+        working-directory: mem0-ts
+        run: pnpm install --frozen-lockfile
+
+      - name: Build
+        working-directory: mem0-ts
+        run: pnpm run build
+
+      - name: Run integration tests (with cleanup)
+        working-directory: mem0-ts
+        env:
+          MEM0_API_KEY: ${{ secrets.MEM0_API_KEY }}
+        run: pnpm run test:integration

CONTRIBUTING.md

@@ -25,6 +25,7 @@ We use `hatch` for managing development environments. To set up:
 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
 
 # The environment will automatically install all dev dependencies
 # Run tests within the activated shell:
@@ -51,6 +52,7 @@ make test
 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

LLM.md

@@ -86,7 +86,6 @@ const memory = new Memory({
 const result = await memory.add('My name is John', { userId: 'john' });
 ```
 
-
 ## Core API Reference
 
 ### Memory Class (Self-Hosted)
@@ -104,7 +103,7 @@ memory = Memory()
 # With custom configuration
 config = MemoryConfig(
     vector_store={"provider": "qdrant", "config": {"host": "localhost"}},
-    llm={"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+    llm={"provider": "openai", "config": {"model": "gpt-4.1-nano-2025-04-14"}},
     embedder={"provider": "openai", "config": {"model": "text-embedding-3-small"}}
 )
 memory = Memory(config)
@@ -305,7 +304,7 @@ config = MemoryConfig(
 - **langchain** - LangChain embeddings
 - **aws_bedrock** - AWS Bedrock embeddings
 
-#### Vector Store Providers (17 supported)
+#### Vector Store Providers (19 supported)
 - **qdrant** - Qdrant vector database (default)
 - **chroma** - ChromaDB
 - **pinecone** - Pinecone vector database
@@ -323,11 +322,14 @@ config = MemoryConfig(
 - **supabase** - Supabase vector
 - **baidu** - Baidu vector database
 - **langchain** - LangChain vector stores
+- **s3_vectors** - Amazon S3 Vectors
+- **databricks** - Databricks vector stores
 
-#### Graph Store Providers (3 supported)
+#### Graph Store Providers (4 supported)
 - **neo4j** - Neo4j graph database
 - **memgraph** - Memgraph
 - **neptune** - AWS Neptune Analytics
+- **kuzu** - Kuzu Graph database
 
 ### Configuration Examples
 
@@ -337,7 +339,7 @@ config = MemoryConfig(
     llm={
         "provider": "openai",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.1,
             "max_tokens": 1000
         }
@@ -415,6 +417,54 @@ config = MemoryConfig(
 )
 ```
 
+#### LLM Providers
+- **OpenAI** - GPT-4, GPT-3.5-turbo, and structured outputs
+- **Anthropic** - Claude models with advanced reasoning
+- **Google AI** - Gemini models for multimodal applications
+- **AWS Bedrock** - Enterprise-grade AWS managed models
+- **Azure OpenAI** - Microsoft Azure hosted OpenAI models
+- **Groq** - High-performance LPU optimized models
+- **Together** - Open-source model inference platform
+- **Ollama** - Local model deployment for privacy
+- **vLLM** - High-performance inference framework
+- **LM Studio** - Local model management
+- **DeepSeek** - Advanced reasoning models
+- **Sarvam** - Indian language models
+- **XAI** - xAI models
+- **LiteLLM** - Unified LLM interface
+- **LangChain** - LangChain LLM integration
+
+#### Vector Store Providers
+- **Chroma** - AI-native open-source vector database
+- **Qdrant** - High-performance vector similarity search
+- **Pinecone** - Managed vector database with serverless options
+- **Weaviate** - Open-source vector search engine
+- **PGVector** - PostgreSQL extension for vector search
+- **Milvus** - Open-source vector database for scale
+- **Redis** - Real-time vector storage with Redis Stack
+- **Supabase** - Open-source Firebase alternative
+- **Upstash Vector** - Serverless vector database
+- **Elasticsearch** - Distributed search and analytics
+- **OpenSearch** - Open-source search and analytics
+- **FAISS** - Facebook AI Similarity Search
+- **MongoDB** - Document database with vector search
+- **Azure AI Search** - Microsoft's search service
+- **Vertex AI Vector Search** - Google Cloud vector search
+- **Databricks Vector Search** - Delta Lake integration
+- **Baidu** - Baidu vector database
+- **LangChain** - LangChain vector store integration
+
+#### Embedding Providers
+- **OpenAI** - High-quality text embeddings
+- **Azure OpenAI** - Enterprise Azure-hosted embeddings
+- **Google AI** - Gemini embedding models
+- **AWS Bedrock** - Amazon embedding models
+- **Hugging Face** - Open-source embedding models
+- **Vertex AI** - Google Cloud enterprise embeddings
+- **Ollama** - Local embedding models
+- **Together** - Open-source model embeddings
+- **LM Studio** - Local model embeddings
+- **LangChain** - LangChain embedder integration
 
 ## TypeScript/JavaScript SDK
 
@@ -477,7 +527,7 @@ const memory = new Memory({
   },
   llm: {
     provider: 'openai',
-    config: { model: 'gpt-4o-mini' }
+    config: { model: 'gpt-4.1-nano' }
   }
 });
 
@@ -569,6 +619,7 @@ print(result["relations"])   # Graph relationships
 - **Neo4j**: Full-featured graph database with Cypher queries
 - **Memgraph**: High-performance in-memory graph database
 - **Neptune**: AWS managed graph database service
+- **kuzu** - OSS Kuzu Graph database
 
 ### Multimodal Memory
 

MIGRATION_GUIDE_v1.0.md

@@ -0,0 +1,221 @@
+# Migration Guide: Upgrading to mem0 1.0.0
+
+## TL;DR
+
+**What changed?** We simplified the API by removing confusing version parameters. Now everything returns a consistent format: `{"results": [...]}`.
+
+**What you need to do:**
+1. Upgrade: `pip install mem0ai==1.0.0`
+2. Remove `version` and `output_format` parameters from your code
+3. Update response handling to use `result["results"]` instead of treating responses as lists
+
+**Time needed:** ~5-10 minutes for most projects
+
+---
+
+## Quick Migration Guide
+
+### 1. Install the Update
+
+```bash
+pip install mem0ai==1.0.0
+```
+
+### 2. Update Your Code
+
+**If you're using the Memory API:**
+
+```python
+# Before
+memory = Memory(config=MemoryConfig(version="v1.1"))
+result = memory.add("I like pizza")
+
+# After
+memory = Memory()  # That's it - version is automatic now
+result = memory.add("I like pizza")
+```
+
+**If you're using the Client API:**
+
+```python
+# Before
+client.add(messages, output_format="v1.1")
+client.search(query, version="v2", output_format="v1.1")
+
+# After
+client.add(messages)  # Just remove those extra parameters
+client.search(query)
+```
+
+### 3. Update How You Handle Responses
+
+All responses now use the same format: a dictionary with `"results"` key.
+
+```python
+# Before - you might have done this
+result = memory.add("I like pizza")
+for item in result:  # Treating it as a list
+    print(item)
+
+# After - do this instead
+result = memory.add("I like pizza")
+for item in result["results"]:  # Access the results key
+    print(item)
+
+# Graph relations (if you use them)
+if "relations" in result:
+    for relation in result["relations"]:
+        print(relation)
+```
+
+---
+
+## Enhanced Message Handling
+
+The platform client (MemoryClient) now supports the same flexible message formats as the OSS version:
+
+```python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-key")
+
+# All three formats now work:
+
+# 1. Single string (automatically converted to user message)
+client.add("I like pizza", user_id="alice")
+
+# 2. Single message dictionary
+client.add({"role": "user", "content": "I like pizza"}, user_id="alice")
+
+# 3. List of messages (conversation)
+client.add([
+    {"role": "user", "content": "I like pizza"},
+    {"role": "assistant", "content": "I'll remember that!"}
+], user_id="alice")
+```
+
+### Async Mode Configuration
+
+The `async_mode` parameter now defaults to `True` but can be configured:
+
+```python
+# Default behavior (async_mode=True)
+client.add(messages, user_id="alice")
+
+# Explicitly set async mode
+client.add(messages, user_id="alice", async_mode=True)
+
+# Disable async mode if needed
+client.add(messages, user_id="alice", async_mode=False)
+```
+
+**Note:** `async_mode=True` provides better performance for most use cases. Only set it to `False` if you have specific synchronous processing requirements.
+
+---
+
+## That's It!
+
+For most users, that's all you need to know. The changes are:
+- ✅ No more `version` or `output_format` parameters
+- ✅ Consistent `{"results": [...]}` response format
+- ✅ Cleaner, simpler API
+
+---
+
+## Common Issues
+
+**Getting `KeyError: 'results'`?**
+
+Your code is still treating the response as a list. Update it:
+```python
+# Change this:
+for memory in response:
+
+# To this:
+for memory in response["results"]:
+```
+
+**Getting `TypeError: unexpected keyword argument`?**
+
+You're still passing old parameters. Remove them:
+```python
+# Change this:
+client.add(messages, output_format="v1.1")
+
+# To this:
+client.add(messages)
+```
+
+**Seeing deprecation warnings?**
+
+Remove any explicit `version="v1.0"` from your config:
+```python
+# Change this:
+memory = Memory(config=MemoryConfig(version="v1.0"))
+
+# To this:
+memory = Memory()
+```
+
+---
+
+## What's New in 1.0.0
+
+- **Better vector stores:** Fixed OpenSearch and improved reliability across all stores
+- **Cleaner API:** One way to do things, no more confusing options
+- **Enhanced GCP support:** Better Vertex AI configuration options
+- **Flexible message input:** Platform client now accepts strings, dicts, and lists (aligned with OSS)
+- **Configurable async_mode:** Now defaults to `True` but users can override if needed
+
+---
+
+## Need Help?
+
+- Check [GitHub Issues](https://github.com/mem0ai/mem0/issues)
+- Read the [documentation](https://docs.mem0.ai/)
+- Open a new issue if you're stuck
+
+---
+
+## Advanced: Configuration Changes
+
+**If you configured vector stores with version:**
+
+```python
+# Before
+config = MemoryConfig(
+    version="v1.1",
+    vector_store=VectorStoreConfig(...)
+)
+
+# After
+config = MemoryConfig(
+    vector_store=VectorStoreConfig(...)
+)
+```
+
+---
+
+## Testing Your Migration
+
+Quick sanity check:
+
+```python
+from mem0 import Memory
+
+memory = Memory()
+
+# Add should return a dict with "results"
+result = memory.add("I like pizza", user_id="test")
+assert "results" in result
+
+# Search should return a dict with "results"
+search = memory.search("food", user_id="test")
+assert "results" in search
+
+# Get all should return a dict with "results"
+all_memories = memory.get_all(user_id="test")
+assert "results" in all_memories
+
+print("✅ Migration successful!")
+```

Makefile

@@ -13,7 +13,7 @@ install:
 install_all:
 	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
+							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:
@@ -50,3 +50,6 @@ test-py-3.10:
 
 test-py-3.11:
 	hatch run dev_py_3_11:test
+
+test-py-3.12:
+	hatch run dev_py_3_12:test

README.md

@@ -21,7 +21,7 @@
 
 <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">
@@ -47,6 +47,8 @@
   <strong>⚡ +26% Accuracy vs. OpenAI Memory • 🚀 91% Faster • 💰 90% Fewer Tokens</strong>
 </p>
 
+> **🎉 mem0ai v1.0.0 is now available!** This major release includes API modernization, improved vector store support, and enhanced GCP integration. [See migration guide →](MIGRATION_GUIDE_v1.0.md)
+
 ##  🔥 Research Highlights
 - **+26% Accuracy** over OpenAI Memory on the LOCOMO benchmark
 - **91% Faster Responses** than full-context, ensuring low-latency at scale
@@ -95,7 +97,7 @@ 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/components/llms/overview).
+Mem0 requires an LLM to function, with `gpt-4.1-nano-2025-04-14 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:
 
@@ -114,7 +116,7 @@ def chat_with_memories(message: str, user_id: str = "default_user") -> str:
     # 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}]
-    response = openai_client.chat.completions.create(model="gpt-4o-mini", messages=messages)
+    response = openai_client.chat.completions.create(model="gpt-4.1-nano-2025-04-14", messages=messages)
     assistant_response = response.choices[0].message.content
 
     # Create new memories from the conversation
@@ -166,4 +168,4 @@ We now have a paper you can cite:
 
 ## ⚖️ License
 
-Apache 2.0 — see the [LICENSE](LICENSE) file for details.
+Apache 2.0 — see the [LICENSE](https://github.com/mem0ai/mem0/blob/main/LICENSE) file for details.

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

@@ -1,3 +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.
+  <strong>🎉 Mem0 1.0.0 is here!</strong> Enhanced filtering, reranking, and smarter memory management.
 </Note>

docs/_snippets/security-compliance.mdx

@@ -1,3 +0,0 @@
-<Note type="info">
-  🔐 Mem0 is now <strong>SOC 2</strong> and <strong>HIPAA</strong> compliant! We're committed to the highest standards of data security and privacy, enabling secure memory for enterprises, healthcare, and beyond. [Learn more](https://mem0.ai/security)
-</Note>

docs/api-reference.mdx

@@ -1,193 +1,108 @@
 ---
-title: Overview
-icon: "info"
+title: "Overview"
+icon: "terminal"
 iconType: "solid"
+description: "REST APIs for memory management, search, and entity operations"
 ---
 
-<Snippet file="security-compliance.mdx" />
+## Mem0 REST API
 
-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.
+Mem0 provides a comprehensive REST API for integrating advanced memory capabilities into your applications. Create, search, update, and manage memories across users, agents, and custom entities with simple HTTP requests.
 
-## Key Features
+<Info>
+**Quick start:** Get your API key from the [Mem0 Dashboard](https://app.mem0.ai/dashboard/api-keys) and make your first memory operation in minutes.
+</Info>
 
-- **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
+## Quick Start Guide
 
-Our API is organized into several main categories:
+Get started with Mem0 API in three simple steps:
 
-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.
+1. **[Add Memories](/api-reference/memory/add-memories)** - Store information and context from user conversations
+2. **[Search Memories](/api-reference/memory/search-memories)** - Retrieve relevant memories using semantic search
+3. **[Get Memories](/api-reference/memory/get-memories)** - Fetch all memories for a specific entity
+
+---
+
+## Core Operations
+
+<CardGroup cols={2}>
+  <Card title="Add Memories" icon="plus" href="/api-reference/memory/add-memories">
+    Store new memories from conversations and interactions
+  </Card>
+
+  <Card title="Search Memories" icon="magnifying-glass" href="/api-reference/memory/search-memories">
+    Find relevant memories using semantic search with filters
+  </Card>
+
+  <Card title="Update Memory" icon="pen" href="/api-reference/memory/update-memory">
+    Modify existing memory content and metadata
+  </Card>
+
+  <Card title="Delete Memory" icon="trash" href="/api-reference/memory/delete-memory">
+    Remove specific memories or batch delete operations
+  </Card>
+</CardGroup>
+
+---
+
+## API Categories
+
+Explore the full API organized by functionality:
+
+<CardGroup cols={2}>
+  <Card title="Memory APIs" icon="microchip" href="/api-reference/memory/add-memories">
+    Core and advanced operations: CRUD, search, batch updates, history, and exports
+  </Card>
+
+  <Card title="Events APIs" icon="clock" href="/api-reference/events/get-events">
+    Track and monitor the status of asynchronous memory operations
+  </Card>
+
+  <Card title="Entities APIs" icon="users" href="/api-reference/entities/get-users">
+    Manage users, agents, and their associated memory data
+  </Card>
+
+  <Card title="Organizations & Projects" icon="building" href="/api-reference/organizations-projects">
+    Multi-tenant support, access control, and team collaboration
+  </Card>
+
+  <Card title="Webhooks" icon="webhook" href="/api-reference/webhook/create-webhook">
+    Real-time notifications for memory events and updates
+  </Card>
+</CardGroup>
+
+<Note>
+**Building multi-tenant apps?** Learn about [Organizations & Projects](/api-reference/organizations-projects) for team isolation and access control.
+</Note>
+
+---
 
 ## Authentication
 
-All API requests require authentication using HTTP Basic Auth. Ensure you include your API key in the Authorization header of each request.
+All API requests require authentication using Token-based authentication. Include your API key in the Authorization header:
 
-## 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')
+```bash
+Authorization: Token <your-api-key>
 ```
 
-  </Tab>
+Get your API key from the [Mem0 Dashboard](https://app.mem0.ai/dashboard/api-keys).
 
-  <Tab title="Node.js">
+<Warning>
+**Keep your API key secure.** Never expose it in client-side code or public repositories. Use environment variables and server-side requests only.
+</Warning>
 
-```javascript
-import { MemoryClient } from "mem0ai";
-const client = new MemoryClient({organizationId: "YOUR_ORG_ID", projectId: "YOUR_PROJECT_ID"});
-```
+---
 
-  </Tab>
-</Tabs>
+## Next Steps
 
-### Project Management Methods
+<CardGroup cols={2}>
+  <Card title="Add Your First Memory" icon="rocket" href="/api-reference/memory/add-memories">
+    Start storing memories via the REST API
+  </Card>
 
-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.
+  <Card title="Search with Filters" icon="filter" href="/api-reference/memory/search-memories">
+    Learn advanced search and filtering techniques
+  </Card>
+</CardGroup>

docs/api-reference/entities/delete-user.mdx

@@ -1,4 +1,4 @@
 ---
 title: 'Delete User'
-openapi: delete /v1/entities/{entity_type}/{entity_id}/
+openapi: delete /v2/entities/{entity_type}/{entity_id}/
 ---

docs/api-reference/events/get-event.mdx

@@ -0,0 +1,6 @@
+---
+title: 'Get Event'
+openapi: get /v1/event/{event_id}/
+---
+
+Retrieve details about a specific event by passing its `event_id`. This endpoint is particularly helpful for tracking the status, payload, and completion details of asynchronous memory operations.

docs/api-reference/events/get-events.mdx

@@ -0,0 +1,13 @@
+---
+title: 'Get Events'
+openapi: get /v1/events/
+---
+
+List recent events for your organization and project.
+
+## Use Cases
+
+- **Dashboards**: Summarize adds/searches over time by paging through events.
+- **Alerting**: Poll for `FAILED` events and trigger follow-up workflows.
+- **Audit**: Store the returned payload/metadata for compliance logs.
+

docs/api-reference/memory/add-memories.mdx

@@ -1,4 +1,97 @@
 ---
 title: 'Add Memories'
 openapi: post /v1/memories/
----
+---
+
+Add new facts, messages, or metadata to a user’s memory store. The Add Memories endpoint accepts either raw text or conversational turns and commits them asynchronously so the memory is ready for later search, retrieval, and graph queries.
+
+## Endpoint
+
+- **Method**: `POST`
+- **URL**: `/v1/memories/`
+- **Content-Type**: `application/json`
+
+Memories are processed asynchronously by default. The response contains queued events you can track while the platform finalizes enrichment.
+
+## Required headers
+
+| Header | Required | Description |
+| --- | --- | --- |
+| `Authorization: Token <MEM0_API_KEY>` | Yes | API key scoped to your workspace. |
+| `Accept: application/json` | Yes | Ensures a JSON response. |
+
+## Request body
+
+Provide at least one message or direct memory string. Most callers supply `messages` so Mem0 can infer structured memories as part of ingestion.
+
+<CodeGroup>
+```json Basic request
+{
+  "user_id": "alice",
+  "messages": [
+    { "role": "user", "content": "I moved to Austin last month." }
+  ],
+  "metadata": {
+    "source": "onboarding_form"
+  }
+}
+```
+</CodeGroup>
+
+### Common fields
+
+| Field | Type | Required | Description |
+| --- | --- | --- | --- |
+| `user_id` | string | No* | Associates the memory with a user. Provide when you want the memory scoped to a specific identity. |
+| `messages` | array | No* | Conversation turns for Mem0 to infer memories from. Each object should include `role` and `content`. |
+| `metadata` | object | Optional | Custom key/value metadata (e.g., `{"topic": "preferences"}`). |
+| `infer` | boolean (default `true`) | Optional | Set to `false` to skip inference and store the provided text as-is. |
+| `async_mode` | boolean (default `true`) | Optional | Controls asynchronous processing. Most clients leave this enabled. |
+| `output_format` | string (default `v1.1`) | Optional | Response format. `v1.1` wraps results in a `results` array. |
+
+> \* Provide at least one `messages` entry to describe what you are storing. For scoped memories, include `user_id`. You can also attach `agent_id`, `app_id`, `run_id`, `project_id`, or `org_id` to refine ownership.
+
+## Response
+
+Successful requests return an array of events queued for processing. Each event includes the generated memory text and an identifier you can persist for auditing.
+
+<CodeGroup>
+```json 200 response
+[
+  {
+    "id": "mem_01JF8ZS4Y0R0SPM13R5R6H32CJ",
+    "event": "ADD",
+    "data": {
+      "memory": "The user moved to Austin in 2025."
+    }
+  }
+]
+```
+
+```json 400 response
+{
+  "error": "400 Bad Request",
+  "details": {
+    "message": "Invalid input data. Please refer to the memory creation documentation at https://docs.mem0.ai/platform/quickstart#4-1-create-memories for correct formatting and required fields."
+  }
+}
+```
+</CodeGroup>
+
+## Graph relationships
+
+Add Memories can enrich the knowledge graph on write. Set `enable_graph: true` to create entity nodes and relationships for the stored memory. Use this when you want downstream `get_all` or search calls to traverse connected entities.
+
+<CodeGroup>
+```json Graph-aware request
+{
+  "user_id": "alice",
+  "messages": [
+    { "role": "user", "content": "I met with Dr. Lee at General Hospital." }
+  ],
+  "enable_graph": true
+}
+```
+</CodeGroup>
+
+The response follows the same format, and related entities become available in [Graph Memory](/platform/features/graph-memory) queries.

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

@@ -3,4 +3,4 @@ title: 'Create Memory Export'
 openapi: post /v1/exports/
 ---
 
-Submit a job to create a structured export of memories using a customizable Pydantic schema. This process may take some time to complete, especially if you’re exporting a large number of memories. You can tailor the export by applying various filters (e.g., user_id, agent_id, run_id, or session_id) and by modifying the Pydantic schema to ensure the final data matches your exact needs.
+Submit a job to create a structured export of memories using a customizable Pydantic schema. This process may take some time to complete, especially if you're exporting a large number of memories. You can tailor the export by applying various filters (e.g., `user_id`, `agent_id`, `run_id`, or `session_id`) and by modifying the Pydantic schema to ensure the final data matches your exact needs.

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

@@ -0,0 +1,99 @@
+---
+title: "Get Memories"
+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, 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
+memories = client.get_all(
+    filters={
+        "AND": [
+            {
+                "user_id": "alex"
+            },
+            {
+                "created_at": {"gte": "2024-07-01", "lte": "2024-07-31"}
+            }
+        ]
+    }
+)
+```
+
+```python Output
+{
+    "results": [
+        {
+            "id": "f4cbdb08-7062-4f3e-8eb2-9f5c80dfe64c",
+            "memory": "Alex is planning a trip to San Francisco from July 1st to July 10th",
+            "created_at": "2024-07-01T12:00:00Z",
+            "updated_at": "2024-07-01T12:00:00Z"
+        },
+        {
+            "id": "a2b8c3d4-5e6f-7g8h-9i0j-1k2l3m4n5o6p",
+            "memory": "Alex prefers vegetarian restaurants",
+            "created_at": "2024-07-05T15:30:00Z",
+            "updated_at": "2024-07-05T15:30:00Z"
+        }
+    ],
+    "total": 2
+}
+```
+
+</CodeGroup>
+
+## Graph Memory
+
+To retrieve graph memory relationships between entities, pass `output_format="v1.1"` in your request. This will return memories with entity and relationship information from the knowledge graph.
+
+<CodeGroup>
+```python Code
+memories = client.get_all(
+    filters={
+        "user_id": "alex"
+    },
+    output_format="v1.1"
+)
+```
+
+```python Output
+{
+    "results": [
+        {
+            "id": "f4cbdb08-7062-4f3e-8eb2-9f5c80dfe64c",
+            "memory": "Alex is planning a trip to San Francisco",
+            "entities": [
+                {
+                    "id": "entity-1",
+                    "name": "Alex",
+                    "type": "person"
+                },
+                {
+                    "id": "entity-2",
+                    "name": "San Francisco",
+                    "type": "location"
+                }
+            ],
+            "relations": [
+                {
+                    "source": "entity-1",
+                    "target": "entity-2",
+                    "relationship": "traveling_to"
+                }
+            ]
+        }
+    ]
+}
+```
+
+</CodeGroup>

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

@@ -0,0 +1,104 @@
+---
+title: 'Search Memories'
+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, 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 Platform API Example
+related_memories = client.search(
+    query="What are Alice's hobbies?",
+    filters={
+        "OR": [
+            {
+              "user_id": "alice"
+            },
+            {
+              "agent_id": {"in": ["travel-agent", "sports-agent"]}
+            }
+        ]
+    },
+)
+```
+
+```json Output
+{
+  "memories": [
+    {
+      "id": "ea925981-272f-40dd-b576-be64e4871429",
+      "memory": "Likes to play cricket and plays cricket on weekends.",
+      "metadata": {
+        "category": "hobbies"
+      },
+      "score": 0.32116443111457704,
+      "created_at": "2024-07-26T10:29:36.630547-07:00",
+      "updated_at": null,
+      "user_id": "alice",
+      "agent_id": "sports-agent"
+    }
+  ],
+}
+```
+</CodeGroup>
+
+<CodeGroup>
+```python Wildcard Example
+# Using wildcard to match all run_ids for a specific user
+all_memories = client.search(
+    query="What are Alice's hobbies?",
+    filters={
+        "AND": [
+            {
+                "user_id": "alice"
+            },
+            {
+                "run_id": "*"
+            }
+        ]
+    },
+)
+```
+</CodeGroup>
+
+<CodeGroup>
+```python Categories Filter Examples
+# Example 1: Using 'contains' for partial matching
+finance_memories = client.search(
+    query="What are my financial goals?",
+    filters={
+        "AND": [
+            { "user_id": "alice" },
+            {
+                "categories": {
+                    "contains": "finance"
+                }
+            }
+        ]
+    },
+)
+
+# Example 2: Using 'in' for exact matching
+personal_memories = client.search(
+    query="What personal information do you have?",
+    filters={
+        "AND": [
+            { "user_id": "alice" },
+            {
+                "categories": {
+                    "in": ["personal_information"]
+                }
+            }
+        ]
+    },
+)
+```
+</CodeGroup>

docs/api-reference/memory/v1-get-memories.mdx

@@ -1,4 +0,0 @@
----
-title: 'Get Memories (v1 - Deprecated)'
-openapi: get /v1/memories/
----

docs/api-reference/memory/v1-search-memories.mdx

@@ -1,4 +0,0 @@
----
-title: 'Search Memories (v1 - Deprecated)'
-openapi: post /v1/memories/search/
----

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

@@ -1,65 +0,0 @@
----
-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, 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
-memories = m.get_all(
-    filters={
-        "AND": [
-            {
-                "user_id": "alex"
-            },
-            {
-                "created_at": {"gte": "2024-07-01", "lte": "2024-07-31"}
-            }
-        ]
-    },
-    version="v2"
-)
-```
-
-```json Output
-[
-{
-    "id":"f38b689d-6b24-45b7-bced-17fbb4d8bac7",
-    "memory":"Name: Alex. Vegetarian. Allergic to nuts.",
-    "user_id":"alex",
-    "hash":"62bc074f56d1f909f1b4c2b639f56f6a",
-    "metadata":null,
-    "created_at":"2024-07-25T23:57:00.108347-07:00",
-    "updated_at":"2024-07-25T23:57:00.108367-07:00"
-}
-]
-```
-</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

@@ -1,72 +0,0 @@
----
-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, 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
-  related_memories = m.search(
-      query="What are Alice's hobbies?",
-      version="v2",
-      filters={
-          "OR": [
-              {
-                "user_id": "alice"
-              },
-              {
-                "agent_id": {"in": ["travel-agent", "sports-agent"]}
-              }
-          ]
-      },
-  )
-  ```
-
-  ```json Output
-  {
-    "memories": [
-      {
-        "id": "ea925981-272f-40dd-b576-be64e4871429",
-        "memory": "Likes to play cricket and plays cricket on weekends.",
-        "metadata": {
-          "category": "hobbies"
-        },
-        "score": 0.32116443111457704,
-        "created_at": "2024-07-26T10:29:36.630547-07:00",
-        "updated_at": null,
-        "user_id": "alice",
-        "agent_id": "sports-agent"
-      }
-    ],
-  }
-  ```
-  </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>

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/organizations-projects.mdx

@@ -0,0 +1,197 @@
+---
+title: Organizations & Projects
+icon: "building"
+description: "Manage multi-tenant applications with organization and project APIs"
+---
+
+## Overview
+
+Organizations and projects provide multi-tenant support, access control, and team collaboration capabilities for Mem0 Platform. Use these APIs to build applications that support multiple teams, customers, or isolated environments.
+
+<Info>
+Organizations and projects are **optional** features. You can use Mem0 without them for single-user or simple multi-user applications.
+</Info>
+
+## Key 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
+
+---
+
+## Using Organizations & Projects
+
+### Initialize with Org/Project Context
+
+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
+
+The Mem0 client provides comprehensive project management 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
+
+<Warning>
+This action will remove all memories, messages, and other related data in the project. **This operation is irreversible.**
+</Warning>
+
+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
+
+| Role | Permissions |
+|------|-------------|
+| **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 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())
+```
+
+---
+
+## API Reference
+
+For complete API specifications and additional endpoints, see:
+
+<CardGroup cols={2}>
+  <Card title="Organizations APIs" icon="building" href="/api-reference/organization/create-org">
+    Create, get, and manage organizations
+  </Card>
+
+  <Card title="Project APIs" icon="folder" href="/api-reference/project/create-project">
+    Full project CRUD and member management endpoints
+  </Card>
+</CardGroup>

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/api-reference/webhook/create-webhook.mdx

@@ -3,7 +3,3 @@ title: 'Create Webhook'
 openapi: post /api/v1/webhooks/projects/{project_id}/
 ---
 
-## Create Webhook
-
-Create a webhook by providing the project ID and the webhook details.
-

docs/api-reference/webhook/delete-webhook.mdx

@@ -2,7 +2,3 @@
 title: 'Delete Webhook'
 openapi: delete /api/v1/webhooks/{webhook_id}/
 ---
-
-## Delete Webhook
-
-Delete a webhook by providing the webhook ID.

docs/api-reference/webhook/get-webhook.mdx

@@ -3,7 +3,3 @@ title: 'Get Webhook'
 openapi: get /api/v1/webhooks/projects/{project_id}/
 ---
 
-## Get Webhook
-
-Get a webhook by providing the project ID.
-

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

@@ -3,7 +3,3 @@ title: 'Update Webhook'
 openapi: put /api/v1/webhooks/{webhook_id}/
 ---
 
-## Update Webhook
-
-Update a webhook by providing the webhook ID and the fields to update.
-

docs/changelog.mdx

@@ -3,11 +3,253 @@ title: "Product Updates"
 mode: "wide"
 ---
 
-<Snippet file="security-compliance.mdx" />
-
+ 
 <Tabs>
 <Tab title="Python">
 
+<Update label="2026-03-19" description="v1.0.7">
+
+**Bug Fixes:**
+- **Core:** Fixed control characters in LLM JSON responses causing parse failures (#4420)
+- **Core:** Replaced hardcoded US/Pacific timezone references with `timezone.utc` (#4404)
+- **Core:** Preserved `http_auth` in `_safe_deepcopy_config` for OpenSearch (#4418)
+- **Core:** Normalized malformed LLM fact output before embedding (#4224)
+- **Embeddings:** Pass `encoding_format='float'` in OpenAI embeddings for proxy compatibility (#4058)
+- **LLMs:** Fixed Ollama to pass tools to `client.chat` and parse `tool_calls` from response (#4176)
+- **Reranker:** Support nested LLM config in `LLMReranker` for non-OpenAI providers (#4405)
+- **Vector Stores:** Cast `vector_distance` to float in Redis search (#4377)
+
+**Improvements:**
+- **Embeddings:** Improved Ollama embedder with model name normalization and error handling (#4403)
+
+</Update>
+
+<Update label="2026-03-16" description="v1.0.6">
+
+**Bug Fixes:**
+- **Telemetry:** Fixed telemetry vector store initialization still running when `MEM0_TELEMETRY` is disabled (#4351)
+- **Core:** Removed destructive `vector_store.reset()` call from `delete_all()` that was wiping the entire vector store instead of deleting only the target memories (#4349)
+- **OSS:** `OllamaLLM` now respects the configured URL instead of always falling back to localhost (#4320)
+- **Core:** Fixed `KeyError` when LLM omits the `entities` key in tool call response (#4313)
+- **Prompts:** Ensured JSON instruction is included in prompts when using `json_object` response format (#4271)
+- **Core:** Fixed incorrect database parameter handling (#3913)
+
+**Dependencies:**
+- Updated LangChain dependencies to v1.0.0 (#4353)
+- Bumped protobuf dependency to 5.29.6 and extended upper bound to `<7.0.0` (#4326)
+
+</Update>
+
+<Update label="2026-03-03" description="v1.0.5">
+- **Telemetry Fix**
+  - Fixed an issue where the PostHog client was initialized even after telemetry was disabled. Although events were not captured, the client was unnecessarily initialized.
+</Update>
+
+<Update label="2026-02-17" description="v1.0.4">
+
+**New Features & Updates:**
+- **Memory Update:**
+  - Added `timestamp` parameter to `update()` — accepts Unix epoch (int/float) or ISO 8601 string
+
+</Update>
+
+<Update label="2026-01-29" description="v1.0.3">
+
+**New Features & Updates:**
+- **Project Settings:**
+  - Added inclusion prompt, exclusion prompt, memory depth, and usecase setting
+
+</Update>
+
+<Update label="2026-01-13" description="v1.0.2">
+
+**New Features & Updates:**
+- **Vector Stores:**
+  - Added DriverInfo metadata to MongoDB vector store
+
+</Update>
+
+<Update label="2025-11-14" description="v1.0.1">
+
+**New Features & Updates:**
+- **Vector Stores:**
+  - Added Apache Cassandra vector store support
+- **Embeddings:**
+  - Added FastEmbed embedding support for local embeddings
+- **Graph Store:**
+  - Added configurable embedding similarity threshold for graph store node matching
+
+**Bug Fixes:**
+- **Core:**
+  - Fixed condition check for memories_result type in Memory class
+  - Fixed list_memories endpoint Pydantic validation error
+  - Fixed memory deletion not removing from vector store
+
+</Update>
+
+<Update label="2025-10-16" description="v1.0.0">
+
+**New Features & Updates:**
+- **Vector Stores:**
+  - Added Azure MySQL support
+  - Added Azure AI Search Vector Store support
+- **LLMs:**
+  - Added Tool Call support for LangchainLLM
+  - Enabled custom model and parameters for Hugging Face with huggingface_base_url
+  - Updated default LLM configuration
+- **Rerankers:**
+  - Added reranker support: Cohere, ZeroEntropy, Hugging Face, Sentence Transformers, and LLMs
+- **Core:**
+  - Added metadata filtering for OSS
+  - Added Assistant memory retrieval
+  - Enabled async mode as default
+
+**Improvements:**
+- **Prompts:**
+  - Improved prompt for better memory retrieval
+- **Dependencies:**
+  - Updated dependency compatibility with OpenAI 2.x
+- **Validation:**
+  - Validated embedding_dims for Kuzu integration
+
+**Bug Fixes:**
+- **Vector Stores:**
+  - Fixed Databricks Vector Store integration
+  - Fixed Milvus DB bug and added test coverage
+  - Fixed Weaviate search method
+- **LLMs:**
+  - Fixed bug with thinking LLM in vLLM
+
+</Update>
+
+<Update label="2025-09-25" description="v0.1.118">
+
+**New Features & Updates:**
+- **Vector Stores:**
+  - Added Valkey vector store support
+  - Added support for ChromaDB Cloud
+  - Added Mem0 vector store backend integration for Neptune Analytics
+- **Graph Store:**
+  - Added Neptune-DB graph store with vector store
+- **Core:**
+  - Implemented structured exception classes with error codes and suggested actions
+
+**Improvements:**
+- **Dependencies:**
+  - Updated OpenAI dependency and improved Ollama compatibility
+- **Testing:**
+  - Added Weaviate DB test
+  - Added comprehensive test suite for SQLiteManager
+- **Documentation:**
+  - Updated category docs
+  - Updated Search V2 / Get All V2 filters documentation
+  - Refactored AWS example title
+  - Fixed Quickstart cURL example
+
+**Bug Fixes:**
+- **Vector Stores:**
+  - Databricks bug fixes
+  - Fixed S3 Vectors memory initialization issue from configuration
+- **Core:**
+  - Fixed JSON parsing with new memories
+  - Replaced hardcoded LLM provider with provider from configuration
+- **LLMs:**
+  - Fixed Bedrock Anthropic models to use system field
+
+</Update>
+
+<Update label="2025-09-03" description="v0.1.117">
+
+**New Features & Updates:**
+- **OpenMemory:**
+  - Added memory export / import feature
+  - Added vector store integrations: Weaviate, FAISS, PGVector, Chroma, Redis, Elasticsearch, Milvus
+  - Added `export_openmemory.sh` migration script
+- **Vector Stores:**
+  - Added Amazon S3 Vectors support
+  - Added Databricks Mosaic AI vector store support
+  - Added support for OpenAI Store
+- **Graph Memory:** Added support for graph memory using Kuzu
+- **Azure:** Added Azure Identity for Azure OpenAI and Azure AI Search authentication
+- **Elasticsearch:** Added headers configuration support
+
+**Improvements:**
+  - Added custom connection client to enable connecting to local containers for Weaviate
+  - Updated configuration AWS Bedrock
+  - Fixed dependency issues and tests; updated docstrings
+- **Documentation:**
+  - Fixed Graph Docs page missing in sidebar
+  - Updated integration documentation
+  - Added version param in Search V2 API documentation
+  - Updated Databricks documentation and refactored docs
+  - Updated favicon logo
+  - Fixed typos and Typescript docs
+
+**Bug Fixes:**
+- Baidu: Added missing provider for Baidu vector DB
+- MongoDB: Replaced `query_vector` args in search method
+- Fixed new memory mistaken for current
+- AsyncMemory._add_to_vector_store: handled edge case when no facts found
+- Fixed missing commas in Kuzu graph INSERT queries
+- Fixed inconsistent created and updated properties for Graph
+- Fixed missing `app_id` on client for Neptune Analytics
+- Correctly pick AWS region from environment variable
+- Fixed Ollama model existence check
+
+**Refactoring:**
+- **PGVector:** Use internal connection pools and context managers
+
+</Update>
+
+<Update label="2025-08-14" description="v0.1.116">
+
+**New Features & Updates:**
+- **Pinecone:** Added namespace support and improved type safety
+- **Milvus:** Added db_name field to MilvusDBConfig
+- **Vector Stores:** Added multi-id filters support
+- **Vercel AI SDK:** Migration to AI SDK V5.0
+- **Python Support:** Added Python 3.12 support
+- **Graph Memory:** Added sanitizer methods for nodes and relationships
+- **LLM Monitoring:** Added monitoring callback support
+
+**Improvements:**
+- **Performance:**
+  - Improved async handling in AsyncMemory class
+- **Documentation:**
+  - Added async add announcement
+  - Added personalized search docs
+  - Added Neptune examples
+  - Added V5 migration docs
+- **Configuration:**
+  - Refactored base class config for LLMs
+  - Added sslmode for pgvector
+- **Dependencies:**
+  - Updated psycopg to version 3
+  - Updated Docker compose
+
+**Bug Fixes:**
+- **Tests:**
+  - Fixed failing tests
+  - Restricted package versions
+- **Memgraph:**
+  - Fixed async attribute errors
+  - Fixed n_embeddings usage
+  - Fixed indexing issues
+- **Vector Stores:**
+  - Fixed Qdrant cloud indexing
+  - Fixed Neo4j Cypher syntax
+  - Fixed LLM parameters
+- **Graph Store:**
+  - Fixed LM config prioritization
+- **Dependencies:**
+  - Fixed JSON import for psycopg
+
+**Refactoring:**
+- **Google AI:** Refactored from Gemini to Google AI
+- **Base Classes:** Refactored LLM base class configuration
+
+</Update>
+
 <Update label="2025-07-24" description="v0.1.115">
 
 **New Features & Updates:**
@@ -153,7 +395,7 @@ mode: "wide"
 <Update label="2025-06-11" description="v0.1.107">
 
 **Improvements:**
-- **Documentation:** 
+- **Documentation:**
   - Updated Livekit documentation migration
   - Updated OpenMemory hosted version documentation
 - **Core:** Updated categorization flow
@@ -190,7 +432,7 @@ mode: "wide"
 - **LLM:** Added support for OpenAI compatible LLM providers with baseUrl configuration
 
 **Improvements:**
-- **Documentation:** 
+- **Documentation:**
   - Fixed broken links
   - Improved Graph Memory features documentation clarity
   - Updated enable_graph documentation
@@ -207,14 +449,14 @@ mode: "wide"
 - **OpenMemory:** Added LLM and Embedding Providers support
 
 **Improvements:**
-- **Documentation:** 
+- **Documentation:**
   - Updated memory export documentation
   - Enhanced role-based memory attribution rules documentation
   - Updated API reference and messages documentation
   - Added Mastra and Raycast documentation
   - Added NOT filter documentation for Search and GetAll V2
   - Announced Claude 4 support
-- **Core:** 
+- **Core:**
   - Removed support for passing string as input in client.add()
   - Added support for sarvam-m model
 - **TypeScript SDK:** Fixed types from message interface
@@ -231,7 +473,7 @@ mode: "wide"
 - **Neo4j:** Added base label configuration support
 
 **Improvements:**
-- **Documentation:** 
+- **Documentation:**
   - Updated Healthcare example index
   - Enhanced collaborative task agent documentation clarity
   - Added criteria-based filtering documentation
@@ -327,7 +569,7 @@ mode: "wide"
 - **Vector Stores:** Added reset function for VectorDBs
 
 **Improvements:**
-- **Documentation:** 
+- **Documentation:**
   - Updated timestamp and expiration_date documentation
   - Fixed v2 search documentation
   - Added "memory" in EC "Custom config" section
@@ -366,12 +608,12 @@ mode: "wide"
 
 **New Features:**
 - **LLM Integrations:** Added Azure OpenAI Embedding Model
-- **Examples:** 
+- **Examples:**
   - Added movie recommendation using grok3
   - Added Voice Assistant using Elevenlabs
 
 **Improvements:**
-- **Documentation:** 
+- **Documentation:**
   - Added keywords AI
   - Reformatted navbar page URLs
   - Updated changelog
@@ -386,7 +628,7 @@ mode: "wide"
 - **LLM Integrations:** Added Mistral AI as LLM provider
 
 **Improvements:**
-- **Documentation:** 
+- **Documentation:**
   - Updated changelog
   - Fixed memory exclusion example
   - Updated xAI documentation
@@ -403,7 +645,7 @@ mode: "wide"
 
 **New Features:**
 - **Langchain Integration:** Added support for Langchain VectorStores
-- **Examples:** 
+- **Examples:**
   - Added personal assistant example
   - Added personal study buddy example
   - Added YouTube assistant Chrome extension example
@@ -520,6 +762,108 @@ mode: "wide"
 
 <Tab title="TypeScript">
 
+<Update label="2026-03-19" description="v2.4.2">
+
+**Bug Fixes:**
+- **Client:** Fixed webhook `createWebhook` and `updateWebhook` API serialization
+- **Client:** Added missing `MEMORY_CATEGORIZED` event type to `WebhookEvent` enum
+- **Types:** Added `WebhookCreatePayload` and `WebhookUpdatePayload` for better type safety
+
+**Tests:**
+- Added end-to-end unit test coverage for the platform client — CRUD, batch, search, webhooks, users, project, and initialization (#4357)
+- Added real API integration tests for memory CRUD, batch operations, search, user management, project configuration, and webhook lifecycle (#4395)
+- Deleted obsolete e2e test files replaced by the new structured test suite (#4419)
+
+</Update>
+
+<Update label="2026-03-16" description="v2.4.1">
+
+**Bug Fixes:**
+- **Core:** Fixed code block content extraction — content inside code blocks is now properly extracted instead of being deleted (#4317)
+
+**Improvements:**
+- **Code Quality:** Fixed linting issues across the SDK (#4334)
+
+</Update>
+
+<Update label="2026-03-14" description="v2.4.0">
+
+**Bug Fixes:**
+- **OSS Storage:** Fixed `SQLITE_CANTOPEN` errors when running as a LaunchAgent, systemd service, or in containers where `process.cwd()` is read-only (e.g. `/`). Default `vector_store.db` location changed from `process.cwd()/vector_store.db` to `~/.mem0/vector_store.db`.
+- **OSS Storage:** Fixed `historyDbPath` config being silently ignored — config merging always overwrote it with defaults. Top-level `historyDbPath` is now correctly propagated into `historyStore.config` with proper precedence.
+- **OSS Storage:** Added `ensureSQLiteDirectory()` — parent directories for SQLite database files are now auto-created before opening, preventing `SQLITE_CANTOPEN` when using nested paths.
+
+**Improvements:**
+- **Migration:** Added deprecation warning when an existing `vector_store.db` is found at the old `process.cwd()` location, guiding users to move it or set `vectorStore.config.dbPath` explicitly.
+- **Config:** Limited default SQLite config spreading to only SQLite history providers, preventing config leaking into Supabase or other providers.
+
+</Update>
+
+<Update label="2026-03-09" description="v2.3.0">
+
+**Breaking Changes:**
+- **Dependencies:** Minimum Node.js version for OSS sqlite features is now Node 20+ (due to `better-sqlite3` v12)
+
+**Bug Fixes:**
+- **OSS Storage:** Replaced `sqlite3` with `better-sqlite3` to fix native binding resolution failures under jiti-based loaders (e.g. OpenClaw plugin system). Fixes issues where the `bindings` module walked V8 stack frames with synthetic filenames, failing to locate the native `.node` addon.
+- **OSS Storage:** Fixed async init race condition in `SQLiteManager` — `init()` is now synchronous
+- **OSS Vector Store:** Migrated `MemoryVectorStore` from `sqlite3` to `better-sqlite3` with transactional batch inserts
+
+**Improvements:**
+- **Performance:** Cached prepared statements in `SQLiteManager` for faster history operations
+- **Performance:** Batch `insert()` in `MemoryVectorStore` wrapped in a transaction for atomicity
+- **Build:** Updated `tsup.config.ts` externals from `sqlite3` to `better-sqlite3`
+
+</Update>
+
+<Update label="2026-02-17" description="v2.2.3">
+
+**New Features & Updates:**
+- **Memory Update:**
+  - Added `timestamp` parameter to `update()` — accepts Unix epoch or ISO 8601 string
+
+</Update>
+
+<Update label="2026-01-29" description="v2.2.2">
+
+**New Features & Updates:**
+- **Project Settings:**
+  - Added inclusion prompt, exclusion prompt, memory depth, and usecase setting
+
+</Update>
+
+<Update label="2025-12-30" description="v2.2.1">
+
+**Improvements:**
+- **Client:** Added support for keyword arguments in `add` and `search` methods, allowing additional properties beyond defined options for experimental features
+
+</Update>
+
+<Update label="2025-12-29" description="v2.2.0">
+
+**New Features:**
+- **Vector Stores:** Added Azure AI Search vector store support
+
+**Improvements:**
+- **Config:** Fixed embedder config schema to support `embeddingDims` and `url` parameters
+- **Graph Memory:** Replaced hardcoded LLM provider with provider from configuration
+
+**Bug Fixes:**
+- **Embedders:** Fixed hardcoded `embeddingDims` values in embedders (OpenAI, Ollama, Google, Azure)
+- **Build:** Fixed TypeScript build errors
+
+</Update>
+
+<Update label="2025-09-04" description="v2.1.38">
+**New Features:**
+- **Client:** Added `metadata` param to `update` method.
+</Update>
+
+<Update label="2025-08-04" description="v2.1.37">
+**New Features:**
+- **OSS:** Added `RedisCloud` search module check
+</Update>
+
 <Update label="2025-07-08" description="v2.1.36">
 **New Features:**
 - **Client:** Added `structured_data_schema` param to `add` method.
@@ -536,17 +880,17 @@ mode: "wide"
 </Update>
 
 <Update label="2025-06-24" description="v2.1.33">
-**Improvement :**
+**Improvement:**
 - **Client:** Added `immutable` param to `add` method.
 </Update>
 
 <Update label="2025-06-20" description="v2.1.32">
-**Improvement :**
+**Improvement:**
 - **Client:** Made `api_version` V2 as default.
 </Update>
 
 <Update label="2025-06-17" description="v2.1.31">
-**Improvement :**
+**Improvement:**
 - **Client:** Added param `filter_memories`.
 </Update>
 
@@ -572,7 +916,6 @@ mode: "wide"
 **Improvements:**
 - **OSS:** Added baseURL param in LLM Config.
 </Update>
-  
 <Update label="2025-05-23" description="v2.1.26">
 **Improvements:**
 - **Client:** Removed type `string` from `messages` interface
@@ -987,6 +1330,36 @@ mode: "wide"
 
 <Tab title="Vercel AI SDK">
 
+<Update label="2025-12-26" description="v2.0.5">
+**Bug Fix:**
+- **Vercel AI SDK:** Removed unnecessary dependencies to make the package lighter.
+</Update>
+
+<Update label="2025-09-25" description="v2.0.4">
+**Bug Fix:**
+- **Vercel AI SDK:** Fixed version parameter in the AI SDK to use V2 for addition.
+</Update>
+
+<Update label="2025-09-25" description="v2.0.3">
+**New Features:**
+- **Vercel AI SDK:** Added file support for multimodal capabilities with memory context
+</Update>
+
+<Update label="2025-09-03" description="v2.0.2">
+**Bug Fix:**
+- **Vercel AI SDK:** Fixed streaming response in the AI SDK.
+</Update>
+
+<Update label="2025-08-05" description="v2.0.1">
+**New Features:**
+- **Vercel AI SDK:** Added a new param `host` to the config.
+</Update>
+
+<Update label="2025-08-05" description="v2.0.0">
+**New Features:**
+- **Vercel AI SDK:** Migration to AI SDK V5.
+</Update>
+
 <Update label="2025-06-15" description="v1.0.6">
 **New Features:**
 - **Vercel AI SDK:** Added param `filter_memories`.
@@ -1004,7 +1377,7 @@ mode: "wide"
 
 <Update label="2025-05-08" description="v1.0.3">
 **Improvements:**
-- **Vercel AI SDK:** Added support for graceful failure in cases services are down. 
+- **Vercel AI SDK:** Added support for graceful failure in cases services are down.
 </Update>
 
 <Update label="2025-05-01" description="v1.0.1">

docs/components/embedders/config.mdx

@@ -1,10 +1,7 @@
 ---
 title: Configurations
-icon: "gear"
-iconType: "solid"
 ---
 
-<Snippet file="security-compliance.mdx" />
 
 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.
 

docs/components/embedders/models/aws_bedrock.mdx

@@ -41,7 +41,7 @@ config = {
 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": "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."}
 ]

docs/components/embedders/models/azure_openai.mdx

@@ -23,7 +23,7 @@ config = {
     "embedder": {
         "provider": "azure_openai",
         "config": {
-            "model": "text-embedding-3-large"
+            "model": "text-embedding-3-large",
             "azure_kwargs": {
                   "api_version": "",
                   "azure_deployment": "",
@@ -40,7 +40,7 @@ config = {
 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": "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."}
 ]
@@ -68,7 +68,7 @@ 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": "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."}
 ]
@@ -77,12 +77,60 @@ 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:
-
+<Tabs>
+<Tab title="Python">
 | Parameter | Description | Default Value |
 | --- | --- | --- |
 | `model` | The name of the embedding model to use | `text-embedding-3-small` |
 | `embedding_dims` | Dimensions of the embedding model | `1536` |
 | `azure_kwargs` | The Azure OpenAI configs | `config_keys` |
+</Tab>
+<Tab title="TypeScript">
+| Parameter         | Description                                   | Default Value              |
+| ----------------- | --------------------------------------------- | -------------------------- |
+| `model`           | The name of the embedding model to use        | `text-embedding-3-small`   |
+| `embeddingDims`   | Dimensions of the embedding model             | `1536`                     |
+| `apiKey`          | Azure OpenAI API key                          | `None`                     |
+| `modelProperties` | Object containing endpoint and other settings | `{ endpoint: "",...rest   }`|
+</Tab>
+</Tabs>

docs/components/embedders/models/gemini.mdx

@@ -1,43 +0,0 @@
----
-title: Gemini
----
-
-To use Gemini 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
-
-```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")
-```
-
-### 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 Gemini API key | `None` |

docs/components/embedders/models/google_AI.mdx

@@ -0,0 +1,79 @@
+---
+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 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: "gemini-embedding-001",
+        embeddingDims: 1536,
+      },
+    },
+};
+
+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 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:
+<Tabs>
+<Tab title="Python">
+| Parameter        | Description                          | Default Value           |
+| ---------------- | ------------------------------------ | ----------------------- |
+| `model`          | The name of the embedding model to use| `models/text-embedding-004` |
+| `embedding_dims` | Dimensions of the embedding model     | `1536`                  |
+| `api_key`        | The Google API key                   | `None`                  |
+</Tab>
+<Tab title="TypeScript">
+| Parameter         | Description                                   | Default Value              |
+| ----------------- | --------------------------------------------- | -------------------------- |
+| `model`           | The name of the embedding model to use        | `gemini-embedding-001`     |
+| `embeddingDims`   | Dimensions of the embedding model             | `1536`                     |
+| `apiKey`          | Google API key                                | `None`                     |
+</Tab>
+</Tabs>

docs/components/embedders/models/huggingface.mdx

@@ -24,7 +24,7 @@ config = {
 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": "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."}
 ]

docs/components/embedders/models/langchain.mdx

@@ -36,7 +36,7 @@ config = {
 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": "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."}
 ]
@@ -44,29 +44,33 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
 ```typescript TypeScript
-import { Memory } from "mem0ai";
+import { Memory } from 'mem0ai/oss';
 import { OpenAIEmbeddings } from "@langchain/openai";
 
-const embeddings = new OpenAIEmbeddings();
+// 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": embeddings
-        }
-    }
-}
+  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." }
+    {"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."}
 ]
-
-memory.add(messages, user_id="alice", metadata={"category": "movies"})
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
 ```
 </CodeGroup>
 
@@ -96,9 +100,10 @@ When using LangChain as an embedder provider, you'll need to:
 
 ### Examples with Different Providers
 
+<CodeGroup>
 #### HuggingFace Embeddings
 
-```python
+```python Python
 from langchain_huggingface import HuggingFaceEmbeddings
 
 # Initialize a HuggingFace embeddings model
@@ -117,9 +122,33 @@ config = {
 }
 ```
 
+```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 Python
 from langchain_ollama import OllamaEmbeddings
 
 # Initialize an Ollama embeddings model
@@ -137,6 +166,27 @@ config = {
 }
 ```
 
+```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>

docs/components/embedders/models/lmstudio.mdx

@@ -20,7 +20,7 @@ config = {
 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": "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."}
 ]
@@ -29,10 +29,10 @@ m.add(messages, user_id="john")
 
 ### Config
 
-Here are the parameters available for configuring Ollama embedder:
+Here are the parameters available for configuring LM Studio embedder:
 
 | Parameter | Description | Default Value |
 | --- | --- | --- |
-| `model` | The name of the OpenAI model to use | `nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf` |
+| `model` | The name of the LM Studio model to use | `nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf` |
 | `embedding_dims` | Dimensions of the embedding model | `1536` |
 | `lmstudio_base_url` | Base URL for LM Studio connection | `http://localhost:1234/v1` |

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
 
@@ -20,19 +21,54 @@ config = {
 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": "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="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 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` |
+| `embeddingDims` | Dimensions of the embedding model | 768
+</Tab>
+</Tabs>

docs/components/embedders/models/openai.mdx

@@ -25,7 +25,7 @@ config = {
 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": "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."}
 ]

docs/components/embedders/models/together.mdx

@@ -27,7 +27,7 @@ config = {
 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": "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."}
 ]

docs/components/embedders/models/vertexai.mdx

@@ -27,7 +27,7 @@ config = {
 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": "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."}
 ]

docs/components/embedders/overview.mdx

@@ -1,11 +1,7 @@
 ---
 title: Overview
-icon: "info"
-iconType: "solid"
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 Mem0 offers support for various embedding models, allowing users to choose the one that best suits their needs.
 
 ## Supported Embedders
@@ -21,7 +17,7 @@ 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>
@@ -31,6 +27,6 @@ See the list of supported embedders below.
 
 ## Usage
 
-To utilize a embedder, you must provide a configuration to customize its usage. If no configuration is supplied, a default configuration will be applied, and `OpenAI` will be used as the embedder.
+To utilize an embedding model, you must provide a configuration to customize its usage. If no configuration is supplied, a default configuration will be applied, and `OpenAI` will be used as the embedding model.
 
-For a comprehensive list of available parameters for embedder configuration, please refer to [Config](./config).
+For a comprehensive list of available parameters for embedding model configuration, please refer to [Config](./config).

docs/components/llms/config.mdx

@@ -1,11 +1,7 @@
 ---
 title: Configurations
-icon: "gear"
-iconType: "solid"
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 ## How to define configurations?
 
 <Tabs>
@@ -119,6 +115,7 @@ Here's a comprehensive list of all parameters that can be used across different
     | `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 +2,6 @@
 title: Anthropic
 ---
 
-<Snippet file="security-compliance.mdx" />
 
 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).
 
@@ -30,7 +29,7 @@ config = {
 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": "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."}
 ]
@@ -55,7 +54,7 @@ const config = {
 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": "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."}
 ]

docs/components/llms/models/aws_bedrock.mdx

@@ -2,8 +2,6 @@
 title: AWS Bedrock
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 ### Setup
 - Before using the AWS Bedrock LLM, make sure you have the appropriate model access from [Bedrock Console](https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/modelaccess).
 - You will also need to authenticate the `boto3` client by using a method in the [AWS documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html#configuring-credentials)
@@ -33,7 +31,7 @@ config = {
 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": "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."}
 ]

docs/components/llms/models/azure_openai.mdx

@@ -2,12 +2,12 @@
 title: Azure OpenAI
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 <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`
 
 
@@ -48,7 +48,7 @@ config = {
 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": "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."}
 ]
@@ -77,7 +77,7 @@ const config = {
 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": "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."}
 ]
@@ -118,6 +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/deepseek.mdx

@@ -2,8 +2,6 @@
 title: DeepSeek
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 To use DeepSeek LLM models, you have to set the `DEEPSEEK_API_KEY` environment variable. You can also optionally set `DEEPSEEK_API_BASE` if you need to use a different API endpoint (defaults to "https://api.deepseek.com").
 
 ## Usage
@@ -30,7 +28,7 @@ config = {
 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": "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."}
 ]

docs/components/llms/models/gemini.mdx

@@ -1,76 +0,0 @@
----
-title: Gemini
----
-
-<Snippet file="security-compliance.mdx" />
-
-To use the Gemini model, set the `GEMINI_API_KEY` environment variable. You can obtain the 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
-
-<CodeGroup>
-```python Python
-import os
-from mem0 import Memory
-
-os.environ["OPENAI_API_KEY"] = "your-openai-api-key"  # Used for embedding model
-os.environ["GEMINI_API_KEY"] = "your-gemini-api-key"
-
-config = {
-    "llm": {
-        "provider": "gemini",
-        "config": {
-            "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 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 `Gemini` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/google_AI.mdx

@@ -2,40 +2,73 @@
 title: Google AI
 ---
 
-<Snippet file="security-compliance.mdx" />
+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).
 
-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)
+> **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/groq.mdx

@@ -2,8 +2,6 @@
 title: Groq
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 [Groq](https://groq.com/) is the creator of the world's first Language Processing Unit (LPU), providing exceptional speed performance for AI workloads running on their LPU Inference Engine.
 
 In order to use LLMs from Groq, go to their [platform](https://console.groq.com/keys) and get the API key. Set the API key as `GROQ_API_KEY` environment variable to use the model as given below in the example.
@@ -32,7 +30,7 @@ config = {
 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": "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."}
 ]
@@ -57,7 +55,7 @@ const config = {
 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": "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."}
 ]

docs/components/llms/models/langchain.mdx

@@ -2,7 +2,6 @@
 title: LangChain
 ---
 
-<Snippet file="security-compliance.mdx" />
 
 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.
 
@@ -21,7 +20,7 @@ os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 # Initialize a LangChain model directly
 openai_model = ChatOpenAI(
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
     temperature=0.2,
     max_tokens=2000
 )
@@ -39,7 +38,7 @@ config = {
 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": "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."}
 ]
@@ -47,34 +46,34 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
 ```typescript TypeScript
-import { Memory } from "mem0ai";
+import { Memory } from 'mem0ai/oss';
 import { ChatOpenAI } from "@langchain/openai";
 
-const openai_model = new ChatOpenAI({
-    model: "gpt-4o",
+// Initialize a LangChain model directly
+const openaiModel = new ChatOpenAI({
+    modelName: "gpt-4",
     temperature: 0.2,
-    max_tokens: 2000
-})
+    maxTokens: 2000,
+    apiKey: process.env.OPENAI_API_KEY,
+});
 
 const config = {
-    "llm": {
-        "provider": "langchain",
-        "config": {
-            "model": openai_model
-        }
-    }
-}
+  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." }
+    {"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."}
 ]
-
-memory.add(messages, user_id="alice", metadata={"category": "movies"})
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
 ```
 </CodeGroup>
 

docs/components/llms/models/litellm.mdx

@@ -1,5 +1,3 @@
-<Snippet file="security-compliance.mdx" />
-
 [Litellm](https://litellm.vercel.app/docs/) is compatible with over 100 large language models (LLMs), all using a standardized input/output format. You can explore the [available models](https://litellm.vercel.app/docs/providers) to use with Litellm. Ensure you set the `API_KEY` for the model you choose to use.
 
 ## Usage
@@ -14,7 +12,7 @@ config = {
     "llm": {
         "provider": "litellm",
         "config": {
-            "model": "gpt-4o-mini",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }
@@ -24,7 +22,7 @@ config = {
 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": "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."}
 ]

docs/components/llms/models/lmstudio.mdx

@@ -2,8 +2,6 @@
 title: LM Studio
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 To use LM Studio with Mem0, you'll need to have LM Studio running locally with its server enabled. LM Studio provides a way to run local LLMs with an OpenAI-compatible API.
 
 ## Usage
@@ -31,7 +29,7 @@ config = {
 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": "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."}
 ]
@@ -59,7 +57,7 @@ config = {
 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": "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."}
 ]

docs/components/llms/models/mistral_AI.mdx

@@ -2,8 +2,6 @@
 title: Mistral AI
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 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
@@ -30,7 +28,7 @@ config = {
 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": "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."}
 ]
@@ -55,7 +53,7 @@ const config = {
 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": "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."}
 ]

docs/components/llms/models/ollama.mdx

@@ -1,10 +1,13 @@
-<Snippet file="security-compliance.mdx" />
+---
+title: Ollama
+---
 
-You can use LLMs from Ollama to run Mem0 locally. These [models](https://ollama.com/search?c=tools) support tool support.
+You can use LLMs from Ollama to run Mem0 locally. These [models](https://ollama.com/search?c=tools) support tool calling.
 
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -24,13 +27,38 @@ config = {
 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": "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"})
 ```
 
+```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 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

@@ -2,10 +2,10 @@
 title: OpenAI
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 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>
@@ -19,7 +19,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }
@@ -40,7 +40,7 @@ config = {
 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": "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."}
 ]
@@ -65,7 +65,7 @@ const config = {
 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": "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."}
 ]
@@ -85,7 +85,7 @@ config = {
     "llm": {
         "provider": "openai_structured",
         "config": {
-            "model": "gpt-4o-2024-08-06",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.0,
         }
     }

docs/components/llms/models/sarvam.mdx

@@ -2,8 +2,6 @@
 title: Sarvam AI
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 **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/).
@@ -30,7 +28,7 @@ config = {
 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": "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."}
 ]

docs/components/llms/models/together.mdx

@@ -1,6 +1,8 @@
-<Snippet file="security-compliance.mdx" />
+---
+title: Together
+---
 
-To use TogetherAI LLM models, you have to set the `TOGETHER_API_KEY` environment variable. You can obtain the TogetherAI API key from their [Account settings page](https://api.together.xyz/settings/api-keys).
+To use Together LLM models, you have to set the `TOGETHER_API_KEY` environment variable. You can obtain the Together API key from their [Account settings page](https://api.together.xyz/settings/api-keys).
 
 ## Usage
 
@@ -25,7 +27,7 @@ config = {
 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": "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."}
 ]
@@ -34,4 +36,4 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
 
 ## Config
 
-All available parameters for the `togetherai` config are present in [Master List of All Params in Config](../config).
+All available parameters for the `together` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/vllm.mdx

@@ -2,8 +2,6 @@
 title: vLLM
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 [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

docs/components/llms/models/xAI.mdx

@@ -2,8 +2,6 @@
 title: xAI
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 [xAI](https://x.ai/) is a new AI company founded by Elon Musk that develops large language models, including Grok. Grok is trained on real-time data from X (formerly Twitter) and aims to provide accurate, up-to-date responses with a touch of wit and humor.
 
 In order to use LLMs from xAI, go to their [platform](https://console.x.ai) and get the API key. Set the API key as `XAI_API_KEY` environment variable to use the model as given below in the example.
@@ -31,7 +29,7 @@ config = {
 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": "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."}
 ]

docs/components/llms/overview.mdx

@@ -1,11 +1,7 @@
 ---
 title: Overview
-icon: "info"
-iconType: "solid"
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 Mem0 includes built-in support for various popular large language models. Memory can utilize the LLM provided by the user, ensuring efficient use for specific needs.
 
 ## Usage
@@ -30,10 +26,9 @@ See the list of supported LLMs below.
   <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" />

docs/components/rerankers/config.mdx

@@ -0,0 +1,105 @@
+---
+title: Config
+description: "Configuration options for rerankers in Mem0"
+---
+
+## Common Configuration Parameters
+
+All rerankers share these common configuration parameters:
+
+| Parameter  | Description                                         | Type  | Default  |
+| ---------- | --------------------------------------------------- | ----- | -------- |
+| `provider` | Reranker provider name                              | `str` | Required |
+| `top_k`    | Maximum number of results to return after reranking | `int` | `None`   |
+| `api_key`  | API key for the reranker service                    | `str` | `None`   |
+
+## Provider-Specific Configuration
+
+### Zero Entropy
+
+| Parameter | Description                                  | Type  | Default      |
+| --------- | -------------------------------------------- | ----- | ------------ |
+| `model`   | Model to use: `zerank-1` or `zerank-1-small` | `str` | `"zerank-1"` |
+| `api_key` | Zero Entropy API key                         | `str` | `None`       |
+
+### Cohere
+
+| Parameter            | Description                                  | Type   | Default                 |
+| -------------------- | -------------------------------------------- | ------ | ----------------------- |
+| `model`              | Cohere rerank model                          | `str`  | `"rerank-english-v3.0"` |
+| `api_key`            | Cohere API key                               | `str`  | `None`                  |
+| `return_documents`   | Whether to return document texts in response | `bool` | `False`                 |
+| `max_chunks_per_doc` | Maximum chunks per document                  | `int`  | `None`                  |
+
+### Sentence Transformer
+
+| Parameter           | Description                                  | Type   | Default                                  |
+| ------------------- | -------------------------------------------- | ------ | ---------------------------------------- |
+| `model`             | HuggingFace cross-encoder model name         | `str`  | `"cross-encoder/ms-marco-MiniLM-L-6-v2"` |
+| `device`            | Device to run model on (`cpu`, `cuda`, etc.) | `str`  | `None`                                   |
+| `batch_size`        | Batch size for processing                    | `int`  | `32`                                     |
+| `show_progress_bar` | Show progress during processing              | `bool` | `False`                                  |
+
+### Hugging Face
+
+| Parameter | Description                                  | Type  | Default                     |
+| --------- | -------------------------------------------- | ----- | --------------------------- |
+| `model`   | HuggingFace reranker model name              | `str` | `"BAAI/bge-reranker-large"` |
+| `api_key` | HuggingFace API token                        | `str` | `None`                      |
+| `device`  | Device to run model on (`cpu`, `cuda`, etc.) | `str` | `None`                      |
+
+### LLM-based
+
+| Parameter        | Description                                | Type    | Default                |
+| ---------------- | ------------------------------------------ | ------- | ---------------------- |
+| `model`          | LLM model to use for scoring               | `str`   | `"gpt-4o-mini"`        |
+| `provider`       | LLM provider (`openai`, `anthropic`, etc.) | `str`   | `"openai"`             |
+| `api_key`        | API key for LLM provider                   | `str`   | `None`                 |
+| `temperature`    | Temperature for LLM generation             | `float` | `0.0`                  |
+| `max_tokens`     | Maximum tokens for LLM response            | `int`   | `100`                  |
+| `scoring_prompt` | Custom prompt template for scoring         | `str`   | Default scoring prompt |
+
+### LLM Reranker
+
+| Parameter      | Description                 | Type   | Default  |
+| -------------- | --------------------------- | ------ | -------- |
+| `llm.provider` | LLM provider for reranking  | `str`  | Required |
+| `llm.config`   | LLM configuration object    | `dict` | Required |
+| `top_n`        | Number of results to return | `int`  | `None`   |
+
+## Environment Variables
+
+You can set API keys using environment variables:
+
+- `ZERO_ENTROPY_API_KEY` - Zero Entropy API key
+- `COHERE_API_KEY` - Cohere API key
+- `HUGGINGFACE_API_KEY` - HuggingFace API token
+- `OPENAI_API_KEY` - OpenAI API key (for LLM-based reranker)
+- `ANTHROPIC_API_KEY` - Anthropic API key (for LLM-based reranker)
+
+## Basic Configuration Example
+
+```python Python
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "my_memories",
+            "path": "./chroma_db"
+        }
+    },
+    "llm": {
+        "provider": "openai",
+        "config": {
+            "model": "gpt-4.1-nano-2025-04-14"
+        }
+    },
+    "reranker": {
+        "provider": "zero_entropy",
+        "config": {
+            "model": "zerank-1",
+            "top_k": 5
+        }
+    }
+}
+```

docs/components/rerankers/custom-prompts.mdx

@@ -0,0 +1,220 @@
+---
+title: Custom Prompts
+---
+
+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-4.1-nano-2025-04-14",
+                    "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 +1,145 @@
+---
+title: Cohere
+description: "Reranking with Cohere"
+---
+
+Cohere provides enterprise-grade reranking models with excellent multilingual support and production-ready performance.
+
+## Models
+
+Cohere offers several reranking models:
+
+- **`rerank-english-v3.0`**: Latest English reranker with best performance
+- **`rerank-multilingual-v3.0`**: Multilingual support for global applications
+- **`rerank-english-v2.0`**: Previous generation English reranker
+
+## Installation
+
+```bash
+pip install cohere
+```
+
+## Configuration
+
+```python Python
+from mem0 import Memory
+
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "my_memories",
+            "path": "./chroma_db"
+        }
+    },
+    "llm": {
+        "provider": "openai",
+        "config": {
+            "model": "gpt-4.1-nano-2025-04-14"
+        }
+    },
+    "reranker": {
+        "provider": "cohere",
+        "config": {
+            "model": "rerank-english-v3.0",
+            "api_key": "your-cohere-api-key",  # or set COHERE_API_KEY
+            "top_k": 5,
+            "return_documents": False,
+            "max_chunks_per_doc": None
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+```
+
+## Environment Variables
+
+Set your API key as an environment variable:
+
+```bash
+export COHERE_API_KEY="your-api-key"
+```
+
+## Usage Example
+
+```python Python
+import os
+from mem0 import Memory
+
+# Set API key
+os.environ["COHERE_API_KEY"] = "your-api-key"
+
+# Initialize memory with Cohere reranker
+config = {
+    "vector_store": {"provider": "chroma"},
+    "llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+    "rerank": {
+        "provider": "cohere",
+        "config": {
+            "model": "rerank-english-v3.0",
+            "top_k": 3
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+
+# Add memories
+messages = [
+    {"role": "user", "content": "I work as a data scientist at Microsoft"},
+    {"role": "user", "content": "I specialize in machine learning and NLP"},
+    {"role": "user", "content": "I enjoy playing tennis on weekends"}
+]
+
+memory.add(messages, user_id="bob")
+
+# Search with reranking
+results = memory.search("What is the user's profession?", user_id="bob")
+
+for result in results['results']:
+    print(f"Memory: {result['memory']}")
+    print(f"Vector Score: {result['score']:.3f}")
+    print(f"Rerank Score: {result['rerank_score']:.3f}")
+    print()
+```
+
+## Multilingual Support
+
+For multilingual applications, use the multilingual model:
+
+```python Python
+config = {
+    "rerank": {
+        "provider": "cohere",
+        "config": {
+            "model": "rerank-multilingual-v3.0",
+            "top_k": 5
+        }
+    }
+}
+```
+
+## Configuration Parameters
+
+| Parameter            | Description                      | Type   | Default                 |
+| -------------------- | -------------------------------- | ------ | ----------------------- |
+| `model`              | Cohere rerank model to use       | `str`  | `"rerank-english-v3.0"` |
+| `api_key`            | Cohere API key                   | `str`  | `None`                  |
+| `top_k`              | Maximum documents to return      | `int`  | `None`                  |
+| `return_documents`   | Whether to return document texts | `bool` | `False`                 |
+| `max_chunks_per_doc` | Maximum chunks per document      | `int`  | `None`                  |
+
+## Features
+
+- **High Quality**: Enterprise-grade relevance scoring
+- **Multilingual**: Support for 100+ languages
+- **Scalable**: Production-ready with high throughput
+- **Reliable**: SLA-backed service with 99.9% uptime
+
+## Best Practices
+
+1. **Model Selection**: Use `rerank-english-v3.0` for English, `rerank-multilingual-v3.0` for other languages
+2. **Batch Processing**: Process multiple queries efficiently
+3. **Error Handling**: Implement retry logic for production systems
+4. **Monitoring**: Track reranking performance and costs

docs/components/rerankers/models/huggingface.mdx

@@ -0,0 +1,350 @@
+---
+title: Hugging Face Reranker
+description: 'Access thousands of reranking models from Hugging Face Hub'
+---
+
+## 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.mdx

@@ -0,0 +1,226 @@
+---
+title: LLM as Reranker
+description: 'Flexible reranking using LLMs'
+---
+
+<Warning>
+**This page has been superseded.** Please see [LLM Reranker](/components/rerankers/models/llm_reranker) for the complete and up-to-date documentation on using LLMs for reranking.
+</Warning>
+
+LLM-based reranker provides maximum flexibility by using any Large Language Model to score document relevance. This approach allows for custom prompts and domain-specific scoring logic.
+
+## Supported LLM Providers
+
+Any LLM provider supported by Mem0 can be used for reranking:
+
+- **OpenAI**: GPT-4, GPT-3.5-turbo, etc.
+- **Anthropic**: Claude models
+- **Together**: Open-source models
+- **Groq**: Fast inference
+- **Ollama**: Local models
+- And more...
+
+## Configuration
+
+```python Python
+from mem0 import Memory
+
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "my_memories",
+            "path": "./chroma_db"
+        }
+    },
+    "llm": {
+        "provider": "openai",
+        "config": {
+            "model": "gpt-4o-mini"
+        }
+    },
+    "reranker": {
+        "provider": "llm",
+        "config": {
+            "model": "gpt-4o-mini",
+            "provider": "openai",
+            "api_key": "your-openai-api-key",  # or set OPENAI_API_KEY
+            "top_k": 5,
+            "temperature": 0.0
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+```
+
+## Custom Scoring Prompt
+
+You can provide a custom prompt for relevance scoring:
+
+```python Python
+custom_prompt = """You are a relevance scoring assistant. Rate how well this document answers the query.
+
+Query: "{query}"
+Document: "{document}"
+
+Score from 0.0 to 1.0 where:
+- 1.0: Perfect match, directly answers the query
+- 0.8-0.9: Highly relevant, good match  
+- 0.6-0.7: Moderately relevant, partial match
+- 0.4-0.5: Slightly relevant, limited useful information
+- 0.0-0.3: Not relevant or no useful information
+
+Provide only a single numerical score between 0.0 and 1.0."""
+
+config["reranker"]["config"]["scoring_prompt"] = custom_prompt
+```
+
+## Usage Example
+
+```python Python
+import os
+from mem0 import Memory
+
+# Set API key
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+
+# Initialize memory with LLM reranker
+config = {
+    "vector_store": {"provider": "chroma"},
+    "llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+    "reranker": {
+        "provider": "llm",
+        "config": {
+            "model": "gpt-4o-mini",
+            "provider": "openai",
+            "temperature": 0.0
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+
+# Add memories
+messages = [
+    {"role": "user", "content": "I'm learning Python programming"},
+    {"role": "user", "content": "I find object-oriented programming challenging"}, 
+    {"role": "user", "content": "I love hiking in national parks"}
+]
+
+memory.add(messages, user_id="david")
+
+# Search with LLM reranking
+results = memory.search("What programming topics is the user studying?", user_id="david")
+
+for result in results['results']:
+    print(f"Memory: {result['memory']}")
+    print(f"Vector Score: {result['score']:.3f}")
+    print(f"Rerank Score: {result['rerank_score']:.3f}")
+    print()
+```
+
+```text Output
+Memory: I'm learning Python programming
+Vector Score: 0.856
+Rerank Score: 0.920
+
+Memory: I find object-oriented programming challenging
+Vector Score: 0.782
+Rerank Score: 0.850
+```
+
+## Domain-Specific Scoring
+
+Create specialized scoring for your domain:
+
+```python Python
+medical_prompt = """You are a medical relevance expert. Score how relevant this medical record is to the clinical query.
+
+Clinical Query: "{query}"
+Medical Record: "{document}"
+
+Consider:
+- Clinical relevance and accuracy
+- Patient safety implications
+- Diagnostic value
+- Treatment relevance
+
+Score from 0.0 to 1.0. Provide only the numerical score."""
+
+config = {
+    "reranker": {
+        "provider": "llm",
+        "config": {
+            "model": "gpt-4o-mini",
+            "provider": "openai",
+            "scoring_prompt": medical_prompt,
+            "temperature": 0.0
+        }
+    }
+}
+```
+
+## Multiple LLM Providers
+
+Use different LLM providers for reranking:
+
+```python Python
+# Using Anthropic Claude
+anthropic_config = {
+    "reranker": {
+        "provider": "llm",
+        "config": {
+            "model": "claude-3-haiku-20240307",
+            "provider": "anthropic",
+            "temperature": 0.0
+        }
+    }
+}
+
+# Using local Ollama model
+ollama_config = {
+    "reranker": {
+        "provider": "llm",
+        "config": {
+            "model": "llama2:7b",
+            "provider": "ollama",
+            "temperature": 0.0
+        }
+    }
+}
+```
+
+## Configuration Parameters
+
+| Parameter | Description | Type | Default |
+|-----------|-------------|------|---------|
+| `model` | LLM model to use for scoring | `str` | `"gpt-4o-mini"` |
+| `provider` | LLM provider name | `str` | `"openai"` |
+| `api_key` | API key for the LLM provider | `str` | `None` |
+| `top_k` | Maximum documents to return | `int` | `None` |
+| `temperature` | Temperature for LLM generation | `float` | `0.0` |
+| `max_tokens` | Maximum tokens for LLM response | `int` | `100` |
+| `scoring_prompt` | Custom prompt template | `str` | Default prompt |
+
+## Advantages
+
+- **Maximum Flexibility**: Custom prompts for any use case
+- **Domain Expertise**: Leverage LLM knowledge for specialized domains
+- **Interpretability**: Understand scoring through prompt engineering
+- **Multi-criteria**: Score based on multiple relevance factors
+
+## Considerations
+
+- **Latency**: Higher latency than specialized rerankers
+- **Cost**: LLM API costs per reranking operation
+- **Consistency**: May have slight variations in scoring
+- **Prompt Engineering**: Requires careful prompt design
+
+## Best Practices
+
+1. **Temperature**: Use 0.0 for consistent scoring
+2. **Prompt Design**: Be specific about scoring criteria
+3. **Token Efficiency**: Keep prompts concise to reduce costs
+4. **Caching**: Cache results for repeated queries when possible
+5. **Fallback**: Handle API errors gracefully

docs/components/rerankers/models/llm_reranker.mdx

@@ -0,0 +1,489 @@
+---
+title: LLM Reranker
+description: 'Use any language model as a reranker with custom prompts'
+---
+
+## 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 +1,159 @@
+---
+title: Sentence Transformer
+description: 'Local reranking with HuggingFace cross-encoder models'
+---
+
+Sentence Transformer reranker provides local reranking using HuggingFace cross-encoder models, perfect for privacy-focused deployments where you want to keep data on-premises.
+
+## Models
+
+Any HuggingFace cross-encoder model can be used. Popular choices include:
+
+- **`cross-encoder/ms-marco-MiniLM-L-6-v2`**: Default, good balance of speed and accuracy
+- **`cross-encoder/ms-marco-TinyBERT-L-2-v2`**: Fastest, smaller model size
+- **`cross-encoder/ms-marco-electra-base`**: Higher accuracy, larger model
+- **`cross-encoder/stsb-distilroberta-base`**: Good for semantic similarity tasks
+
+## Installation
+
+```bash
+pip install sentence-transformers
+```
+
+## Configuration
+
+```python Python
+from mem0 import Memory
+
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "my_memories",
+            "path": "./chroma_db"
+        }
+    },
+    "llm": {
+        "provider": "openai",
+        "config": {
+            "model": "gpt-4o-mini"
+        }
+    },
+    "rerank": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "device": "cpu",  # or "cuda" for GPU
+            "batch_size": 32,
+            "show_progress_bar": False,
+            "top_k": 5
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+```
+
+## GPU Acceleration
+
+For better performance, use GPU acceleration:
+
+```python Python
+config = {
+    "rerank": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "device": "cuda",  # Use GPU
+            "batch_size": 64   # high batch size for high memory GPUs
+        }
+    }
+}
+```
+
+## Usage Example
+
+```python Python
+from mem0 import Memory
+
+# Initialize memory with local reranker
+config = {
+    "vector_store": {"provider": "chroma"},
+    "llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+    "rerank": {
+        "provider": "sentence_transformer",
+        "config": {
+            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
+            "device": "cpu"
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+
+# Add memories
+messages = [
+    {"role": "user", "content": "I love reading science fiction novels"},
+    {"role": "user", "content": "My favorite author is Isaac Asimov"},
+    {"role": "user", "content": "I also enjoy watching sci-fi movies"}
+]
+
+memory.add(messages, user_id="charlie")
+
+# Search with local reranking
+results = memory.search("What books does the user like?", user_id="charlie")
+
+for result in results['results']:
+    print(f"Memory: {result['memory']}")
+    print(f"Vector Score: {result['score']:.3f}")
+    print(f"Rerank Score: {result['rerank_score']:.3f}")
+    print()
+```
+
+## Custom Models
+
+You can use any HuggingFace cross-encoder model:
+
+```python Python
+# Using a different model
+config = {
+    "rerank": {
+        "provider": "sentence_transformer", 
+        "config": {
+            "model": "cross-encoder/stsb-distilroberta-base",
+            "device": "cpu"
+        }
+    }
+}
+```
+
+## Configuration Parameters
+
+| Parameter | Description | Type | Default |
+|-----------|-------------|------|---------|
+| `model` | HuggingFace cross-encoder model name | `str` | `"cross-encoder/ms-marco-MiniLM-L-6-v2"` |
+| `device` | Device to run model on (`cpu`, `cuda`, etc.) | `str` | `None` |
+| `batch_size` | Batch size for processing documents | `int` | `32` |
+| `show_progress_bar` | Show progress bar during processing | `bool` | `False` |
+| `top_k` | Maximum documents to return | `int` | `None` |
+
+## Advantages
+
+- **Privacy**: Complete local processing, no external API calls
+- **Cost**: No per-token charges after initial model download
+- **Customization**: Use any HuggingFace cross-encoder model
+- **Offline**: Works without internet connection after model download
+
+## Performance Considerations
+
+- **First Run**: Model download may take time initially
+- **Memory Usage**: Models require GPU/CPU memory
+- **Batch Size**: Optimize batch size based on available memory
+- **Device**: GPU acceleration significantly improves speed
+
+## Best Practices
+
+1. **Model Selection**: Choose model based on accuracy vs speed requirements
+2. **Device Management**: Use GPU when available for better performance
+3. **Batch Processing**: Process multiple documents together for efficiency
+4. **Memory Monitoring**: Monitor system memory usage with larger models

docs/components/rerankers/models/zero_entropy.mdx

@@ -0,0 +1,117 @@
+---
+title: Zero Entropy
+description: 'Neural reranking with Zero Entropy'
+---
+
+[Zero Entropy](https://www.zeroentropy.dev) provides neural reranking models that significantly improve search relevance with fast performance.
+
+## Models
+
+Zero Entropy offers two reranking models:
+
+- **`zerank-1`**: Flagship state-of-the-art reranker (non-commercial license)
+- **`zerank-1-small`**: Open-source model (Apache 2.0 license)
+
+## Installation
+
+```bash
+pip install zeroentropy
+```
+
+## Configuration
+
+```python Python
+from mem0 import Memory
+
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "my_memories",
+            "path": "./chroma_db"
+        }
+    },
+    "llm": {
+        "provider": "openai",
+        "config": {
+            "model": "gpt-4o-mini"
+        }
+    },
+    "rerank": {
+        "provider": "zero_entropy",
+        "config": {
+            "model": "zerank-1",  # or "zerank-1-small"
+            "api_key": "your-zero-entropy-api-key",  # or set ZERO_ENTROPY_API_KEY
+            "top_k": 5
+        }
+    }
+}
+
+memory = Memory.from_config(config)
+```
+
+## Environment Variables
+
+Set your API key as an environment variable:
+
+```bash
+export ZERO_ENTROPY_API_KEY="your-api-key"
+```
+
+## Usage Example
+
+```python Python
+import os
+from mem0 import Memory
+
+# Set API key
+os.environ["ZERO_ENTROPY_API_KEY"] = "your-api-key"
+
+# Initialize memory with Zero Entropy reranker
+config = {
+    "vector_store": {"provider": "chroma"},
+    "llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
+    "rerank": {"provider": "zero_entropy", "config": {"model": "zerank-1"}}
+}
+
+memory = Memory.from_config(config)
+
+# Add memories
+messages = [
+    {"role": "user", "content": "I love Italian pasta, especially carbonara"},
+    {"role": "user", "content": "Japanese sushi is also amazing"},
+    {"role": "user", "content": "I enjoy cooking Mediterranean dishes"}
+]
+
+memory.add(messages, user_id="alice")
+
+# Search with reranking
+results = memory.search("What Italian food does the user like?", user_id="alice")
+
+for result in results['results']:
+    print(f"Memory: {result['memory']}")
+    print(f"Vector Score: {result['score']:.3f}")
+    print(f"Rerank Score: {result['rerank_score']:.3f}")
+    print()
+```
+
+## Configuration Parameters
+
+| Parameter | Description | Type | Default |
+|-----------|-------------|------|---------|
+| `model` | Model to use: `"zerank-1"` or `"zerank-1-small"` | `str` | `"zerank-1"` |
+| `api_key` | Zero Entropy API key | `str` | `None` |
+| `top_k` | Maximum documents to return after reranking | `int` | `None` |
+
+## Performance
+
+- **Fast**: Optimized neural architecture for low latency
+- **Accurate**: State-of-the-art relevance scoring
+- **Cost-effective**: ~$0.025/1M tokens processed
+
+## Best Practices
+
+1. **Model Selection**: Use `zerank-1` for best quality, `zerank-1-small` for faster processing
+2. **Batch Size**: Process multiple queries together when possible
+3. **Top-k Limiting**: Set reasonable `top_k` values (5-20) for best performance
+4. **API Key Management**: Use environment variables for secure key storage

docs/components/rerankers/optimization.mdx

@@ -0,0 +1,310 @@
+---
+title: Performance Optimization
+---
+
+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 +1,78 @@
+---
+title: Overview
+description: 'Pick the right reranker path to boost Mem0 search relevance.'
+---
+
+Mem0 rerankers rescore vector search hits so your agents surface the most relevant memories. Use this hub to decide when reranking helps, configure a provider, and fine-tune performance.
+
+<Info>
+Reranking trades extra latency for better precision. Start once you have baseline search working and measure before/after relevance.
+</Info>
+
+<CardGroup cols={3}>
+  <Card
+    title="Understand Reranking"
+    description="See how reranker-enhanced search changes your retrieval flow."
+    icon="search"
+    href="/open-source/features/reranker-search"
+  />
+  <Card
+    title="Configure Providers"
+    description="Add reranker blocks to your memory configuration."
+    icon="settings"
+    href="/components/rerankers/config"
+  />
+  <Card
+    title="Optimize Performance"
+    description="Balance relevance, latency, and cost with tuning tactics."
+    icon="speedometer"
+    href="/components/rerankers/optimization"
+  />
+  <Card
+    title="Custom Prompts"
+    description="Shape LLM-based reranking with tailored instructions."
+    icon="code"
+    href="/components/rerankers/custom-prompts"
+  />
+  <Card
+    title="Zero Entropy Guide"
+    description="Adopt the managed neural reranker for production workloads."
+    icon="sparkles"
+    href="/components/rerankers/models/zero_entropy"
+  />
+  <Card
+    title="Sentence Transformers"
+    description="Keep reranking on-device with cross-encoder models."
+    icon="cpu"
+    href="/components/rerankers/models/sentence_transformer"
+  />
+</CardGroup>
+
+## Picking the Right Reranker
+
+- **API-first** when you need top quality and can absorb request costs (Cohere, Zero Entropy).  
+- **Self-hosted** for privacy-sensitive deployments that must stay on your hardware (Sentence Transformer, Hugging Face).  
+- **LLM-driven** when you need bespoke scoring logic or complex prompts.  
+- **Hybrid** by enabling reranking only on premium journeys to control spend.
+
+## Implementation Checklist
+
+1. Confirm baseline search KPIs so you can measure uplift.  
+2. Select a provider and add the `reranker` block to your config.  
+3. Test latency impact with production-like query batches.  
+4. Decide whether to enable reranking globally or per-search via the `rerank` flag.
+
+<CardGroup cols={2}>
+  <Card
+    title="Set Up Reranking"
+    description="Walk through the configuration fields and defaults."
+    icon="settings"
+    href="/components/rerankers/config"
+  />
+  <Card
+    title="Example: Reranker Search"
+    description="Follow the feature guide to see reranking in action."
+    icon="rocket"
+    href="/open-source/features/reranker-search"
+  />
+</CardGroup>

docs/components/vectordbs/config.mdx

@@ -1,16 +1,12 @@
 ---
 title: Configurations
-icon: "gear"
-iconType: "solid"
 ---
 
-<Snippet file="security-compliance.mdx" />
-
 ## How to define configurations?
 
 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", "upstash_vector", "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

@@ -16,8 +16,8 @@ config = {
     "vector_store": {
         "provider": "azure_ai_search",
         "config": {
-            "service_name": "ai-search-test",
-            "api_key": "*****",
+            "service_name": "<your-azure-ai-search-service-name>",
+            "api_key": "<your-api-key>",
             "collection_name": "mem0", 
             "embedding_model_dims": 1536
         }
@@ -27,7 +27,7 @@ config = {
 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": "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."}
 ]
@@ -41,8 +41,8 @@ config = {
     "vector_store": {
         "provider": "azure_ai_search",
         "config": {
-            "service_name": "ai-search-test",
-            "api_key": "*****",
+            "service_name": "<your-azure-ai-search-service-name>",
+            "api_key": "<your-api-key>",
             "collection_name": "mem0", 
             "embedding_model_dims": 1536,
             "compression_type": "binary",
@@ -59,8 +59,8 @@ config = {
     "vector_store": {
         "provider": "azure_ai_search",
         "config": {
-            "service_name": "ai-search-test",
-            "api_key": "*****",
+            "service_name": "<your-azure-ai-search-service-name>",
+            "api_key": "<your-api-key>",
             "collection_name": "mem0", 
             "embedding_model_dims": 1536,
             "hybrid_search": True,
@@ -70,12 +70,92 @@ config = {
 }
 ```
 
+## 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 Principal 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 an 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 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 for 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 | 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` |

docs/components/vectordbs/dbs/azure_mysql.mdx

@@ -0,0 +1,128 @@
+---
+title: Azure MySQL
+---
+
+[Azure Database for MySQL](https://azure.microsoft.com/products/mysql) is a fully managed relational database service that provides enterprise-grade reliability and security. It supports JSON-based vector storage for semantic search capabilities in AI applications.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "azure_mysql",
+        "config": {
+            "host": "your-server.mysql.database.azure.com",
+            "port": 3306,
+            "user": "your_username",
+            "password": "your_password",
+            "database": "mem0_db",
+            "collection_name": "memories",
+        }
+    }
+}
+
+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"})
+```
+
+#### Using Azure Managed Identity
+
+For production deployments, use Azure Managed Identity instead of passwords:
+
+```python
+config = {
+    "vector_store": {
+        "provider": "azure_mysql",
+        "config": {
+            "host": "your-server.mysql.database.azure.com",
+            "user": "your_username",
+            "database": "mem0_db",
+            "collection_name": "memories",
+            "use_azure_credential": True,  # Uses DefaultAzureCredential
+            "ssl_disabled": False
+        }
+    }
+}
+```
+
+<Note>
+When `use_azure_credential` is enabled, the password is obtained via Azure DefaultAzureCredential (supports Managed Identity, Azure CLI, etc.)
+</Note>
+
+### Config
+
+Here are the parameters available for configuring Azure MySQL:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `host` | MySQL server hostname | Required |
+| `port` | MySQL server port | `3306` |
+| `user` | Database user | Required |
+| `password` | Database password (optional with Azure credential) | `None` |
+| `database` | Database name | Required |
+| `collection_name` | Table name for storing vectors | `"mem0"` |
+| `embedding_model_dims` | Dimensions of embedding vectors | `1536` |
+| `use_azure_credential` | Use Azure DefaultAzureCredential | `False` |
+| `ssl_ca` | Path to SSL CA certificate | `None` |
+| `ssl_disabled` | Disable SSL (not recommended) | `False` |
+| `minconn` | Minimum connections in pool | `1` |
+| `maxconn` | Maximum connections in pool | `5` |
+
+### Setup
+
+#### Create MySQL Flexible Server using Azure CLI:
+
+```bash
+# Create resource group
+az group create --name mem0-rg --location eastus
+
+# Create MySQL Flexible Server
+az mysql flexible-server create \
+    --resource-group mem0-rg \
+    --name mem0-mysql-server \
+    --location eastus \
+    --admin-user myadmin \
+    --admin-password <YourPassword> \
+    --version 8.0.21
+
+# Create database
+az mysql flexible-server db create \
+    --resource-group mem0-rg \
+    --server-name mem0-mysql-server \
+    --database-name mem0_db
+
+# Configure firewall
+az mysql flexible-server firewall-rule create \
+    --resource-group mem0-rg \
+    --name mem0-mysql-server \
+    --rule-name AllowMyIP \
+    --start-ip-address <YourIP> \
+    --end-ip-address <YourIP>
+```
+
+#### Enable Azure AD Authentication:
+
+1. In Azure Portal, navigate to your MySQL Flexible Server
+2. Go to **Security** > **Authentication** and enable Azure AD
+3. Add your application's managed identity as a MySQL user:
+
+```sql
+CREATE AADUSER 'your-app-identity' IDENTIFIED BY 'your-client-id';
+GRANT ALL PRIVILEGES ON mem0_db.* TO 'your-app-identity'@'%';
+FLUSH PRIVILEGES;
+```
+
+<Tip>
+For production, use [Managed Identity](https://learn.microsoft.com/azure/active-directory/managed-identities-azure-resources/) to eliminate password management.
+</Tip>

docs/components/vectordbs/dbs/baidu.mdx

@@ -37,7 +37,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
 
 ### Config
 
-Here are the available parameters for the `mochow` config:
+Here are the parameters available for configuring Baidu VectorDB:
 
 | Parameter | Description | Default Value |
 | --- | --- | --- |

docs/components/vectordbs/dbs/cassandra.mdx

@@ -0,0 +1,181 @@
+---
+title: Apache Cassandra
+---
+
+[Apache Cassandra](https://cassandra.apache.org/) is a highly scalable, distributed NoSQL database designed for handling large amounts of data across many commodity servers with no single point of failure. It supports vector storage for semantic search capabilities in AI applications and can scale to massive datasets with linear performance improvements.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "cassandra",
+        "config": {
+            "contact_points": ["127.0.0.1"],
+            "port": 9042,
+            "username": "cassandra",
+            "password": "cassandra",
+            "keyspace": "mem0",
+            "collection_name": "memories",
+        }
+    }
+}
+
+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"})
+```
+
+#### Using DataStax Astra DB
+
+For managed Cassandra with DataStax Astra DB:
+
+```python
+config = {
+    "vector_store": {
+        "provider": "cassandra",
+        "config": {
+            "contact_points": ["dummy"],  # Not used with secure connect bundle
+            "username": "token",
+            "password": "AstraCS:...",  # Your Astra DB application token
+            "keyspace": "mem0",
+            "collection_name": "memories",
+            "secure_connect_bundle": "/path/to/secure-connect-bundle.zip"
+        }
+    }
+}
+```
+
+<Note>
+When using DataStax Astra DB, provide the secure connect bundle path. The contact_points parameter is ignored when a secure connect bundle is provided.
+</Note>
+
+### Config
+
+Here are the parameters available for configuring Apache Cassandra:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `contact_points` | List of contact point IP addresses | Required |
+| `port` | Cassandra port | `9042` |
+| `username` | Database username | `None` |
+| `password` | Database password | `None` |
+| `keyspace` | Keyspace name | `"mem0"` |
+| `collection_name` | Table name for storing vectors | `"memories"` |
+| `embedding_model_dims` | Dimensions of embedding vectors | `1536` |
+| `secure_connect_bundle` | Path to Astra DB secure connect bundle | `None` |
+| `protocol_version` | CQL protocol version | `4` |
+| `load_balancing_policy` | Custom load balancing policy | `None` |
+
+### Setup
+
+#### Option 1: Local Cassandra Setup using Docker:
+
+```bash
+# Pull and run Cassandra container
+docker run --name mem0-cassandra \
+    -p 9042:9042 \
+    -e CASSANDRA_CLUSTER_NAME="Mem0Cluster" \
+    -d cassandra:latest
+
+# Wait for Cassandra to start (may take 1-2 minutes)
+docker exec -it mem0-cassandra cqlsh
+
+# Create keyspace
+CREATE KEYSPACE IF NOT EXISTS mem0
+WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 1};
+```
+
+#### Option 2: DataStax Astra DB (Managed Cloud):
+
+1. Sign up at [DataStax Astra](https://astra.datastax.com/)
+2. Create a new database
+3. Download the secure connect bundle
+4. Generate an application token
+
+<Tip>
+For production deployments, use DataStax Astra DB for fully managed Cassandra with automatic scaling, backups, and security.
+</Tip>
+
+#### Option 3: Install Cassandra Locally:
+
+**Ubuntu/Debian:**
+```bash
+# Add Apache Cassandra repository
+echo "deb https://downloads.apache.org/cassandra/debian 40x main" | sudo tee -a /etc/apt/sources.list.d/cassandra.sources.list
+curl https://downloads.apache.org/cassandra/KEYS | sudo apt-key add -
+
+# Install Cassandra
+sudo apt-get update
+sudo apt-get install cassandra
+
+# Start Cassandra
+sudo systemctl start cassandra
+
+# Verify installation
+nodetool status
+```
+
+**macOS:**
+```bash
+# Using Homebrew
+brew install cassandra
+
+# Start Cassandra
+brew services start cassandra
+
+# Connect to CQL shell
+cqlsh
+```
+
+### Python Client Installation
+
+Install the required Python package:
+
+```bash
+pip install cassandra-driver
+```
+
+### Performance Considerations
+
+- **Replication Factor**: For production, use replication factor of at least 3
+- **Consistency Level**: Balance between consistency and performance (QUORUM recommended)
+- **Partitioning**: Cassandra automatically distributes data across nodes
+- **Scaling**: Add nodes to linearly increase capacity and performance
+
+### Advanced Configuration
+
+```python
+from cassandra.policies import DCAwareRoundRobinPolicy
+
+config = {
+    "vector_store": {
+        "provider": "cassandra",
+        "config": {
+            "contact_points": ["node1.example.com", "node2.example.com", "node3.example.com"],
+            "port": 9042,
+            "username": "mem0_user",
+            "password": "secure_password",
+            "keyspace": "mem0_prod",
+            "collection_name": "memories",
+            "protocol_version": 4,
+            "load_balancing_policy": DCAwareRoundRobinPolicy(local_dc='DC1')
+        }
+    }
+}
+```
+
+<Warning>
+For production use, configure appropriate replication strategies and consistency levels based on your availability and consistency requirements.
+</Warning>
+

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",
         }
     }
 }
@@ -21,7 +26,7 @@ config = {
 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": "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."}
 ]
@@ -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

@@ -31,7 +31,7 @@ config = {
 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": "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."}
 ]
@@ -40,7 +40,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
 
 ### Config
 
-Let's see the available parameters for the `elasticsearch` config:
+Here are the parameters available for configuring Elasticsearch:
 
 | Parameter              | Description                                        | Default Value |
 | ---------------------- | -------------------------------------------------- | ------------- |
@@ -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

@@ -22,7 +22,7 @@ config = {
 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": "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."}
 ]

docs/components/vectordbs/dbs/langchain.mdx

@@ -38,7 +38,7 @@ config = {
 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": "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."}
 ]
@@ -64,12 +64,12 @@ 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: "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." }
 ]
 
-memory.add(messages, user_id="alice", metadata={"category": "movies"})
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
 ```
 </CodeGroup>
 

docs/components/vectordbs/dbs/milvus.mdx

@@ -1,4 +1,4 @@
-[Milvus](https://milvus.io/) Milvus is an open-source vector database that suits AI applications of every size from running a demo chatbot in Jupyter notebook to building web-scale search that serves billions of users.
+[Milvus](https://milvus.io/) is an open-source vector database that suits AI applications of every size, from running a demo chatbot in a Jupyter notebook to building web-scale search that serves billions of users.
 
 ### Usage
 
@@ -11,9 +11,10 @@ config = {
         "provider": "milvus",
         "config": {
             "collection_name": "test",
-            "embedding_model_dims": "123",
+            "embedding_model_dims": 1536,
             "url": "127.0.0.1",
             "token": "8e4b8ca8cf2c67",
+            "db_name": "my_database",
         }
     }
 }
@@ -21,7 +22,7 @@ config = {
 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": "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."}
 ]
@@ -30,7 +31,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
 
 ### Config
 
-Here's the parameters available for configuring Milvus Database:
+Here are the parameters available for configuring Milvus:
 
 | Parameter | Description | Default Value |
 | --- | --- | --- |
@@ -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

@@ -24,7 +24,7 @@ config = {
 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": "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."}
 ]
@@ -40,6 +40,6 @@ Here are the parameters available for configuring MongoDB:
 | 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 |
+| mongo_uri | The MongoDB URI connection string | `mongodb://username:password@localhost:27017` |
 
-> **Note**: If Mongo_uri is not provided it will default to 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

@@ -58,7 +58,7 @@ config = {
 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": "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."}
 ]
@@ -74,8 +74,8 @@ results = m.search("What kind of movies does Alice like?", user_id="alice")
 ### Features
 
 - Fast and Efficient Vector Search
-- Can be deployed on-premises, in containers, or on cloud platforms like AWS OpenSearch Service.
-- Multiple Authentication and Security Methods (Basic Authentication, API Keys, LDAP, SAML, and OpenID Connect)
+- Can be deployed on-premises, in containers, or on cloud platforms like AWS OpenSearch Service
+- Multiple authentication and security methods (Basic Authentication, API Keys, LDAP, SAML, and OpenID Connect)
 - Automatic index creation with optimized mappings for vector search
-- Memory Optimization through Disk-Based Vector Search and Quantization
-- Real-Time Analytics and Observability
+- Memory optimization through disk-based vector search and quantization
+- Real-time analytics and observability

docs/components/vectordbs/dbs/pgvector.mdx

@@ -1,8 +1,9 @@
-[pgvector](https://github.com/pgvector/pgvector) is open-source vector similarity search for Postgres. After connecting with postgres run `CREATE EXTENSION IF NOT EXISTS vector;` to create the vector extension.
+[pgvector](https://github.com/pgvector/pgvector) is an open-source vector similarity search extension for Postgres. After connecting to Postgres, run `CREATE EXTENSION IF NOT EXISTS vector;` to create the vector extension.
 
 ### Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -23,20 +24,51 @@ config = {
 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": "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"})
 ```
 
+```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 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:
+Here are 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

@@ -1,5 +1,7 @@
 [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.
 
+> **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"
@@ -30,7 +33,7 @@ config = {
 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": "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."}
 ]
@@ -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/qdrant.mdx

@@ -23,7 +23,7 @@ config = {
 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": "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."}
 ]
@@ -48,7 +48,7 @@ const config = {
 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": "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."}
 ]

docs/components/vectordbs/dbs/redis.mdx

@@ -34,7 +34,7 @@ config = {
 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": "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."}
 ]
@@ -60,7 +60,7 @@ const config = {
 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": "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."}
 ]

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 parameters available for configuring Amazon S3 Vectors:
+
+| 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

@@ -26,7 +26,7 @@ config = {
 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": "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."}
 ]
@@ -53,7 +53,7 @@ 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": "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."}
 ]
@@ -109,7 +109,7 @@ end;
 $$;
 ```
 
-Goto [Supabase](https://supabase.com/dashboard/projects) and run the above SQL migrations inside the SQL Editor.
+Go to [Supabase](https://supabase.com/dashboard/projects) and run the above SQL migrations in the SQL Editor.
 
 ### Config
 

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 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
+
+Here are the parameters available for configuring Valkey:
+
+| 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

@@ -31,7 +31,7 @@ await memory.add(messages, { userId: "bob", metadata: { interest: "books" } });
 
 ### Config
 
-Let's see the available parameters for the `vectorize` config:
+Here are the parameters available for configuring Vectorize:
 
 <Tabs>
 <Tab title="TypeScript">

docs/components/vectordbs/dbs/vertex_ai.mdx

@@ -12,7 +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": {