improvement(OSS): Fix AOSS and AWS BedRock LLM (#2697)

Co-authored-by: Prateek Chhikara <prateekchhikara24@gmail.com>
Co-authored-by: Deshraj Yadav <deshrajdry@gmail.com>

.github/workflows/ci.yml

@@ -59,6 +59,10 @@ jobs:
       - name: Install dependencies
         run: make install_all
         if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+      - name: Run Formatting
+        run: |
+          mkdir -p mem0/.ruff_cache && chmod -R 777 mem0/.ruff_cache
+          cd mem0 && poetry run ruff check . --select F
       - name: Run tests and generate coverage report
         run: make test
 
@@ -90,6 +94,10 @@ jobs:
       - name: Install dependencies
         run: cd embedchain && make install_all
         if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+      - name: Run Formatting
+        run: |
+          mkdir -p embedchain/.ruff_cache && chmod -R 777 embedchain/.ruff_cache
+          cd embedchain && poetry run ruff check . --select F
       - name: Lint with ruff
         run: cd embedchain && make lint
       - name: Run tests and generate coverage report

Makefile

@@ -12,8 +12,9 @@ install:
 
 install_all:
 	poetry install
-	poetry run pip install groq together boto3 litellm ollama chromadb sentence_transformers vertexai \
-	                        google-generativeai elasticsearch opensearch-py vecs
+	poetry run 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 pinecone-text faiss-cpu langchain-community \
+							upstash-vector azure-search-documents langchain-memgraph
 
 # Format code with ruff
 format:

README.md

@@ -1,24 +1,22 @@
 <p align="center">
   <a href="https://github.com/mem0ai/mem0">
-  <img src="docs/images/banner-sm.png" width="800px" alt="Mem0 - The Memory Layer for Personalized AI">
+    <img src="docs/images/banner-sm.png" width="800px" alt="Mem0 - The Memory Layer for Personalized AI">
   </a>
+</p>
 <p align="center" style="display: flex; justify-content: center; gap: 20px; align-items: center;">
-  <a href="https://trendshift.io/repositories/11194" target="_blank">
-    <img src="https://trendshift.io/api/badge/repositories/11194" alt="mem0ai%2Fmem0 | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
-  </a>
-  <a href="https://www.ycombinator.com/launches/LpA-mem0-open-source-memory-layer-for-ai-apps" target="_blank">
-    <img alt="Launch YC: Mem0 - Open Source Memory Layer for AI Apps" src="https://www.ycombinator.com/launches/LpA-mem0-open-source-memory-layer-for-ai-apps/upvote_embed.svg"/>
+  <a href="https://trendshift.io/repositories/11194" target="blank">
+    <img src="https://trendshift.io/api/badge/repositories/11194" alt="mem0ai%2Fmem0 | Trendshift" width="250" height="55"/>
   </a>
 </p>
 
-
-  <p align="center">
-    <a href="https://mem0.ai">Learn more</a>
-    ·
-    <a href="https://mem0.dev/DiG">Join Discord</a>
-    ·
-    <a href="https://mem0.dev/demo">Demo</a>
-  </p>
+<p align="center">
+  <a href="https://mem0.ai">Learn more</a>
+  ·
+  <a href="https://mem0.dev/DiG">Join Discord</a>
+  ·
+  <a href="https://mem0.dev/demo">Demo</a>
+  ·
+  <a href="https://mem0.dev/openmemory">OpenMemory</a>
 </p>
 
 <p align="center">
@@ -26,62 +24,78 @@
     <img src="https://dcbadge.vercel.app/api/server/6PzXDgEjG5?style=flat" alt="Mem0 Discord">
   </a>
   <a href="https://pepy.tech/project/mem0ai">
-    <img src="https://img.shields.io/pypi/dm/mem0ai" alt="Mem0 PyPI - Downloads" >
+    <img src="https://img.shields.io/pypi/dm/mem0ai" alt="Mem0 PyPI - Downloads">
   </a>
   <a href="https://github.com/mem0ai/mem0">
     <img src="https://img.shields.io/github/commit-activity/m/mem0ai/mem0?style=flat-square" alt="GitHub commit activity">
   </a>
-  <a href="https://pypi.org/project/mem0ai" target="_blank">
-        <img src="https://img.shields.io/pypi/v/mem0ai?color=%2334D058&label=pypi%20package" alt="Package version">
-    </a>
-    <a href="https://www.npmjs.com/package/mem0ai" target="_blank">
-        <img src="https://img.shields.io/npm/v/mem0ai" alt="Npm package">
-    </a>
+  <a href="https://pypi.org/project/mem0ai" target="blank">
+    <img src="https://img.shields.io/pypi/v/mem0ai?color=%2334D058&label=pypi%20package" alt="Package version">
+  </a>
+  <a href="https://www.npmjs.com/package/mem0ai" target="blank">
+    <img src="https://img.shields.io/npm/v/mem0ai" alt="Npm package">
+  </a>
   <a href="https://www.ycombinator.com/companies/mem0">
     <img src="https://img.shields.io/badge/Y%20Combinator-S24-orange?style=flat-square" alt="Y Combinator S24">
   </a>
 </p>
 
+<p align="center">
+  <a href="https://mem0.ai/research"><strong>📄 Building Production-Ready AI Agents with Scalable Long-Term Memory →</strong></a>
+</p>
+<p align="center">
+  <strong>⚡ +26% Accuracy vs. OpenAI Memory • 🚀 91% Faster • 💰 90% Fewer Tokens</strong>
+</p>
+
+##  🔥 Research Highlights
+- **+26% Accuracy** over OpenAI Memory on the LOCOMO benchmark
+- **91% Faster Responses** than full-context, ensuring low-latency at scale
+- **90% Lower Token Usage** than full-context, cutting costs without compromise
+- [Read the full paper](https://mem0.ai/research)
 
 # Introduction
 
-[Mem0](https://mem0.ai) (pronounced as "mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. Mem0 remembers user preferences, adapts to individual needs, and continuously improves over time, making it ideal for customer support chatbots, AI assistants, and autonomous systems.
+[Mem0](https://mem0.ai) ("mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. It remembers user preferences, adapts to individual needs, and continuously learns over time—ideal for customer support chatbots, AI assistants, and autonomous systems.
 
-### Features & Use Cases
+### Key Features & Use Cases
 
-Core Capabilities:
-- **Multi-Level Memory**: User, Session, and AI Agent memory retention with adaptive personalization
-- **Developer-Friendly**: Simple API integration, cross-platform consistency, and hassle-free managed service
+**Core Capabilities:**
+- **Multi-Level Memory**: Seamlessly retains User, Session, and Agent state with adaptive personalization
+- **Developer-Friendly**: Intuitive API, cross-platform SDKs, and a fully managed service option
 
-Applications:
-- **AI Assistants**: Seamless conversations with context and personalization
-- **Learning & Support**: Tailored content recommendations and context-aware customer assistance
-- **Healthcare & Companions**: Patient history tracking and deeper relationship building
-- **Productivity & Gaming**: Streamlined workflows and adaptive environments based on user behavior
+**Applications:**
+- **AI Assistants**: Consistent, context-rich conversations
+- **Customer Support**: Recall past tickets and user history for tailored help
+- **Healthcare**: Track patient preferences and history for personalized care
+- **Productivity & Gaming**: Adaptive workflows and environments based on user behavior
 
-## Get Started
+## 🚀 Quickstart Guide <a name="quickstart"></a>
 
-Get started quickly with [Mem0 Platform](https://app.mem0.ai) - our fully managed solution that provides automatic updates, advanced analytics, enterprise security, and dedicated support. [Create a free account](https://app.mem0.ai) to begin.
+Choose between our hosted platform or self-hosted package:
 
-For complete control, you can self-host Mem0 using our open-source package. See the [Quickstart guide](#quickstart) below to set up your own instance.
+### Hosted Platform
 
-## Quickstart Guide <a name="quickstart"></a>
+Get up and running in minutes with automatic updates, analytics, and enterprise security.
 
-Install the Mem0 package via pip:
+1. Sign up on [Mem0 Platform](https://app.mem0.ai)
+2. Embed the memory layer via SDK or API keys
+
+### Self-Hosted (Open Source)
+
+Install the sdk via pip:
 
 ```bash
 pip install mem0ai
 ```
 
-Install the Mem0 package via npm:
-
+Install sdk via npm:
 ```bash
 npm install mem0ai
 ```
 
 ### Basic Usage
 
-Mem0 requires an LLM to function, with `gpt-4o-mini` from OpenAI as the default. However, it supports a variety of LLMs; for details, refer to our [Supported LLMs documentation](https://docs.mem0.ai/llms).
+Mem0 requires an LLM to function, with `gpt-4o-mini` from OpenAI as the default. However, it supports a variety of LLMs; for details, refer to our [Supported LLMs documentation](https://docs.mem0.ai/components/llms/overview).
 
 First step is to instantiate the memory:
 
@@ -96,7 +110,7 @@ def chat_with_memories(message: str, user_id: str = "default_user") -> str:
     # Retrieve relevant memories
     relevant_memories = memory.search(query=message, user_id=user_id, limit=3)
     memories_str = "\n".join(f"- {entry['memory']}" for entry in relevant_memories["results"])
-    
+
     # Generate Assistant response
     system_prompt = f"You are a helpful AI. Answer the question based on query and memories.\nUser Memories:\n{memories_str}"
     messages = [{"role": "system", "content": system_prompt}, {"role": "user", "content": message}]
@@ -122,68 +136,34 @@ if __name__ == "__main__":
     main()
 ```
 
-See the example for [Node.js](https://docs.mem0.ai/examples/ai_companion_js).
+For detailed integration steps, see the [Quickstart](https://docs.mem0.ai/quickstart) and [API Reference](https://docs.mem0.ai/api-reference).
 
-For more advanced usage and API documentation, visit our [documentation](https://docs.mem0.ai).
+## 🔗 Integrations & Demos
 
-> [!TIP]
-> For a hassle-free experience, try our [hosted platform](https://app.mem0.ai) with automatic updates and enterprise features.
+- **ChatGPT with Memory**: Personalized chat powered by Mem0 ([Live Demo](https://mem0.dev/demo))
+- **Browser Extension**: Store memories across ChatGPT, Perplexity, and Claude ([Chrome Extension](https://chromewebstore.google.com/detail/onihkkbipkfeijkadecaafbgagkhglop?utm_source=item-share-cb))
+- **Langgraph Support**: Build a customer bot with Langgraph + Mem0 ([Guide](https://docs.mem0.ai/integrations/langgraph))
+- **CrewAI Integration**: Tailor CrewAI outputs with Mem0 ([Example](https://docs.mem0.ai/integrations/crewai))
 
-## Demos
+## 📚 Documentation & Support
 
-- Mem0 - ChatGPT with Memory: A personalized AI chat app powered by Mem0 that remembers your preferences, facts, and memories.
+- Full docs: https://docs.mem0.ai
+- Community: [Discord](https://mem0.dev/DiG) · [Twitter](https://x.com/mem0ai)
+- Contact: founders@mem0.ai
 
-[Mem0 - ChatGPT with Memory](https://github.com/user-attachments/assets/cebc4f8e-bdb9-4837-868d-13c5ab7bb433)
+## Citation
 
-Try live [demo](https://mem0.dev/demo/)
+We now have a paper you can cite:
 
-<br/><br/>
+```bibtex
+@article{mem0,
+  title={Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory},
+  author={Chhikara, Prateek and Khant, Dev and Aryan, Saket and Singh, Taranjeet and Yadav, Deshraj},
+  journal={arXiv preprint arXiv:2504.19413},
+  year={2025}
+}
+```
 
-- AI Companion: Experience personalized conversations with an AI that remembers your preferences and past interactions
+## ⚖️ License
 
-[AI Companion Demo](https://github.com/user-attachments/assets/3fc72023-a72c-4593-8be0-3cee3ba744da)
-
-<br/><br/>
-
-- Enhance your AI interactions by storing memories across ChatGPT, Perplexity, and Claude using our browser extension. Get [chrome extension](https://chromewebstore.google.com/detail/mem0/onihkkbipkfeijkadecaafbgagkhglop?hl=en).
-
-
-[Chrome Extension Demo](https://github.com/user-attachments/assets/ca92e40b-c453-4ff6-b25e-739fb18a8650)
-
-<br/><br/>
-
-- Customer support bot using <strong>Langgraph and Mem0</strong>. Get the complete code from [here](https://docs.mem0.ai/integrations/langgraph)
-
-
-[Langgraph: Customer Bot](https://github.com/user-attachments/assets/ca6b482e-7f46-42c8-aa08-f88d1d93a5f4)
-
-<br/><br/>
-
-- Use Mem0 with CrewAI to get personalized results. Full example [here](https://docs.mem0.ai/integrations/crewai)
-
-[CrewAI Demo](https://github.com/user-attachments/assets/69172a79-ccb9-4340-91f1-caa7d2dd4213)
-
-
-
-## Documentation
-
-For detailed usage instructions and API reference, visit our [documentation](https://docs.mem0.ai). You'll find:
-- Complete API reference
-- Integration guides
-- Advanced configuration options
-- Best practices and examples
-- More details about:
-  - Open-source version
-  - [Hosted Mem0 Platform](https://app.mem0.ai)
-
-## Support
-
-Join our community for support and discussions. If you have any questions, feel free to reach out to us using one of the following methods:
-
-- [Join our Discord](https://mem0.dev/DiG)
-- [Follow us on Twitter](https://x.com/mem0ai)
-- [Email founders](mailto:founders@mem0.ai)
-
-## License
-
-This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.
+Apache 2.0 — see the [LICENSE](LICENSE) file for details.

cookbooks/helper/mem0_teachability.py

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

cookbooks/mem0-autogen.ipynb

@@ -1,42 +1,116 @@
 {
  "cells": [
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "1e8a980a2e0b9a85",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "%pip install --upgrade pip\n",
     "%pip install mem0ai pyautogen flaml"
-   ],
-   "id": "1e8a980a2e0b9a85",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d437544fe259dd1b",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-25T20:29:52.443024Z",
      "start_time": "2024-09-25T20:29:52.440046Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "# Set up ENV Vars\n",
     "import os\n",
     "os.environ['OPENAI_API_KEY'] = \"sk-xxx\"\n"
-   ],
-   "id": "d437544fe259dd1b",
-   "outputs": [],
-   "execution_count": 11
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "initial_id",
    "metadata": {
-    "collapsed": true,
     "ExecuteTime": {
      "end_time": "2024-09-25T20:30:03.914245Z",
      "start_time": "2024-09-25T20:29:53.236601Z"
-    }
+    },
+    "collapsed": true
    },
-   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:autogen.agentchat.contrib.gpt_assistant_agent:OpenAI client config of GPTAssistantAgent(assistant) - model: gpt-4o\n",
+      "WARNING:autogen.agentchat.contrib.gpt_assistant_agent:Matching assistant found, using the first matching assistant: {'id': 'asst_PpOJ2mJC8QeysR54I6DEdi4E', 'created_at': 1726444855, 'description': None, 'instructions': 'You are a helpful AI assistant.\\nSolve tasks using your coding and language skills.\\nIn the following cases, suggest python code (in a python coding block) or shell script (in a sh coding block) for the user to execute.\\n    1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time, check the operating system. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.\\n    2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.\\nSolve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.\\nWhen using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can\\'t modify your code. So do not suggest incomplete code which requires users to modify. Don\\'t use a code block if it\\'s not intended to be executed by the user.\\nIf you want the user to save the code in a file before executing it, put # filename: <filename> inside the code block as the first line. Don\\'t include multiple code blocks in one response. Do not ask users to copy and paste the result. Instead, use \\'print\\' function for the output when relevant. Check the execution result returned by the user.\\nIf the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can\\'t be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.\\nWhen you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible.\\nReply \"TERMINATE\" in the end when everything is done.\\n    ', 'metadata': {}, 'model': 'gpt-4o', 'name': 'assistant', 'object': 'assistant', 'tools': [], 'response_format': 'auto', 'temperature': 1.0, 'tool_resources': ToolResources(code_interpreter=None, file_search=None), 'top_p': 1.0}\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
+      "\n",
+      "Write a Python function that reverses a string.\n",
+      "\n",
+      "--------------------------------------------------------------------------------\n",
+      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
+      "\n",
+      "Sure! Here is the Python code for a function that takes a string as input and returns the reversed string.\n",
+      "\n",
+      "```python\n",
+      "def reverse_string(s):\n",
+      "    return s[::-1]\n",
+      "\n",
+      "# Example usage\n",
+      "if __name__ == \"__main__\":\n",
+      "    example_string = \"Hello, world!\"\n",
+      "    reversed_string = reverse_string(example_string)\n",
+      "    print(f\"Original string: {example_string}\")\n",
+      "    print(f\"Reversed string: {reversed_string}\")\n",
+      "```\n",
+      "\n",
+      "When you run this code, it will print the original string and the reversed string. You can replace `example_string` with any string you want to reverse.\n",
+      "\n",
+      "\n",
+      "--------------------------------------------------------------------------------\n",
+      "\u001b[31m\n",
+      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
+      "\n",
+      "exitcode: 0 (execution succeeded)\n",
+      "Code output: \n",
+      "Original string: Hello, world!\n",
+      "Reversed string: !dlrow ,olleH\n",
+      "\n",
+      "\n",
+      "--------------------------------------------------------------------------------\n",
+      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
+      "\n",
+      "Great, the function worked as expected! The original string \"Hello, world!\" was correctly reversed to \"!dlrow ,olleH\".\n",
+      "\n",
+      "If you have any other tasks or need further assistance, let me know! \n",
+      "\n",
+      "TERMINATE\n",
+      "\n",
+      "\n",
+      "--------------------------------------------------------------------------------\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "ChatResult(chat_id=None, chat_history=[{'content': 'Write a Python function that reverses a string.', 'role': 'assistant', 'name': 'user_proxy'}, {'content': 'Sure! Here is the Python code for a function that takes a string as input and returns the reversed string.\\n\\n```python\\ndef reverse_string(s):\\n    return s[::-1]\\n\\n# Example usage\\nif __name__ == \"__main__\":\\n    example_string = \"Hello, world!\"\\n    reversed_string = reverse_string(example_string)\\n    print(f\"Original string: {example_string}\")\\n    print(f\"Reversed string: {reversed_string}\")\\n```\\n\\nWhen you run this code, it will print the original string and the reversed string. You can replace `example_string` with any string you want to reverse.\\n', 'role': 'user', 'name': 'assistant'}, {'content': 'exitcode: 0 (execution succeeded)\\nCode output: \\nOriginal string: Hello, world!\\nReversed string: !dlrow ,olleH\\n', 'role': 'assistant', 'name': 'user_proxy'}, {'content': 'Great, the function worked as expected! The original string \"Hello, world!\" was correctly reversed to \"!dlrow ,olleH\".\\n\\nIf you have any other tasks or need further assistance, let me know! \\n\\nTERMINATE\\n', 'role': 'user', 'name': 'assistant'}], summary='Great, the function worked as expected! The original string \"Hello, world!\" was correctly reversed to \"!dlrow ,olleH\".\\n\\nIf you have any other tasks or need further assistance, let me know! \\n\\n\\n', cost={'usage_including_cached_inference': {'total_cost': 0}, 'usage_excluding_cached_inference': {'total_cost': 0}}, human_input=[])"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# AutoGen GPTAssistantAgent Capabilities:\n",
     "# - Generates code based on user requirements and preferences.\n",
@@ -93,90 +167,40 @@
     "user_query = \"Write a Python function that reverses a string.\"\n",
     "# Initiate Chat w/o Memory\n",
     "user_proxy.initiate_chat(gpt_assistant, message=user_query)"
-   ],
-   "id": "initial_id",
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:autogen.agentchat.contrib.gpt_assistant_agent:OpenAI client config of GPTAssistantAgent(assistant) - model: gpt-4o\n",
-      "WARNING:autogen.agentchat.contrib.gpt_assistant_agent:Matching assistant found, using the first matching assistant: {'id': 'asst_PpOJ2mJC8QeysR54I6DEdi4E', 'created_at': 1726444855, 'description': None, 'instructions': 'You are a helpful AI assistant.\\nSolve tasks using your coding and language skills.\\nIn the following cases, suggest python code (in a python coding block) or shell script (in a sh coding block) for the user to execute.\\n    1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time, check the operating system. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.\\n    2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.\\nSolve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.\\nWhen using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can\\'t modify your code. So do not suggest incomplete code which requires users to modify. Don\\'t use a code block if it\\'s not intended to be executed by the user.\\nIf you want the user to save the code in a file before executing it, put # filename: <filename> inside the code block as the first line. Don\\'t include multiple code blocks in one response. Do not ask users to copy and paste the result. Instead, use \\'print\\' function for the output when relevant. Check the execution result returned by the user.\\nIf the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can\\'t be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.\\nWhen you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible.\\nReply \"TERMINATE\" in the end when everything is done.\\n    ', 'metadata': {}, 'model': 'gpt-4o', 'name': 'assistant', 'object': 'assistant', 'tools': [], 'response_format': 'auto', 'temperature': 1.0, 'tool_resources': ToolResources(code_interpreter=None, file_search=None), 'top_p': 1.0}\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001B[33muser_proxy\u001B[0m (to assistant):\n",
-      "\n",
-      "Write a Python function that reverses a string.\n",
-      "\n",
-      "--------------------------------------------------------------------------------\n",
-      "\u001B[33massistant\u001B[0m (to user_proxy):\n",
-      "\n",
-      "Sure! Here is the Python code for a function that takes a string as input and returns the reversed string.\n",
-      "\n",
-      "```python\n",
-      "def reverse_string(s):\n",
-      "    return s[::-1]\n",
-      "\n",
-      "# Example usage\n",
-      "if __name__ == \"__main__\":\n",
-      "    example_string = \"Hello, world!\"\n",
-      "    reversed_string = reverse_string(example_string)\n",
-      "    print(f\"Original string: {example_string}\")\n",
-      "    print(f\"Reversed string: {reversed_string}\")\n",
-      "```\n",
-      "\n",
-      "When you run this code, it will print the original string and the reversed string. You can replace `example_string` with any string you want to reverse.\n",
-      "\n",
-      "\n",
-      "--------------------------------------------------------------------------------\n",
-      "\u001B[31m\n",
-      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to assistant):\n",
-      "\n",
-      "exitcode: 0 (execution succeeded)\n",
-      "Code output: \n",
-      "Original string: Hello, world!\n",
-      "Reversed string: !dlrow ,olleH\n",
-      "\n",
-      "\n",
-      "--------------------------------------------------------------------------------\n",
-      "\u001B[33massistant\u001B[0m (to user_proxy):\n",
-      "\n",
-      "Great, the function worked as expected! The original string \"Hello, world!\" was correctly reversed to \"!dlrow ,olleH\".\n",
-      "\n",
-      "If you have any other tasks or need further assistance, let me know! \n",
-      "\n",
-      "TERMINATE\n",
-      "\n",
-      "\n",
-      "--------------------------------------------------------------------------------\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "ChatResult(chat_id=None, chat_history=[{'content': 'Write a Python function that reverses a string.', 'role': 'assistant', 'name': 'user_proxy'}, {'content': 'Sure! Here is the Python code for a function that takes a string as input and returns the reversed string.\\n\\n```python\\ndef reverse_string(s):\\n    return s[::-1]\\n\\n# Example usage\\nif __name__ == \"__main__\":\\n    example_string = \"Hello, world!\"\\n    reversed_string = reverse_string(example_string)\\n    print(f\"Original string: {example_string}\")\\n    print(f\"Reversed string: {reversed_string}\")\\n```\\n\\nWhen you run this code, it will print the original string and the reversed string. You can replace `example_string` with any string you want to reverse.\\n', 'role': 'user', 'name': 'assistant'}, {'content': 'exitcode: 0 (execution succeeded)\\nCode output: \\nOriginal string: Hello, world!\\nReversed string: !dlrow ,olleH\\n', 'role': 'assistant', 'name': 'user_proxy'}, {'content': 'Great, the function worked as expected! The original string \"Hello, world!\" was correctly reversed to \"!dlrow ,olleH\".\\n\\nIf you have any other tasks or need further assistance, let me know! \\n\\nTERMINATE\\n', 'role': 'user', 'name': 'assistant'}], summary='Great, the function worked as expected! The original string \"Hello, world!\" was correctly reversed to \"!dlrow ,olleH\".\\n\\nIf you have any other tasks or need further assistance, let me know! \\n\\n\\n', cost={'usage_including_cached_inference': {'total_cost': 0}, 'usage_excluding_cached_inference': {'total_cost': 0}}, human_input=[])"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 12
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "c2fe6fd02324be37",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-25T20:31:40.536369Z",
      "start_time": "2024-09-25T20:31:31.078911Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/z6/3w4ng1lj3mn4vmhplgc4y0580000gn/T/ipykernel_77647/3850691550.py:28: DeprecationWarning: The current add API output format is deprecated. To use the latest format, set `api_version='v1.1'`. The current format will be removed in mem0ai 1.1.0 and later versions.\n",
+      "  MEM0_MEMORY_CLIENT.add(MEMORY_DATA, user_id=USER_ID)\n",
+      "/var/folders/z6/3w4ng1lj3mn4vmhplgc4y0580000gn/T/ipykernel_77647/3850691550.py:29: DeprecationWarning: The current add API output format is deprecated. To use the latest format, set `api_version='v1.1'`. The current format will be removed in mem0ai 1.1.0 and later versions.\n",
+      "  MEM0_MEMORY_CLIENT.add(MEMORY_DATA, agent_id=AGENT_ID)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'message': 'ok'}"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# Benefits of Preference Memory in AutoGen Agents:\n",
     "# - Personalization: Tailors responses to individual user or team preferences.\n",
@@ -207,61 +231,28 @@
     "# Add preference data to memory\n",
     "MEM0_MEMORY_CLIENT.add(MEMORY_DATA, user_id=USER_ID)\n",
     "MEM0_MEMORY_CLIENT.add(MEMORY_DATA, agent_id=AGENT_ID)"
-   ],
-   "id": "c2fe6fd02324be37",
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/var/folders/z6/3w4ng1lj3mn4vmhplgc4y0580000gn/T/ipykernel_77647/3850691550.py:28: DeprecationWarning: The current add API output format is deprecated. To use the latest format, set `api_version='v1.1'`. The current format will be removed in mem0ai 1.1.0 and later versions.\n",
-      "  MEM0_MEMORY_CLIENT.add(MEMORY_DATA, user_id=USER_ID)\n",
-      "/var/folders/z6/3w4ng1lj3mn4vmhplgc4y0580000gn/T/ipykernel_77647/3850691550.py:29: DeprecationWarning: The current add API output format is deprecated. To use the latest format, set `api_version='v1.1'`. The current format will be removed in mem0ai 1.1.0 and later versions.\n",
-      "  MEM0_MEMORY_CLIENT.add(MEMORY_DATA, agent_id=AGENT_ID)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'message': 'ok'}"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 16
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
+   "id": "fb6d6a8f36aedfd6",
+   "metadata": {},
    "source": [
     "## Option 1: \n",
     "Using Direct Prompt Injection:\n",
     "`user memory example`"
-   ],
-   "id": "fb6d6a8f36aedfd6"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "29be484c69093371",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-25T20:31:52.411604Z",
      "start_time": "2024-09-25T20:31:40.611497Z"
     }
    },
-   "cell_type": "code",
-   "source": [
-    "# Retrieve the memory\n",
-    "relevant_memories = MEM0_MEMORY_CLIENT.search(user_query, user_id=USER_ID, limit=3)\n",
-    "relevant_memories_text = '\\n'.join(mem['memory'] for mem in relevant_memories)\n",
-    "print(f\"Relevant memories:\")\n",
-    "print(relevant_memories_text)\n",
-    "\n",
-    "prompt = f\"{user_query}\\n Coding Preferences: \\n{relevant_memories_text}\"\n",
-    "browse_result = user_proxy.initiate_chat(gpt_assistant, message=prompt)"
-   ],
-   "id": "29be484c69093371",
    "outputs": [
     {
      "name": "stderr",
@@ -280,7 +271,7 @@
       "Prefers functions to have a descriptive docstring\n",
       "Prefers camelCase for variable names\n",
       "Prefers code to be explicitly written with clear variable names\n",
-      "\u001B[33muser_proxy\u001B[0m (to assistant):\n",
+      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
       "\n",
       "Write a Python function that reverses a string.\n",
       " Coding Preferences: \n",
@@ -289,7 +280,7 @@
       "Prefers code to be explicitly written with clear variable names\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33massistant\u001B[0m (to user_proxy):\n",
+      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
       "\n",
       "Sure, I will write a Python function that reverses a given string with clear and descriptive variable names, along with a descriptive docstring.\n",
       "\n",
@@ -324,9 +315,9 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[31m\n",
-      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to assistant):\n",
+      "\u001b[31m\n",
+      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
       "\n",
       "exitcode: 0 (execution succeeded)\n",
       "Code output: \n",
@@ -335,7 +326,7 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33massistant\u001B[0m (to user_proxy):\n",
+      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
       "\n",
       "Great! It looks like the code executed successfully and produced the correct output, reversing the string \"Hello World!\" to \"!dlroW olleH\".\n",
       "\n",
@@ -354,26 +345,38 @@
      ]
     }
    ],
-   "execution_count": 17
+   "source": [
+    "# Retrieve the memory\n",
+    "relevant_memories = MEM0_MEMORY_CLIENT.search(user_query, user_id=USER_ID, limit=3)\n",
+    "relevant_memories_text = '\\n'.join(mem['memory'] for mem in relevant_memories)\n",
+    "print(\"Relevant memories:\")\n",
+    "print(relevant_memories_text)\n",
+    "\n",
+    "prompt = f\"{user_query}\\n Coding Preferences: \\n{relevant_memories_text}\"\n",
+    "browse_result = user_proxy.initiate_chat(gpt_assistant, message=prompt)"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
+   "id": "fc0ae72d0ef7f6de",
+   "metadata": {},
    "source": [
     "## Option 2:\n",
     "Using UserProxyAgent: \n",
     "`agent memory example`"
-   ],
-   "id": "fc0ae72d0ef7f6de"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "bfd9342cf2096ca5",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-25T20:31:52.421965Z",
      "start_time": "2024-09-25T20:31:52.418762Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "# UserProxyAgent in AutoGen:\n",
     "# - Acts as intermediary between humans and AI agents in the AutoGen framework.\n",
@@ -405,39 +408,24 @@
     "        self.memory.add(MEMORY_DATA, agent_id=self.agent_id)\n",
     "        return response\n",
     "    "
-   ],
-   "id": "bfd9342cf2096ca5",
-   "outputs": [],
-   "execution_count": 18
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "6d2a757d1cf65881",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-25T20:32:20.269222Z",
      "start_time": "2024-09-25T20:32:07.485051Z"
     }
    },
-   "cell_type": "code",
-   "source": [
-    "mem0_user_proxy = Mem0ProxyCoderAgent(\n",
-    "    name=AGENT_ID,\n",
-    "    code_execution_config={\n",
-    "        \"work_dir\": \"coding\",\n",
-    "        \"use_docker\": False,\n",
-    "    },  # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.\n",
-    "    is_termination_msg=lambda msg: \"TERMINATE\" in msg[\"content\"],\n",
-    "    human_input_mode=\"NEVER\",\n",
-    "    max_consecutive_auto_reply=1,\n",
-    ")\n",
-    "code_result = mem0_user_proxy.initiate_chat(gpt_assistant, message=user_query)"
-   ],
-   "id": "6d2a757d1cf65881",
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001B[33mchicory.ai\u001B[0m (to assistant):\n",
+      "\u001b[33mchicory.ai\u001b[0m (to assistant):\n",
       "\n",
       "Write a Python function that reverses a string.\n",
       " Coding Preferences: \n",
@@ -460,7 +448,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001B[33massistant\u001B[0m (to chicory.ai):\n",
+      "\u001b[33massistant\u001b[0m (to chicory.ai):\n",
       "\n",
       "Sure, I'll write a Python function that reverses a string following your coding preferences.\n",
       "\n",
@@ -487,9 +475,9 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[31m\n",
-      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n",
-      "\u001B[33mchicory.ai\u001B[0m (to assistant):\n",
+      "\u001b[31m\n",
+      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001b[0m\n",
+      "\u001b[33mchicory.ai\u001b[0m (to assistant):\n",
       "\n",
       "exitcode: 0 (execution succeeded)\n",
       "Code output: \n",
@@ -497,7 +485,7 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33massistant\u001B[0m (to chicory.ai):\n",
+      "\u001b[33massistant\u001b[0m (to chicory.ai):\n",
       "\n",
       "Great! The function has successfully reversed the string as expected.\n",
       "\n",
@@ -518,26 +506,41 @@
      ]
     }
    ],
-   "execution_count": 19
+   "source": [
+    "mem0_user_proxy = Mem0ProxyCoderAgent(\n",
+    "    name=AGENT_ID,\n",
+    "    code_execution_config={\n",
+    "        \"work_dir\": \"coding\",\n",
+    "        \"use_docker\": False,\n",
+    "    },  # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.\n",
+    "    is_termination_msg=lambda msg: \"TERMINATE\" in msg[\"content\"],\n",
+    "    human_input_mode=\"NEVER\",\n",
+    "    max_consecutive_auto_reply=1,\n",
+    ")\n",
+    "code_result = mem0_user_proxy.initiate_chat(gpt_assistant, message=user_query)"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
+   "id": "7706c06216ca4374",
+   "metadata": {},
    "source": [
     "# Option 3:\n",
     "Using Teachability:\n",
     "`agent memory example`"
-   ],
-   "id": "7706c06216ca4374"
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "ae6bb87061877645",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-25T20:33:17.737146Z",
      "start_time": "2024-09-25T20:33:17.713250Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "# building on top of existing Teachability package from autogen\n",
     "# from autogen.agentchat.contrib.capabilities.teachability import Teachability\n",
@@ -564,24 +567,18 @@
     "                memory_client = MEM0_MEMORY_CLIENT,\n",
     "            )\n",
     "teachability.add_to_agent(user_proxy)"
-   ],
-   "id": "ae6bb87061877645",
-   "outputs": [],
-   "execution_count": 20
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "36c9bcbedcd406b4",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-25T20:33:46.616261Z",
      "start_time": "2024-09-25T20:33:19.719999Z"
     }
    },
-   "cell_type": "code",
-   "source": [
-    "# Initiate Chat w/ Teachability + Memory\n",
-    "user_proxy.initiate_chat(gpt_assistant, message=user_query)"
-   ],
-   "id": "36c9bcbedcd406b4",
    "outputs": [
     {
      "name": "stderr",
@@ -594,12 +591,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001B[33muser_proxy\u001B[0m (to assistant):\n",
+      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
       "\n",
       "Write a Python function that reverses a string.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33massistant\u001B[0m (to user_proxy):\n",
+      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -626,9 +623,9 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
-      "LOOK FOR RELEVANT MEMOS, AS QUESTION-ANSWER PAIRS\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[93m\n",
+      "LOOK FOR RELEVANT MEMOS, AS QUESTION-ANSWER PAIRS\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -655,19 +652,19 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Does any part of the TEXT ask the agent to perform a task or solve a problem? Answer with just one word, yes or no.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Yes\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
-      "LOOK FOR RELEVANT MEMOS, AS TASK-ADVICE PAIRS\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[93m\n",
+      "LOOK FOR RELEVANT MEMOS, AS TASK-ADVICE PAIRS\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -694,32 +691,32 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Copy just the task from the TEXT, then stop. Don't solve it, and don't include any advice.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Save the above code in a file named `reverse_string.py`, then execute it. This script defines the `reverse_string` function and demonstrates its usage by reversing the string \"Hello, World!\". It will print both the original and reversed strings.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Save the above code in a file named `reverse_string.py`, then execute it. This script defines the `reverse_string` function and demonstrates its usage by reversing the string \"Hello, World!\". It will print both the original and reversed strings.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Summarize very briefly, in general terms, the type of task described in the TEXT. Leave out details that might not appear in a similar problem.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "The task involves saving a script to a file, executing it, and demonstrating a function that reverses a string.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
+      "\u001b[93m\n",
       "MEMOS APPENDED TO LAST MESSAGE...\n",
       "\n",
       "# Memories that might help\n",
@@ -728,8 +725,8 @@
       "- Prefers comments explaining each step\n",
       "- Prefers code to be explicitly written with clear variable names\n",
       "\n",
-      "\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -756,17 +753,17 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Does any part of the TEXT ask the agent to perform a task or solve a problem? Answer with just one word, yes or no.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Yes\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -793,17 +790,17 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Briefly copy any advice from the TEXT that may be useful for a similar but different task in the future. But if no advice is present, just respond with 'none'.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Save the above code in a file named `reverse_string.py`, then execute it.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -830,34 +827,34 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Briefly copy just the task from the TEXT, then stop. Don't solve it, and don't include any advice.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Save the above code in a file named `reverse_string.py`, then execute it. This script defines the `reverse_string` function and demonstrates its usage by reversing the string \"Hello, World!\". It will print both the original and reversed strings.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Save the above code in a file named `reverse_string.py`, then execute it. This script defines the `reverse_string` function and demonstrates its usage by reversing the string \"Hello, World!\". It will print both the original and reversed strings.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Summarize very briefly, in general terms, the type of task described in the TEXT. Leave out details that might not appear in a similar problem.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "The task involves saving a script to a file, executing it, and demonstrating a function that reverses a string.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
-      "REMEMBER THIS TASK-ADVICE PAIR\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[93m\n",
+      "REMEMBER THIS TASK-ADVICE PAIR\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -884,17 +881,17 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Does the TEXT contain information that could be committed to memory? Answer with just one word, yes or no.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Yes\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -921,17 +918,17 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Imagine that the user forgot this information in the TEXT. How would they ask you for this information? Include no other text in your response.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "How do I reverse a string in Python?\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Sure, I'll provide you with a Python function that takes a string as input and returns the reversed string. Here is the complete code:\n",
       "\n",
@@ -958,12 +955,12 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Copy the information from the TEXT that should be committed to memory. Add no explanation.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "```python\n",
       "# filename: reverse_string.py\n",
@@ -985,11 +982,11 @@
       "```\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
-      "REMEMBER THIS QUESTION-ANSWER PAIR\u001B[0m\n",
-      "\u001B[31m\n",
-      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to assistant):\n",
+      "\u001b[93m\n",
+      "REMEMBER THIS QUESTION-ANSWER PAIR\u001b[0m\n",
+      "\u001b[31m\n",
+      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to assistant):\n",
       "\n",
       "exitcode: 0 (execution succeeded)\n",
       "Code output: \n",
@@ -998,7 +995,7 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33massistant\u001B[0m (to user_proxy):\n",
+      "\u001b[33massistant\u001b[0m (to user_proxy):\n",
       "\n",
       "The code executed successfully, and the output is correct. The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
@@ -1008,9 +1005,9 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
-      "LOOK FOR RELEVANT MEMOS, AS QUESTION-ANSWER PAIRS\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[93m\n",
+      "LOOK FOR RELEVANT MEMOS, AS QUESTION-ANSWER PAIRS\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "The code executed successfully, and the output is correct. The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
@@ -1020,19 +1017,19 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Does any part of the TEXT ask the agent to perform a task or solve a problem? Answer with just one word, yes or no.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Yes\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
-      "LOOK FOR RELEVANT MEMOS, AS TASK-ADVICE PAIRS\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[93m\n",
+      "LOOK FOR RELEVANT MEMOS, AS TASK-ADVICE PAIRS\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "The code executed successfully, and the output is correct. The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
@@ -1042,32 +1039,32 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Copy just the task from the TEXT, then stop. Don't solve it, and don't include any advice.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "If you have any other tasks or need further assistance, feel free to ask.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "If you have any other tasks or need further assistance, feel free to ask.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Summarize very briefly, in general terms, the type of task described in the TEXT. Leave out details that might not appear in a similar problem.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "The task described in the TEXT involves offering help or assistance with various tasks.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
+      "\u001b[93m\n",
       "MEMOS APPENDED TO LAST MESSAGE...\n",
       "\n",
       "# Memories that might help\n",
@@ -1078,8 +1075,8 @@
       "- Code should be saved in a file named 'reverse_string.py'\n",
       "- Prefers camelCase for variable names\n",
       "\n",
-      "\u001B[0m\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[0m\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "The code executed successfully, and the output is correct. The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
@@ -1089,17 +1086,17 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Does any part of the TEXT ask the agent to perform a task or solve a problem? Answer with just one word, yes or no.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Yes\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "The code executed successfully, and the output is correct. The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
@@ -1109,17 +1106,17 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Briefly copy any advice from the TEXT that may be useful for a similar but different task in the future. But if no advice is present, just respond with 'none'.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "none\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "The code executed successfully, and the output is correct. The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
@@ -1129,17 +1126,17 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Does the TEXT contain information that could be committed to memory? Answer with just one word, yes or no.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "Yes\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "The code executed successfully, and the output is correct. The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
@@ -1149,17 +1146,17 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Imagine that the user forgot this information in the TEXT. How would they ask you for this information? Include no other text in your response.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "What was the original string that was reversed to \"!dlroW ,olleH\"?\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "The code executed successfully, and the output is correct. The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
@@ -1169,18 +1166,18 @@
       "\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33muser_proxy\u001B[0m (to analyzer):\n",
+      "\u001b[33muser_proxy\u001b[0m (to analyzer):\n",
       "\n",
       "Copy the information from the TEXT that should be committed to memory. Add no explanation.\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[33manalyzer\u001B[0m (to user_proxy):\n",
+      "\u001b[33manalyzer\u001b[0m (to user_proxy):\n",
       "\n",
       "The string \"Hello, World!\" was successfully reversed to \"!dlroW ,olleH\".\n",
       "\n",
       "--------------------------------------------------------------------------------\n",
-      "\u001B[93m\n",
-      "REMEMBER THIS QUESTION-ANSWER PAIR\u001B[0m\n"
+      "\u001b[93m\n",
+      "REMEMBER THIS QUESTION-ANSWER PAIR\u001b[0m\n"
      ]
     },
     {
@@ -1194,7 +1191,10 @@
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 21
+   "source": [
+    "# Initiate Chat w/ Teachability + Memory\n",
+    "user_proxy.initiate_chat(gpt_assistant, message=user_query)"
+   ]
   }
  ],
  "metadata": {

docs/_snippets/paper-release.mdx

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

docs/api-reference.mdx

@@ -4,6 +4,8 @@ icon: "info"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Mem0 provides a powerful set of APIs that allow you to integrate advanced memory management capabilities into your applications. Our APIs are designed to be intuitive, efficient, and scalable, enabling you to create, retrieve, update, and delete memories across various entities such as users, agents, apps, and runs.
 
 ## Key Features

docs/api-reference/memory/feedback.mdx

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

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

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

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

@@ -14,11 +14,11 @@ The v2 search API is powerful and flexible, allowing for more precise memory ret
 
   <CodeGroup>
   ```python Code
-  related_memories = m.vsearch(
+  related_memories = m.search(
       query="What are Alice's hobbies?",
       version="v2",
       filters={
-          "AND": [
+          "OR": [
               {
                 "user_id": "alice"
               },

docs/changelog.mdx

@@ -0,0 +1,508 @@
+---
+title: "Product Updates"
+mode: "wide"
+---
+
+<Snippet file="paper-release.mdx" />
+
+<Tabs>
+<Tab title="Python">
+
+<Update label="2025-04-26" description="v0.1.94">
+
+**New Features:**
+- **Integrations:** Added Memgraph integration
+- **Memory:** Added timestamp support
+- **Vector Stores:** Added reset function for VectorDBs
+
+**Improvements:**
+- **Documentation:** 
+  - Updated timestamp and expiration_date documentation
+  - Fixed v2 search documentation
+  - Added "memory" in EC "Custom config" section
+  - Fixed typos in the json config sample
+
+</Update>
+
+<Update label="2025-04-21" description="v0.1.93">
+
+**Improvements:**
+- **Vector Stores:** Initialized embedding_model_dims in all vectordbs
+
+**Bug Fixes:**
+- **Documentation:** Fixed agno link
+
+</Update>
+
+<Update label="2025-04-18" description="v0.1.92">
+
+**New Features:**
+- **Memory:** Added Memory Reset functionality
+- **Client:** Added support for Custom Instructions
+- **Examples:** Added Fitness Checker powered by memory
+
+**Improvements:**
+- **Core:** Updated capture_event
+- **Documentation:** Fixed curl for v2 get_all
+
+**Bug Fixes:**
+- **Vector Store:** Fixed user_id functionality
+- **Client:** Various client improvements
+
+</Update>
+
+<Update label="2025-04-16" description="v0.1.91">
+
+**New Features:**
+- **LLM Integrations:** Added Azure OpenAI Embedding Model
+- **Examples:** 
+  - Added movie recommendation using grok3
+  - Added Voice Assistant using Elevenlabs
+
+**Improvements:**
+- **Documentation:** 
+  - Added keywords AI
+  - Reformatted navbar page URLs
+  - Updated changelog
+  - Updated openai.mdx
+- **FAISS:** Silenced FAISS info logs
+
+</Update>
+
+<Update label="2025-04-11" description="v0.1.90">
+
+**New Features:**
+- **LLM Integrations:** Added Mistral AI as LLM provider
+
+**Improvements:**
+- **Documentation:** 
+  - Updated changelog
+  - Fixed memory exclusion example
+  - Updated xAI documentation
+  - Updated YouTube Chrome extension example documentation
+
+**Bug Fixes:**
+- **Core:** Fixed EmbedderFactory.create() in GraphMemory
+- **Azure OpenAI:** Added patch to fix Azure OpenAI
+- **Telemetry:** Fixed telemetry issue
+
+</Update>
+
+<Update label="2025-04-11" description="v0.1.89">
+
+**New Features:**
+- **Langchain Integration:** Added support for Langchain VectorStores
+- **Examples:** 
+  - Added personal assistant example
+  - Added personal study buddy example
+  - Added YouTube assistant Chrome extension example
+  - Added agno example
+  - Updated OpenAI Responses API examples
+- **Vector Store:** Added capability to store user_id in vector database
+- **Async Memory:** Added async support for OSS
+
+**Improvements:**
+- **Documentation:** Updated formatting and examples
+
+</Update>
+
+<Update label="2025-04-09" description="v0.1.87">
+
+**New Features:**
+- **Upstash Vector:** Added support for Upstash Vector store
+
+**Improvements:**
+- **Code Quality:** Removed redundant code lines
+- **Build:** Updated MAKEFILE
+- **Documentation:** Updated memory export documentation
+
+</Update>
+
+<Update label="2025-04-07" description="v0.1.86">
+
+**Improvements:**
+- **FAISS:** Added embedding_dims parameter to FAISS vector store
+
+</Update>
+
+<Update label="2025-04-07" description="v0.1.84">
+
+**New Features:**
+- **Langchain Embedder:** Added Langchain embedder integration
+
+**Improvements:**
+- **Langchain LLM:** Updated Langchain LLM integration to directly pass the Langchain object LLM
+</Update>
+
+<Update label="2025-04-07" description="v0.1.83">
+
+**Bug Fixes:**
+- **Langchain LLM:** Fixed issues with Langchain LLM integration
+</Update>
+
+<Update label="2025-04-07" description="v0.1.82">
+
+**New Features:**
+- **LLM Integrations:** Added support for Langchain LLMs, Google as new LLM and embedder
+- **Development:** Added development docker compose
+
+**Improvements:**
+- **Output Format:** Set output_format='v1.1' and updated documentation
+
+**Documentation:**
+- **Integrations:** Added LMStudio and Together.ai documentation
+- **API Reference:** Updated output_format documentation
+- **Integrations:** Added PipeCat integration documentation
+- **Integrations:** Added Flowise integration documentation for Mem0 memory setup
+
+**Bug Fixes:**
+- **Tests:** Fixed failing unit tests
+</Update>
+
+<Update label="2025-04-02" description="v0.1.79">
+
+**New Features:**
+- **FAISS Support:** Added FAISS vector store support
+
+</Update>
+
+<Update label="2025-04-02" description="v0.1.78">
+
+**New Features:**
+- **Livekit Integration:** Added Mem0 livekit example
+- **Evaluation:** Added evaluation framework and tools
+
+**Documentation:**
+- **Multimodal:** Updated multimodal documentation
+- **Examples:** Added examples for email processing
+- **API Reference:** Updated API reference section
+- **Elevenlabs:** Added Elevenlabs integration example
+
+**Bug Fixes:**
+- **OpenAI Environment Variables:** Fixed issues with OpenAI environment variables
+- **Deployment Errors:** Added `package.json` file to fix deployment errors
+- **Tools:** Fixed tools issues and improved formatting
+- **Docs:** Updated API reference section for `expiration date`
+</Update>
+
+<Update label="2025-03-26" description="v0.1.77">
+
+**Bug Fixes:**
+- **OpenAI Environment Variables:** Fixed issues with OpenAI environment variables
+- **Deployment Errors:** Added `package.json` file to fix deployment errors
+- **Tools:** Fixed tools issues and improved formatting
+- **Docs:** Updated API reference section for `expiration date`
+</Update>
+
+<Update label="2025-03-19" description="v0.1.76">
+**New Features:**
+- **Supabase Vector Store:** Added support for Supabase Vector Store
+- **Supabase History DB:** Added Supabase History DB to run Mem0 OSS on Serverless
+- **Feedback Method:** Added feedback method to client
+
+**Bug Fixes:**
+- **Azure OpenAI:** Fixed issues with Azure OpenAI
+- **Azure AI Search:** Fixed test cases for Azure AI Search
+</Update>
+
+</Tab>
+
+<Tab title="TypeScript">
+
+<Update label="2025-05-08" description="v2.1.25">
+**Improvements:**
+- **Client:** Improved error handling in client.
+</Update>
+
+<Update label="2025-05-06" description="v2.1.24">
+**New Features:**
+- **Client:** Added new param `output_format` to match Python SDK.
+- **Client:** Added new enum `OutputFormat` for `v1.0` and `v1.1`
+</Update>
+
+<Update label="2025-05-05" description="v2.1.23">
+**New Features:**
+- **Client:** Updated `deleteUsers` to use `v2` API.
+- **Client:** Deprecated `deleteUser` and added deprecation warning.
+</Update>
+
+<Update label="2025-05-02" description="v2.1.22">
+**New Features:**
+- **Client:** Updated `deleteUser` to use `entity_id` and `entity_type`
+</Update>
+
+<Update label="2025-05-01" description="v2.1.21">
+**Improvements:**
+- **OSS SDK:** Bumped version of `@anthropic-ai/sdk` to `0.40.1`
+</Update>
+
+<Update label="2025-04-28" description="v2.1.20">
+**Improvements:**
+- **Client:** Fixed `organizationId` and `projectId` being asssigned to default in `ping` method
+</Update>
+
+<Update label="2025-04-22" description="v2.1.19">
+**Improvements:**
+- **Client:** Added support for `timestamps`
+</Update>
+
+<Update label="2025-04-17" description="v2.1.18">
+**Improvements:**
+- **Client:** Added support for custom instructions
+</Update>
+
+<Update label="2025-04-15" description="v2.1.17">
+**New Features:**
+- **OSS SDK:** Added support for Langchain LLM
+- **OSS SDK:** Added support for Langchain Embedder
+- **OSS SDK:** Added support for Langchain Vector Store
+- **OSS SDK:** Added support for Azure OpenAI Embedder
+
+
+**Improvements:**
+- **OSS SDK:** Changed `model` in LLM and Embedder to use type any from `string` to use langchain llm models
+- **OSS SDK:** Added client to vector store config for langchain vector store
+- **OSS SDK:** - Updated Azure OpenAI to use new OpenAI SDK
+</Update>
+
+<Update label="2025-04-11" description="v2.1.16-patch.1">
+**Bug Fixes:**
+- **Azure OpenAI:** Fixed issues with Azure OpenAI
+</Update>
+
+<Update label="2025-04-11" description="v2.1.16">
+**New Features:**
+- **Azure OpenAI:** Added support for Azure OpenAI
+- **Mistral LLM:** Added Mistral LLM integration in OSS
+
+**Improvements:**
+- **Zod:** Updated Zod to 3.24.1 to avoid conflicts with other packages
+</Update>
+
+<Update label="2025-04-09" description="v2.1.15">
+**Improvements:**
+- **Client:** Added support for Mem0 to work with Chrome Extensions
+</Update>
+
+<Update label="2025-04-01" description="v2.1.14">
+**New Features:**
+- **Mastra Example:** Added Mastra example
+- **Integrations:** Added Flowise integration documentation for Mem0 memory setup
+
+**Improvements:**
+- **Demo:** Updated Demo Mem0AI
+- **Client:** Enhanced Ping method in Mem0 Client
+- **AI SDK:** Updated AI SDK implementation
+</Update>
+
+<Update label="2025-03-29" description="v2.1.13">
+**Improvements:**
+- **Introuced `ping` method to check if API key is valid and populate org/project id**
+</Update>
+
+<Update label="2025-03-29" description="AI SDK v1.0.0">
+**New Features:**
+- **Vercel AI SDK Update:** Support threshold and rerank
+
+**Improvements:**
+- **Made add calls async to avoid blocking**
+- **Bump `mem0ai` to use `2.1.12`**
+
+</Update>
+
+<Update label="2025-03-26" description="v2.1.12">
+**New Features:**
+- **Mem0 OSS:** Support infer param
+
+**Improvements:**
+- **Updated Supabase TS Docs**
+- **Made package size smaller**
+
+</Update>
+
+<Update label="2025-03-19" description="v2.1.11">
+**New Features:**
+- **Supabase Vector Store Integration**
+- **Feedback Method**
+</Update>
+
+</Tab>
+
+<Tab title="Platform">
+
+<Update label="2025-04-26" description="">
+
+**Improvements:**
+- **Performance:** Parallelized embedding calls
+- **Monitoring:** Added timing for LLM calls
+- **Search:** Added category checking in Search V2
+- **Bug Fixes:** Fixed issues with ADD filters
+- **Graph:** Implemented new graph updates
+
+</Update>
+
+<Update label="2025-04-25" description="">
+
+**Improvements:**
+- **Memory:** Fixed memory export functionality
+- **Analytics:** Added logging for project
+
+</Update>
+
+<Update label="2025-04-24" description="">
+
+**Improvements:**
+- **Output:** Added memory_type display for ADD output
+
+</Update>
+
+<Update label="2025-04-23" description="">
+
+**New Features:**
+- **UI:** Added new Pricing Component
+- **Memory:** Implemented Long/Short term memory categorization
+- **Output:** Modified serializer to hide memory_type
+
+**Documentation:**
+- Updated README for deployment
+
+</Update>
+
+<Update label="2025-04-22" description="">
+
+**New Features:**
+- **Memory:** Added timestamp to ADD call
+
+**Bug Fixes:**
+- Fixed issues with coreV2
+
+</Update>
+
+<Update label="2025-04-21" description="">
+
+**New Features:**
+- **Memory:** Implemented backdating with migrations and backfilling script
+
+</Update>
+
+<Update label="2025-04-17" description="">
+
+**New Features:**
+- **Billing:** Integrated Stripe Billing Dashboard
+- **Admin:** Added webhook creation functionality
+
+**Bug Fixes:**
+- Fixed Users Page issues
+- Fixed Custom Categories
+- Fixed Table components
+- Updated Stripe configuration
+
+</Update>
+
+<Update label="2025-04-16" description="">
+
+**Improvements:**
+- **Performance:** Made Admin panel and Memory Page faster
+- **Security:** Implemented active session cancellation
+- **Analytics:** Added Stripe customer ID capture
+
+</Update>
+
+<Update label="2025-04-12" description="">
+
+**New Features:**
+- **Memory Management:** 
+  - Added ability to delete memories from Project level with filters
+  - Added delete memories capability on Memories Page
+- **Memory Visualization:** Released V1 Graph Memory Visualization
+- **Graph Playground:** Enabled for @mem0.ai users
+- **Notifications:** Added email alerts to organization owners when new members join
+- **Memory Export:** Added date support for filtering memory exports
+
+**Improvements:**
+- **Performance:** 
+  - Optimized graph for better performance
+  - Optimized database calls in ADD method
+- **Analytics:** Added flagging of paid users in Posthog
+- **CI/CD:** Improved CI pipeline and fixed lint issues
+
+</Update>
+
+<Update label="2025-04-10" description="">
+
+**New Features:**
+- **Notifications:** Implemented email notifications for organization owners when new members join
+
+**Improvements:**
+- **CI/CD:** Fixed Dockerfile for CI tests
+
+</Update>
+
+<Update label="2025-04-09" description="">
+
+**Improvements:**
+- **Integrations:** Updated chat model for Together Qwen
+- **Platform:** Removed older platforms
+- **Bug Fixes:** Fixed FILTER_MAPPING
+
+</Update>
+
+<Update label="2025-04-03" description="">
+
+**New Features:**
+- **Memory:** Added implicit memory capabilities
+- **API:** Improved implicit lambda and get_all v2 functionality
+
+</Update>
+
+<Update label="2025-04-02" description="">
+
+**New Features:**
+- **Integrations:** Added Clay integration
+
+**Improvements:**
+- **Integrations:** Removed deepseek coder from Together
+- **API:** Added custom instructions for add v2
+
+</Update>
+
+<Update label="2025-03-31" description="">
+
+**Security:**
+- **Validation:** Added key validation in messages
+
+</Update>
+
+<Update label="2025-03-28" description="">
+- **Updated Playground Prompt**
+- **Send Email on User Addition to Org/Proj**
+- **Fix Search Entity**
+</Update>
+
+<Update label="2025-03-19" description="">
+- **General Stability & Performance Improvements**
+</Update>
+
+</Tab>
+
+<Tab title="Vercel AI SDK">
+
+<Update label="2025-05-10" description="v1.0.4">
+**New Features:**
+- **Vercel AI SDK:** Added support for new param `output_format`.
+</Update>
+
+<Update label="2025-05-08" description="v1.0.3">
+**Improvements:**
+- **Vercel AI SDK:** Added support for graceful failure in cases services are down. 
+</Update>
+
+<Update label="2025-05-01" description="v1.0.1">
+**New Features:**
+- **Vercel AI SDK:** Added support for graph memories
+</Update>
+
+</Tab>
+
+</Tabs>
+

docs/components/embedders/config.mdx

@@ -4,6 +4,8 @@ icon: "gear"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.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.
 
 ## How to define configurations?
@@ -84,6 +86,7 @@ Here's a comprehensive list of all parameters that can be used across different
 | `memory_add_embedding_type` | The type of embedding to use for the add memory action                       | VertexAI            |
 | `memory_update_embedding_type` | The type of embedding to use for the update memory action                       | VertexAI            |
 | `memory_search_embedding_type` | The type of embedding to use for the search memory action                       | VertexAI            |
+| `lmstudio_base_url` | Base URL for LM Studio API                    | LM Studio         |
 </Tab>
 <Tab title="TypeScript">
 | Parameter | Description | Provider |

docs/components/embedders/models/aws_bedrock.mdx

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

docs/components/embedders/models/azure_openai.mdx

@@ -6,7 +6,8 @@ To use Azure OpenAI embedding models, set the `EMBEDDING_AZURE_OPENAI_API_KEY`,
 
 ### Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -46,6 +47,36 @@ messages = [
 m.add(messages, user_id="john")
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+    embedder: {
+        provider: "azure_openai",
+        config: {
+            model: "text-embedding-3-large",
+            modelProperties: {
+                endpoint: "your-api-base-url",
+                deployment: "your-deployment-name",
+                apiVersion: "version-to-use",
+            }
+        }
+    }
+}
+
+const memory = new Memory(config);
+
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+
+await memory.add(messages, { userId: "john" });
+```
+</CodeGroup>
+
 ### Config
 
 Here are the parameters available for configuring Azure OpenAI embedder:

docs/components/embedders/models/huggingface.mdx

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

docs/components/embedders/models/langchain.mdx

@@ -0,0 +1,146 @@
+---
+title: LangChain
+---
+
+Mem0 supports LangChain as a provider to access a wide range of embedding models. LangChain is a framework for developing applications powered by language models, making it easy to integrate various embedding providers through a consistent interface.
+
+For a complete list of available embedding models supported by LangChain, refer to the [LangChain Text Embedding documentation](https://python.langchain.com/docs/integrations/text_embedding/).
+
+## Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+from langchain_openai import OpenAIEmbeddings
+
+# Set necessary environment variables for your chosen LangChain provider
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+
+# Initialize a LangChain embeddings model directly
+openai_embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",
+    dimensions=1536
+)
+
+# Pass the initialized model to the config
+config = {
+    "embedder": {
+        "provider": "langchain",
+        "config": {
+            "model": openai_embeddings
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+```typescript TypeScript
+import { Memory } from "mem0ai";
+import { OpenAIEmbeddings } from "@langchain/openai";
+
+const embeddings = new OpenAIEmbeddings();
+const config = {
+    "embedder": {
+        "provider": "langchain",
+        "config": {
+            "model": embeddings
+        }
+    }
+}
+
+const memory = new Memory(config);
+
+const messages = [
+    { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
+    { role: "assistant", content: "How about a thriller movies? They can be quite engaging." },
+    { role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
+    { role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." }
+]
+
+memory.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+</CodeGroup>
+
+## Supported LangChain Embedding Providers
+
+LangChain supports a wide range of embedding providers, including:
+
+- OpenAI (`OpenAIEmbeddings`)
+- Cohere (`CohereEmbeddings`)
+- Google (`VertexAIEmbeddings`)
+- Hugging Face (`HuggingFaceEmbeddings`)
+- Sentence Transformers (`HuggingFaceEmbeddings`)
+- Azure OpenAI (`AzureOpenAIEmbeddings`)
+- Ollama (`OllamaEmbeddings`)
+- Together (`TogetherEmbeddings`)
+- And many more
+
+You can use any of these model instances directly in your configuration. For a complete and up-to-date list of available embedding providers, refer to the [LangChain Text Embedding documentation](https://python.langchain.com/docs/integrations/text_embedding/).
+
+## Provider-Specific Configuration
+
+When using LangChain as an embedder provider, you'll need to:
+
+1. Set the appropriate environment variables for your chosen embedding provider
+2. Import and initialize the specific model class you want to use
+3. Pass the initialized model instance to the config
+
+### Examples with Different Providers
+
+#### HuggingFace Embeddings
+
+```python
+from langchain_huggingface import HuggingFaceEmbeddings
+
+# Initialize a HuggingFace embeddings model
+hf_embeddings = HuggingFaceEmbeddings(
+    model_name="BAAI/bge-small-en-v1.5",
+    encode_kwargs={"normalize_embeddings": True}
+)
+
+config = {
+    "embedder": {
+        "provider": "langchain",
+        "config": {
+            "model": hf_embeddings
+        }
+    }
+}
+```
+
+#### Ollama Embeddings
+
+```python
+from langchain_ollama import OllamaEmbeddings
+
+# Initialize an Ollama embeddings model
+ollama_embeddings = OllamaEmbeddings(
+    model="nomic-embed-text"
+)
+
+config = {
+    "embedder": {
+        "provider": "langchain",
+        "config": {
+            "model": ollama_embeddings
+        }
+    }
+}
+```
+
+<Note>
+  Make sure to install the necessary LangChain packages and any provider-specific dependencies.
+</Note>
+
+## Config
+
+All available parameters for the `langchain` embedder config are present in [Master List of All Params in Config](../config).

docs/components/embedders/models/lmstudio.mdx

@@ -0,0 +1,38 @@
+You can use embedding models from LM Studio to run Mem0 locally.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
+
+config = {
+    "embedder": {
+        "provider": "lmstudio",
+        "config": {
+            "model": "nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf"
+        }
+    }
+}
+
+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 Ollama 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` |
+| `embedding_dims` | Dimensions of the embedding model | `1536` |
+| `lmstudio_base_url` | Base URL for LM Studio connection | `http://localhost:1234/v1` |

docs/components/embedders/overview.mdx

@@ -4,6 +4,8 @@ icon: "info"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Mem0 offers support for various embedding models, allowing users to choose the one that best suits their needs.
 
 ## Supported Embedders
@@ -22,6 +24,9 @@ See the list of supported embedders below.
   <Card title="Gemini" href="/components/embedders/models/gemini"></Card>
   <Card title="Vertex AI" href="/components/embedders/models/vertexai"></Card>
   <Card title="Together" href="/components/embedders/models/together"></Card>
+  <Card title="LM Studio" href="/components/embedders/models/lmstudio"></Card>
+  <Card title="Langchain" href="/components/embedders/models/langchain"></Card>
+  <Card title="AWS Bedrock" href="/components/embedders/models/aws_bedrock"></Card>
 </CardGroup>
 
 ## Usage

docs/components/llms/config.mdx

@@ -4,6 +4,8 @@ icon: "gear"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## How to define configurations?
 
 <Tabs>
@@ -29,7 +31,7 @@ iconType: "solid"
 Config values are applied in the following order of precedence (from highest to lowest):
 
 1. Values explicitly set in the `config` object/dictionary
-2. Environment variables (e.g., `OPENAI_API_KEY`, `OPENAI_API_BASE`)
+2. Environment variables (e.g., `OPENAI_API_KEY`, `OPENAI_BASE_URL`)
 3. Default values defined in the LLM implementation
 
 This means that values specified in the `config` will override corresponding environment variables, which in turn override default values.
@@ -108,6 +110,7 @@ Here's a comprehensive list of all parameters that can be used across different
     | `azure_kwargs`       | Azure LLM args for initialization             | AzureOpenAI       |
     | `deepseek_base_url`  | Base URL for DeepSeek API                     | DeepSeek          |
     | `xai_base_url`       | Base URL for XAI API                          | XAI               |
+    | `lmstudio_base_url`  | Base URL for LM Studio API                    | LM Studio         |
   </Tab>
   <Tab title="TypeScript">
     | Parameter            | Description                                   | Provider          |

docs/components/llms/models/anthropic.mdx

@@ -2,6 +2,8 @@
 title: Anthropic
 ---
 
+<Snippet file="paper-release.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).
 
 ## Usage

docs/components/llms/models/aws_bedrock.mdx

@@ -2,6 +2,8 @@
 title: AWS Bedrock
 ---
 
+<Snippet file="paper-release.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)
@@ -13,16 +15,15 @@ title: AWS Bedrock
 import os
 from mem0 import Memory
 
-os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
-os.environ['AWS_REGION'] = 'us-east-1'
-os.environ["AWS_ACCESS_KEY"] = "xx"
+os.environ['AWS_REGION'] = 'us-west-2'
+os.environ["AWS_ACCESS_KEY_ID"] = "xx"
 os.environ["AWS_SECRET_ACCESS_KEY"] = "xx"
 
 config = {
     "llm": {
         "provider": "aws_bedrock",
         "config": {
-            "model": "arn:aws:bedrock:us-east-1:123456789012:model/your-model-name",
+            "model": "anthropic.claude-3-5-haiku-20241022-v1:0",
             "temperature": 0.2,
             "max_tokens": 2000,
         }

docs/components/llms/models/azure_openai.mdx

@@ -2,14 +2,24 @@
 title: Azure OpenAI
 ---
 
+<Snippet file="paper-release.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/).
 
+> **Note**: The following are currently unsupported with reasoning models `Parallel tool calling`,`temperature`, `top_p`, `presence_penalty`, `frequency_penalty`, `logprobs`, `top_logprobs`, `logit_bias`, `max_tokens`
+
+
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
+os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
+
 os.environ["LLM_AZURE_OPENAI_API_KEY"] = "your-api-key"
 os.environ["LLM_AZURE_DEPLOYMENT"] = "your-deployment-name"
 os.environ["LLM_AZURE_ENDPOINT"] = "your-api-base-url"
@@ -45,7 +55,38 @@ messages = [
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
-We also support the new [OpenAI structured-outputs](https://platform.openai.com/docs/guides/structured-outputs/introduction) model.
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  llm: {
+    provider: 'azure_openai',
+    config: {
+      apiKey: process.env.AZURE_OPENAI_API_KEY || '',
+      modelProperties: {
+        endpoint: 'https://your-api-base-url',
+        deployment: 'your-deployment-name',
+        modelName: 'your-model-name',
+        apiVersion: 'version-to-use',
+        // Any other parameters you want to pass to the Azure OpenAI API
+      },
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
+
+We also support the new [OpenAI structured-outputs](https://platform.openai.com/docs/guides/structured-outputs/introduction) model. Typescript SDK does not support the `azure_openai_structured` model yet.
 
 ```python
 import os

docs/components/llms/models/deepseek.mdx

@@ -2,6 +2,8 @@
 title: DeepSeek
 ---
 
+<Snippet file="paper-release.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

docs/components/llms/models/gemini.mdx

@@ -2,6 +2,8 @@
 title: Gemini
 ---
 
+<Snippet file="paper-release.mdx" />
+
 To use Gemini model, you have to set the `GEMINI_API_KEY` environment variable. You can obtain the Gemini API key from the [Google AI Studio](https://aistudio.google.com/app/apikey)
 
 ## Usage

docs/components/llms/models/google_AI.mdx

@@ -2,6 +2,8 @@
 title: Google AI
 ---
 
+<Snippet file="paper-release.mdx" />
+
 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)
 
 ## Usage

docs/components/llms/models/groq.mdx

@@ -2,6 +2,8 @@
 title: Groq
 ---
 
+<Snippet file="paper-release.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.

docs/components/llms/models/langchain.mdx

@@ -0,0 +1,110 @@
+---
+title: LangChain
+---
+
+<Snippet file="paper-release.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.
+
+For a complete list of available chat models supported by LangChain, refer to the [LangChain Chat Models documentation](https://python.langchain.com/docs/integrations/chat).
+
+## Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+from langchain_openai import ChatOpenAI
+
+# Set necessary environment variables for your chosen LangChain provider
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+
+# Initialize a LangChain model directly
+openai_model = ChatOpenAI(
+    model="gpt-4o",
+    temperature=0.2,
+    max_tokens=2000
+)
+
+# Pass the initialized model to the config
+config = {
+    "llm": {
+        "provider": "langchain",
+        "config": {
+            "model": openai_model
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+```typescript TypeScript
+import { Memory } from "mem0ai";
+import { ChatOpenAI } from "@langchain/openai";
+
+const openai_model = new ChatOpenAI({
+    model: "gpt-4o",
+    temperature: 0.2,
+    max_tokens: 2000
+})
+
+const config = {
+    "llm": {
+        "provider": "langchain",
+        "config": {
+            "model": openai_model
+        }
+    }
+}
+
+const memory = new Memory(config);
+
+const messages = [
+    { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
+    { role: "assistant", content: "How about a thriller movies? They can be quite engaging." },
+    { role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
+    { role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." }
+]
+
+memory.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+</CodeGroup>
+
+## Supported LangChain Providers
+
+LangChain supports a wide range of LLM providers, including:
+
+- OpenAI (`ChatOpenAI`)
+- Anthropic (`ChatAnthropic`)
+- Google (`ChatGoogleGenerativeAI`, `ChatGooglePalm`)
+- Mistral (`ChatMistralAI`)
+- Ollama (`ChatOllama`)
+- Azure OpenAI (`AzureChatOpenAI`)
+- HuggingFace (`HuggingFaceChatEndpoint`)
+- And many more
+
+You can use any of these model instances directly in your configuration. For a complete and up-to-date list of available providers, refer to the [LangChain Chat Models documentation](https://python.langchain.com/docs/integrations/chat).
+
+## Provider-Specific Configuration
+
+When using LangChain as a provider, you'll need to:
+
+1. Set the appropriate environment variables for your chosen LLM provider
+2. Import and initialize the specific model class you want to use
+3. Pass the initialized model instance to the config
+
+<Note>
+  Make sure to install the necessary LangChain packages and any provider-specific dependencies.
+</Note>
+
+## Config
+
+All available parameters for the `langchain` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/litellm.mdx

@@ -1,3 +1,5 @@
+<Snippet file="paper-release.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

docs/components/llms/models/lmstudio.mdx

@@ -0,0 +1,84 @@
+---
+title: LM Studio
+---
+
+<Snippet file="paper-release.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
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "your-api-key" # used for embedding model
+
+config = {
+    "llm": {
+        "provider": "lmstudio",
+        "config": {
+            "model": "lmstudio-community/Meta-Llama-3.1-70B-Instruct-GGUF/Meta-Llama-3.1-70B-Instruct-IQ2_M.gguf",
+            "temperature": 0.2,
+            "max_tokens": 2000,
+            "lmstudio_base_url": "http://localhost:1234/v1", # default LM Studio API URL
+        }
+    }
+}
+
+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"})
+```
+</CodeGroup>
+
+### Running Completely Locally
+
+You can also use LM Studio for both LLM and embedding to run Mem0 entirely locally:
+
+```python
+from mem0 import Memory
+
+# No external API keys needed!
+config = {
+    "llm": {
+        "provider": "lmstudio"
+    },
+    "embedder": {
+        "provider": "lmstudio"
+    }
+}
+
+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="alice123", metadata={"category": "movies"})
+```
+
+<Note>
+  When using LM Studio for both LLM and embedding, make sure you have:
+  1. An LLM model loaded for generating responses
+  2. An embedding model loaded for vector embeddings
+  3. The server enabled with the correct endpoints accessible
+</Note>
+
+<Note>
+  To use LM Studio, you need to:
+  1. Download and install [LM Studio](https://lmstudio.ai/)
+  2. Start a local server from the "Server" tab
+  3. Set the appropriate `lmstudio_base_url` in your configuration (default is usually http://localhost:1234/v1)
+</Note>
+
+## Config
+
+All available parameters for the `lmstudio` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/mistral_AI.mdx

@@ -2,11 +2,14 @@
 title: Mistral AI
 ---
 
-To use mistral's models, please Obtain the Mistral AI api key from their [console](https://console.mistral.ai/). Set the `MISTRAL_API_KEY` environment variable to use the model as given below in the example.
+<Snippet file="paper-release.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
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -34,6 +37,32 @@ messages = [
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  llm: {
+    provider: 'mistral',
+    config: {
+      apiKey: process.env.MISTRAL_API_KEY || '',
+      model: 'mistral-tiny-latest', // Or 'mistral-small-latest', 'mistral-medium-latest', etc.
+      temperature: 0.1,
+      maxTokens: 2000,
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
+```
+</CodeGroup>
+
 ## Config
 
 All available parameters for the `litellm` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/ollama.mdx

@@ -1,3 +1,5 @@
+<Snippet file="paper-release.mdx" />
+
 You can use LLMs from Ollama to run Mem0 locally. These [models](https://ollama.com/search?c=tools) support tool support.
 
 ## Usage

docs/components/llms/models/openai.mdx

@@ -2,6 +2,8 @@
 title: OpenAI
 ---
 
+<Snippet file="paper-release.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).
 
 ## Usage
@@ -92,10 +94,6 @@ config = {
 m = Memory.from_config(config)
 ```
 
-<Note>
-  OpenAI structured-outputs is currently only available in the Python implementation.
-</Note>
-
 ## Config
 
-All available parameters for the `openai` config are present in [Master List of All Params in Config](../config).
+All available parameters for the `openai` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/together.mdx

@@ -1,3 +1,5 @@
+<Snippet file="paper-release.mdx" />
+
 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).
 
 ## Usage

docs/components/llms/models/xAI.mdx

@@ -2,6 +2,8 @@
 title: xAI
 ---
 
+<Snippet file="paper-release.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.
@@ -19,7 +21,7 @@ config = {
     "llm": {
         "provider": "xai",
         "config": {
-            "model": "grok-2-latest",
+            "model": "grok-3-beta",
             "temperature": 0.1,
             "max_tokens": 2000,
         }

docs/components/llms/overview.mdx

@@ -4,6 +4,8 @@ icon: "info"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.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
@@ -32,6 +34,8 @@ To view all supported llms, visit the [Supported LLMs](./models).
   <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="LM Studio" href="/components/llms/models/lmstudio" />
+  <Card title="Langchain" href="/components/llms/models/langchain" />
 </CardGroup>
 
 ## Structured vs Unstructured Outputs

docs/components/vectordbs/config.mdx

@@ -4,11 +4,13 @@ icon: "gear"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.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","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")
   - `config`: A nested dictionary containing provider-specific settings
 
 

docs/components/vectordbs/dbs/azure.mdx

@@ -0,0 +1,99 @@
+---
+title: Azure AI Search
+---
+
+[Azure AI Search](https://learn.microsoft.com/azure/search/search-what-is-azure-search/) (formerly known as "Azure Cognitive Search") provides secure information retrieval at scale over user-owned content in traditional and generative AI search applications.
+
+## Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"   # This key is used for embedding purpose
+
+config = {
+    "vector_store": {
+        "provider": "azure_ai_search",
+        "config": {
+            "service_name": "ai-search-test",
+            "api_key": "*****",
+            "collection_name": "mem0", 
+            "embedding_model_dims": 1536
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+
+## Using binary compression for large vector collections
+
+```python
+config = {
+    "vector_store": {
+        "provider": "azure_ai_search",
+        "config": {
+            "service_name": "ai-search-test",
+            "api_key": "*****",
+            "collection_name": "mem0", 
+            "embedding_model_dims": 1536,
+            "compression_type": "binary",
+            "use_float16": True  # Use half precision for storage efficiency
+        }
+    }
+}
+```
+
+## Using hybrid search
+
+```python
+config = {
+    "vector_store": {
+        "provider": "azure_ai_search",
+        "config": {
+            "service_name": "ai-search-test",
+            "api_key": "*****",
+            "collection_name": "mem0", 
+            "embedding_model_dims": 1536,
+            "hybrid_search": True,
+            "vector_filter_mode": "postFilter"
+        }
+    }
+}
+```
+
+## Configuration Parameters
+
+| Parameter | Description | Default Value | Options |
+| --- | --- | --- | --- |
+| `service_name` | Azure AI Search service name | Required | - |
+| `api_key` | API key of the Azure AI Search service | Required | - |
+| `collection_name` | The name of the collection/index to store vectors | `mem0` | Any valid index name |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` | Any integer value |
+| `compression_type` | Type of vector compression to use | `none` | `none`, `scalar`, `binary` |
+| `use_float16` | Store vectors in half precision (Edm.Half) | `False` | `True`, `False` |
+| `vector_filter_mode` | Vector filter mode to use | `preFilter` | `postFilter`, `preFilter` |
+| `hybrid_search` | Use hybrid search | `False` | `True`, `False` |
+
+## Notes on Configuration Options
+
+- **compression_type**: 
+  - `none`: No compression, uses full vector precision
+  - `scalar`: Scalar quantization with reasonable balance of speed and accuracy
+  - `binary`: Binary quantization for maximum compression with some accuracy trade-off
+
+- **vector_filter_mode**:
+  - `preFilter`: Applies filters before vector search (faster)
+  - `postFilter`: Applies filters after vector search (may provide better relevance)
+
+- **use_float16**: Using half precision (float16) reduces storage requirements but may slightly impact accuracy. Useful for very large vector collections.
+
+- **Filterable Fields**: The implementation automatically extracts `user_id`, `run_id`, and `agent_id` fields from payloads for filtering.

docs/components/vectordbs/dbs/azure_ai_search.mdx

@@ -1,44 +0,0 @@
-[Azure AI Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search/) (formerly known as "Azure Cognitive Search") provides secure information retrieval at scale over user-owned content in traditional and generative AI search applications.
-
-### Usage
-
-```python
-import os
-from mem0 import Memory
-
-os.environ["OPENAI_API_KEY"] = "sk-xx"   #this key is used for embedding purpose
-
-config = {
-    "vector_store": {
-        "provider": "azure_ai_search",
-        "config": {
-            "service_name": "ai-search-test",
-            "api_key": "*****",
-            "collection_name": "mem0", 
-            "embedding_model_dims": 1536 ,
-            "use_compression": False
-        }
-    }
-}
-
-m = Memory.from_config(config)
-messages = [
-    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
-    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
-    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
-]
-m.add(messages, user_id="alice", metadata={"category": "movies"})
-```
-
-### Config
-
-Let's see the available parameters for the `qdrant` config:
-service_name (str): Azure Cognitive Search service name.  
-| Parameter | Description | Default Value |
-| --- | --- | --- |
-| `service_name` | Azure AI Search service name | `None` |
-| `api_key` | API key of the Azure AI Search service | `None` |
-| `collection_name` | The name of the collection/index to store the vectors, it will be created automatically if not exist | `mem0` |
-| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
-| `use_compression` | Use scalar quantization vector compression | False |

docs/components/vectordbs/dbs/elasticsearch.mdx

@@ -54,6 +54,7 @@ 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`        |
 
 ### Features
 
@@ -62,3 +63,46 @@ Let's see the available parameters for the `elasticsearch` config:
 - Multiple authentication methods (Basic Auth, API Key)
 - Automatic index creation with optimized mappings for vector search
 - Memory isolation through payload filtering
+- Custom search query function to customize the search query
+
+### Custom Search Query
+
+The `custom_search_query` parameter allows you to customize the search query when `Memory.search` is called.  
+  
+__Example__  
+```python
+import os
+from typing import List, Optional, Dict
+from mem0 import Memory
+
+def custom_search_query(query: List[float], limit: int, filters: Optional[Dict]) -> Dict:
+    return {
+        "knn": {
+            "field": "vector", 
+            "query_vector": query, 
+            "k": limit, 
+            "num_candidates": limit * 2
+        }
+    }
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "elasticsearch",
+        "config": {
+            "collection_name": "mem0",
+            "host": "localhost",
+            "port": 9200,
+            "embedding_model_dims": 1536,
+            "custom_search_query": custom_search_query
+        }
+    }
+}
+```
+It should be a function that takes the following parameters:
+- `query`: a query vector used in `Memory.search`
+- `limit`: a number of results used in `Memory.search`
+- `filters`: a dictionary of key-value pairs used in `Memory.search`. You can add custom pairs for the custom search query.  
+  
+The function should return a query body for the Elasticsearch search API.

docs/components/vectordbs/dbs/faiss.mdx

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

docs/components/vectordbs/dbs/langchain.mdx

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

docs/components/vectordbs/dbs/opensearch.mdx

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

docs/components/vectordbs/dbs/pinecone.mdx

@@ -0,0 +1,92 @@
+[Pinecone](https://www.pinecone.io/) is a fully managed vector database designed for machine learning applications, offering high performance vector search with low latency at scale. It's particularly well-suited for semantic search, recommendation systems, and other AI-powered applications.
+
+> **Note**: Before configuring Pinecone, you need to select an embedding model (e.g., OpenAI, Cohere, or custom models) and ensure the `embedding_model_dims` in your config matches your chosen model's dimensions. For example, OpenAI's text-embedding-3-small uses 1536 dimensions.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+os.environ["PINECONE_API_KEY"] = "your-api-key"
+
+# Example using serverless configuration
+config = {
+    "vector_store": {
+        "provider": "pinecone",
+        "config": {
+            "collection_name": "testing",
+            "embedding_model_dims": 1536,  # Matches OpenAI's text-embedding-3-small
+            "serverless_config": {
+                "cloud": "aws",  # Choose between 'aws' or 'gcp' or 'azure'
+                "region": "us-east-1"
+            },
+            "metric": "cosine"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller 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 Pinecone:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `collection_name` | Name of the index/collection | Required |
+| `embedding_model_dims` | Dimensions of the embedding model (must match your chosen embedding model) | Required |
+| `client` | Existing Pinecone client instance | `None` |
+| `api_key` | API key for Pinecone | Environment variable: `PINECONE_API_KEY` |
+| `environment` | Pinecone environment | `None` |
+| `serverless_config` | Configuration for serverless deployment (AWS or GCP or Azure) | `None` |
+| `pod_config` | Configuration for pod-based deployment | `None` |
+| `hybrid_search` | Whether to enable hybrid search | `False` |
+| `metric` | Distance metric for vector similarity | `"cosine"` |
+| `batch_size` | Batch size for operations | `100` |
+
+> **Important**: You must choose either `serverless_config` or `pod_config` for your deployment, but not both.
+
+#### Serverless Config Example
+```python
+config = {
+    "vector_store": {
+        "provider": "pinecone",
+        "config": {
+            "collection_name": "memory_index",
+            "embedding_model_dims": 1536,  # For OpenAI's text-embedding-3-small
+            "serverless_config": {
+                "cloud": "aws",  # or "gcp" or "azure"
+                "region": "us-east-1"  # Choose appropriate region
+            }
+        }
+    }
+}
+```
+
+#### Pod Config Example
+```python
+config = {
+    "vector_store": {
+        "provider": "pinecone",
+        "config": {
+            "collection_name": "memory_index",
+            "embedding_model_dims": 1536,  # For OpenAI's text-embedding-ada-002
+            "pod_config": {
+                "environment": "gcp-starter",
+                "replicas": 1,
+                "pod_type": "starter"
+            }
+        }
+    }
+}
+```

docs/components/vectordbs/dbs/supabase.mdx

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

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

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

docs/components/vectordbs/dbs/vertex_ai.mdx

@@ -1,4 +1,6 @@
-## Google Cloud Vertex AI Vector Search
+---
+title: Vertex AI Vector Search
+---
 
 
 ### Usage

docs/components/vectordbs/dbs/weaviate.mdx

@@ -0,0 +1,47 @@
+[Weaviate](https://weaviate.io/) is an open-source vector search engine. It allows efficient storage and retrieval of high-dimensional vector embeddings, enabling powerful search and retrieval capabilities.
+
+
+### Installation
+```bash
+pip install weaviate weaviate-client
+```
+
+### Usage
+
+```python Python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "weaviate",
+        "config": {
+            "collection_name": "test",
+            "cluster_url": "http://localhost:8080",
+            "auth_client_secret": None,
+        }
+    }
+}
+
+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
+
+Let's see the available parameters for the `weaviate` config:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `collection_name` | The name of the collection to store the vectors | `mem0` |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
+| `cluster_url` | URL for the Weaviate server | `None` |
+| `auth_client_secret` | API key for Weaviate authentication | `None` |

docs/components/vectordbs/overview.mdx

@@ -4,6 +4,8 @@ icon: "info"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Mem0 includes built-in support for various popular databases. Memory can utilize the database provided by the user, ensuring efficient use for specific needs.
 
 ## Supported Vector Databases
@@ -18,13 +20,18 @@ See the list of supported vector databases below.
   <Card title="Qdrant" href="/components/vectordbs/dbs/qdrant"></Card>
   <Card title="Chroma" href="/components/vectordbs/dbs/chroma"></Card>
   <Card title="Pgvector" href="/components/vectordbs/dbs/pgvector"></Card>
+  <Card title="Upstash Vector" href="/components/vectordbs/dbs/upstash-vector"></Card>
   <Card title="Milvus" href="/components/vectordbs/dbs/milvus"></Card>
-  <Card title="Azure AI Search" href="/components/vectordbs/dbs/azure_ai_search"></Card>
+  <Card title="Pinecone" href="/components/vectordbs/dbs/pinecone"></Card>
+  <Card title="Azure" href="/components/vectordbs/dbs/azure"></Card>
   <Card title="Redis" href="/components/vectordbs/dbs/redis"></Card>
   <Card title="Elasticsearch" href="/components/vectordbs/dbs/elasticsearch"></Card>
   <Card title="OpenSearch" href="/components/vectordbs/dbs/opensearch"></Card>
   <Card title="Supabase" href="/components/vectordbs/dbs/supabase"></Card>
-  <Card title="Vertex AI Vector Search" href="/components/vectordbs/dbs/vertex_ai_vector_search"></Card>
+  <Card title="Vertex AI" href="/components/vectordbs/dbs/vertex_ai"></Card>
+  <Card title="Weaviate" href="/components/vectordbs/dbs/weaviate"></Card>
+  <Card title="FAISS" href="/components/vectordbs/dbs/faiss"></Card>
+  <Card title="LangChain" href="/components/vectordbs/dbs/langchain"></Card>
 </CardGroup>
 
 ## Usage

docs/contributing/development.mdx

@@ -3,6 +3,8 @@ title: Development
 icon: "code"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 # Development Contributions
 
 We strive to make contributions **easy, collaborative, and enjoyable**. Follow the steps below to ensure a smooth contribution process.

docs/contributing/documentation.mdx

@@ -3,6 +3,8 @@ title: Documentation
 icon: "book"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 # Documentation Contributions
 
 ## 📌 Prerequisites

docs/core-concepts/memory-operations.mdx

@@ -5,6 +5,8 @@ icon: "gear"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Mem0 provides two core operations for managing memories in AI applications: adding new memories and searching existing ones. This guide covers how these operations work and how to use them effectively in your application.
 
 

docs/core-concepts/memory-types.mdx

@@ -4,6 +4,9 @@ description: Understanding different types of memory in AI Applications
 icon: "memory"
 iconType: "solid"
 ---
+
+<Snippet file="paper-release.mdx" />
+
 To build useful AI applications, we need to understand how different memory systems work together. This guide explores the fundamental types of memory in AI systems and shows how Mem0 implements these concepts.
 
 ## Why Memory Matters

docs/docs.json

@@ -47,14 +47,19 @@
                     "pages": [
                       "features/platform-overview",
                       "features/advanced-retrieval",
+                      "features/contextual-add",
                       "features/multimodal-support",
+                      "features/timestamp",
                       "features/selective-memory",
                       "features/custom-categories",
                       "features/custom-instructions",
                       "features/direct-import",
                       "features/async-client",
                       "features/memory-export",
-                      "features/webhooks"
+                      "features/webhooks",
+                      "features/graph-memory",
+                      "features/feedback-mechanism",
+                      "features/expiration-date"
                     ]
                   }
                 ]
@@ -70,8 +75,10 @@
                     "group": "Features",
                     "icon": "wrench",
                     "pages": [
+                      "open-source/features/async-memory",
                       "features/openai_compatibility",
-                      "features/custom-prompts",
+                      "features/custom-fact-extraction-prompt",
+                      "features/custom-update-memory-prompt",
                       "open-source/multimodal-support",
                       "open-source/features/rest-api"
                     ]
@@ -106,7 +113,9 @@
                           "components/llms/models/aws_bedrock",
                           "components/llms/models/gemini",
                           "components/llms/models/deepseek",
-                          "components/llms/models/xAI"
+                          "components/llms/models/xAI",
+                          "components/llms/models/lmstudio",
+                          "components/llms/models/langchain"
                         ]
                       }
                     ]
@@ -125,12 +134,16 @@
                           "components/vectordbs/dbs/chroma",
                           "components/vectordbs/dbs/pgvector",
                           "components/vectordbs/dbs/milvus",
-                          "components/vectordbs/dbs/azure_ai_search",
+                          "components/vectordbs/dbs/pinecone",
+                          "components/vectordbs/dbs/azure",
                           "components/vectordbs/dbs/redis",
                           "components/vectordbs/dbs/elasticsearch",
                           "components/vectordbs/dbs/opensearch",
                           "components/vectordbs/dbs/supabase",
-                          "components/vectordbs/dbs/vertex_ai_vector_search"
+                          "components/vectordbs/dbs/vertex_ai",
+                          "components/vectordbs/dbs/weaviate",
+                          "components/vectordbs/dbs/faiss",
+                          "components/vectordbs/dbs/langchain"
                         ]
                       }
                     ]
@@ -150,7 +163,11 @@
                           "components/embedders/models/ollama",
                           "components/embedders/models/huggingface",
                           "components/embedders/models/vertexai",
-                          "components/embedders/models/gemini"
+                          "components/embedders/models/gemini",
+                          "components/embedders/models/lmstudio",
+                          "components/embedders/models/together",
+                          "components/embedders/models/langchain",
+                          "components/embedders/models/aws_bedrock"
                         ]
                       }
                     ]
@@ -167,6 +184,14 @@
               }
             ]
           },
+          {
+            "tab": "OpenMemory",
+            "icon": "square-terminal",
+            "pages": [
+              "openmemory/overview",
+              "openmemory/quickstart"
+            ]
+          },
           {
             "tab": "Examples",
             "groups": [
@@ -174,9 +199,12 @@
                 "group": "💡 Examples",
                 "icon": "lightbulb",
                 "pages": [
-                  "examples/overview",
+                  "examples",
+                  "examples/aws_example",
                   "examples/mem0-demo",
                   "examples/ai_companion_js",
+                  "examples/eliza_os",
+                  "examples/mem0-mastra",
                   "examples/mem0-with-ollama",
                   "examples/personal-ai-tutor",
                   "examples/customer-support-agent",
@@ -185,7 +213,12 @@
                   "examples/chrome-extension",
                   "examples/document-writing",
                   "examples/multimodal-demo",
-                  "examples/personalized-deep-research"
+                  "examples/personalized-deep-research",
+                  "examples/mem0-agentic-tool",
+                  "examples/openai-inbuilt-tools",
+                  "examples/mem0-openai-voice-demo",
+                  "examples/email_processing",
+                  "examples/youtube-assistant"
                 ]
               }
             ]
@@ -197,8 +230,9 @@
                 "group": "Integrations",
                 "icon": "plug",
                 "pages": [
-                  "integrations/overview",
+                  "integrations",
                   "integrations/vercel-ai-sdk",
+                  "integrations/flowise",
                   "integrations/crewai",
                   "integrations/autogen",
                   "integrations/langchain",
@@ -206,7 +240,12 @@
                   "integrations/llama-index",
                   "integrations/langchain-tools",
                   "integrations/dify",
-                  "integrations/mcp-server"
+                  "integrations/mcp-server",
+                  "integrations/livekit",
+                  "integrations/elevenlabs",
+                  "integrations/pipecat",
+                  "integrations/agno",
+                  "integrations/keywords"
                 ]
               }
             ]
@@ -219,7 +258,7 @@
                 "group": "API Reference",
                 "icon": "terminal",
                 "pages": [
-                  "api-reference/overview",
+                  "api-reference",
                   {
                     "group": "Memory APIs",
                     "icon": "microchip",
@@ -237,7 +276,8 @@
                       "api-reference/memory/batch-delete",
                       "api-reference/memory/delete-memories",
                       "api-reference/memory/create-memory-export",
-                      "api-reference/memory/get-memory-export"
+                      "api-reference/memory/get-memory-export",
+                      "api-reference/memory/feedback"
                     ]
                   },
                   {
@@ -260,6 +300,18 @@
                       "api-reference/organization/delete-org"
                     ]
                   },
+                  {
+                    "group": "Project APIs",
+                    "icon": "folder",
+                    "pages": [
+                      "api-reference/project/create-project",
+                      "api-reference/project/get-projects",
+                      "api-reference/project/get-project",
+                      "api-reference/project/get-project-members",
+                      "api-reference/project/add-project-member",
+                      "api-reference/project/delete-project"
+                    ]
+                  },
                   {
                     "group": "Webhook APIs",
                     "icon": "webhook",
@@ -273,6 +325,19 @@
                 ]
               }
             ]
+          },
+          {
+            "tab": "Changelog",
+            "icon": "clock",
+            "groups": [
+              {
+                "group": "Product Updates",
+                "icon": "rocket",
+                "pages": [
+                  "changelog"
+                ]
+              }
+            ]
           }
         ]
       },
@@ -333,6 +398,9 @@
     "posthog": {
       "apiKey": "phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX",
       "apiHost": "https://mango.mem0.ai"
+    },
+    "intercom": {
+      "appId": "jjv2r0tt"
     }
   }
 }

docs/examples.mdx

@@ -3,6 +3,8 @@ title: Overview
 description: How to use mem0 in your existing applications?
 ---
 
+<Snippet file="paper-release.mdx" />
+
 
 With Mem0, you can create stateful LLM-based applications such as chatbots, virtual assistants, or AI agents. Mem0 enhances your applications by providing a memory layer that makes responses:
 
@@ -47,6 +49,10 @@ Explore how **Mem0** can power real-world applications and bring personalized, i
     Add **long-term memory** to ChatGPT, Claude, or Perplexity via the **Mem0 Chrome Extension** — personalize your AI chats anywhere.  
   </Card>  
 
+  <Card title="YouTube Assistant" icon="puzzle-piece" href="/examples/youtube-assistant">  
+    Integrate **Mem0** into **YouTube's** native UI, providing personalized responses with video context. 
+  </Card> 
+
   <Card title="Document Writing Assistant" icon="pen" href="/examples/document-writing">  
     Create a **Writing Assistant** that understands and adapts to your unique style, improving consistency and productivity.  
   </Card>  
@@ -55,7 +61,23 @@ Explore how **Mem0** can power real-world applications and bring personalized, i
     Supercharge AI with **Mem0's multimodal memory** — blend text, images, and more for richer, context-aware interactions.  
   </Card>  
 
-  <Card title="Personalized Research Agent" icon="robot" href="/examples/personalized-deep-research">  
+  <Card title="Personalized Research Agent" icon="magnifying-glass" href="/examples/personalized-deep-research">  
     Build a **Deep Research AI** that remembers your research goals and compiles insights from vast information sources.  
   </Card>  
+
+  <Card title="Mem0 as an Agentic Tool" icon="robot" href="/examples/mem0-agentic-tool">  
+    Integrate Mem0's memory capabilities with OpenAI's Agents SDK to create AI agents with persistent memory.  
+  </Card>  
+
+  <Card title="OpenAI Inbuilt Tools" icon="robot" href="/examples/openai-inbuilt-tools">  
+    Use Mem0's memory capabilities with OpenAI's Inbuilt Tools to create AI agents with persistent memory.  
+  </Card>  
+
+  <Card title="Mem0 OpenAI Voice Demo" icon="microphone" href="/examples/mem0-openai-voice-demo">  
+    Use Mem0's memory capabilities with OpenAI's Inbuilt Tools to create AI agents with persistent memory.  
+  </Card> 
+
+  <Card title="Email Processing" icon="envelope" href="/examples/email_processing">  
+    Use Mem0's memory capabilities to process emails and create AI agents with persistent memory.  
+  </Card> 
 </CardGroup>

docs/examples/ai_companion.mdx

@@ -2,6 +2,8 @@
 title: AI Companion
 ---
 
+<Snippet file="paper-release.mdx" />
+
 You can create a personalised AI Companion using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
 
 ## Overview

docs/examples/ai_companion_js.mdx

@@ -2,6 +2,8 @@
 title: AI Companion in Node.js
 ---
 
+<Snippet file="paper-release.mdx" />
+
 You can create a personalised AI Companion using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
 
 ## Overview

docs/examples/aws_example.mdx

@@ -0,0 +1,120 @@
+---
+title: AWS Bedrock and AOSS
+---
+
+<Snippet file="paper-release.mdx" />
+
+This example demonstrates how to configure and use the `mem0ai` SDK with **AWS Bedrock** and **OpenSearch Service (AOSS)** for persistent memory capabilities in Python.
+
+## Installation
+
+Install the required dependencies:
+
+```bash
+pip install mem0ai boto3 opensearch-py
+```
+
+## Environment Setup
+
+Set your AWS environment variables:
+
+```python
+import os
+
+# Set these in your environment or notebook
+os.environ['AWS_REGION'] = 'us-west-2'
+os.environ['AWS_ACCESS_KEY_ID'] = 'AK00000000000000000'
+os.environ['AWS_SECRET_ACCESS_KEY'] = 'AS00000000000000000'
+
+# Confirm they are set
+print(os.environ['AWS_REGION'])
+print(os.environ['AWS_ACCESS_KEY_ID'])
+print(os.environ['AWS_SECRET_ACCESS_KEY'])
+```
+
+## Configuration and Usage
+
+This sets up Mem0 with AWS Bedrock for embeddings and LLM, and OpenSearch as the vector store.
+
+```python
+import boto3
+from opensearchpy import OpenSearch, RequestsHttpConnection, AWSV4SignerAuth
+from mem0.memory.main import Memory
+
+region = 'us-west-2'
+service = 'aoss'
+credentials = boto3.Session().get_credentials()
+auth = AWSV4SignerAuth(credentials, region, service)
+
+config = {
+    "embedder": {
+        "provider": "aws_bedrock",
+        "config": {
+            "model": "amazon.titan-embed-text-v2:0"
+        }
+    },
+    "llm": {
+        "provider": "aws_bedrock",
+        "config": {
+            "model": "anthropic.claude-3-5-haiku-20241022-v1:0",
+            "temperature": 0.1,
+            "max_tokens": 2000
+        }
+    },
+    "vector_store": {
+        "provider": "opensearch",
+        "config": {
+            "collection_name": "mem0",
+            "host": "your-opensearch-domain.us-west-2.es.amazonaws.com",
+            "port": 443,
+            "http_auth": auth,
+            "embedding_model_dims": 1024,
+            "connection_class": RequestsHttpConnection,
+            "pool_maxsize": 20,
+            "use_ssl": True,
+            "verify_certs": True
+        }
+    }
+}
+
+# Initialize memory system
+m = Memory.from_config(config)
+```
+
+## Usage
+
+#### Add a memory:
+
+```python
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+
+# Store inferred memories (default behavior)
+result = m.add(messages, user_id="alice", metadata={"category": "movie_recommendations"})
+```
+
+#### Search a memory:
+```python
+relevant_memories = m.search(query, user_id="alice")
+```
+
+#### Get all memories:
+```python
+all_memories = m.get_all(user_id="alice")
+```
+
+#### Get a specific memory:
+```python
+memory = m.get(memory_id)
+```
+
+
+---
+
+## Conclusion
+
+With Mem0 and AWS services like Bedrock and OpenSearch, you can build intelligent AI companions that remember, adapt, and personalize their responses over time. This makes them ideal for long-term assistants, tutors, or support bots with persistent memory and natural conversation abilities.

docs/examples/chrome-extension.mdx

@@ -1,5 +1,7 @@
 # Mem0 Chrome Extension
 
+<Snippet file="paper-release.mdx" />
+
 Enhance your AI interactions with **Mem0**, a Chrome extension that introduces a universal memory layer across platforms like `ChatGPT`, `Claude`, and `Perplexity`. Mem0 ensures seamless context sharing, making your AI experiences more personalized and efficient.
 
 <Note>

docs/examples/customer-support-agent.mdx

@@ -2,6 +2,8 @@
 title: Customer Support AI Agent
 ---
 
+<Snippet file="paper-release.mdx" />
+
 You can create a personalized Customer Support AI Agent using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
 
 ## Overview

docs/examples/document-writing.mdx

@@ -1,6 +1,7 @@
 ---
 title: Document Editing with Mem0
 ---
+<Snippet file="paper-release.mdx" />
 
 This guide demonstrates how to leverage **Mem0** to edit documents efficiently, ensuring they align with your unique writing style and preferences.
 

docs/examples/eliza_os.mdx

@@ -0,0 +1,75 @@
+---
+title: Eliza OS Character
+---
+
+<Snippet file="paper-release.mdx" />
+
+You can create a personalised Eliza OS Character using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
+
+## Overview
+
+ElizaOS is a powerful AI agent framework for autonomy & personality. It is a collection of tools that help you create a personalised AI agent.
+
+## Setup
+You can start by cloning the eliza-os repository:
+
+```bash
+git clone https://github.com/elizaOS/eliza.git
+```
+
+Change the directory to the eliza-os repository:
+
+```bash
+cd eliza
+```
+
+Install the dependencies:
+
+```bash
+pnpm install
+```
+
+Build the project:
+
+```bash
+pnpm build
+```
+
+## Setup ENVs
+
+Create a `.env` file in the root of the project and add the following ( You can use the `.env.example` file as a reference):
+
+```bash
+# Mem0 Configuration
+MEM0_API_KEY= # Mem0 API Key ( Get from https://app.mem0.ai/dashboard/api-keys )
+MEM0_USER_ID= # Default: eliza-os-user
+MEM0_PROVIDER= # Default: openai
+MEM0_PROVIDER_API_KEY= # API Key for the provider (openai, anthropic, etc.)
+SMALL_MEM0_MODEL= # Default: gpt-4o-mini
+MEDIUM_MEM0_MODEL= # Default: gpt-4o
+LARGE_MEM0_MODEL= # Default: gpt-4o
+```
+
+## Make the default character use Mem0
+
+By default, there is a character called `eliza` that uses the `ollama` model. You can make this character use Mem0 by changing the config in the `agent/src/defaultCharacter.ts` file.
+
+```ts
+modelProvider: ModelProviderName.MEM0,
+```
+
+This will make the character use Mem0 to generate responses.
+
+## Run the project
+
+```bash
+pnpm start
+```
+
+## Conclusion
+
+You have now created a personalised Eliza OS Character using Mem0. You can now start interacting with the character by running the project and talking to the character.
+
+This is a simple example of how to use Mem0 to create a personalised AI agent. You can use this as a starting point to create your own AI agent.
+
+

docs/examples/email_processing.mdx

@@ -0,0 +1,188 @@
+---
+title: Email Processing with Mem0
+---
+
+<Snippet file="paper-release.mdx" />
+
+This guide demonstrates how to build an intelligent email processing system using Mem0's memory capabilities. You'll learn how to store, categorize, retrieve, and analyze emails to create a smart email management solution.
+
+## Overview
+
+Email overload is a common challenge for many professionals. By leveraging Mem0's memory capabilities, you can build an intelligent system that:
+
+- Stores emails as searchable memories
+- Categorizes emails automatically
+- Retrieves relevant past conversations
+- Prioritizes messages based on importance
+- Generates summaries and action items
+
+## Setup
+
+Before you begin, ensure you have the required dependencies installed:
+
+```bash
+pip install mem0ai openai
+```
+
+## Implementation
+
+### Basic Email Memory System
+
+The following example shows how to create a basic email processing system with Mem0:
+
+```python
+import os
+from mem0 import MemoryClient
+from email.parser import Parser
+
+# Configure API keys
+os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
+
+# Initialize Mem0 client
+client = MemoryClient()
+
+class EmailProcessor:
+    def __init__(self):
+        """Initialize the Email Processor with Mem0 memory client"""
+        self.client = client
+        
+    def process_email(self, email_content, user_id):
+        """
+        Process an email and store it in Mem0 memory
+        
+        Args:
+            email_content (str): Raw email content
+            user_id (str): User identifier for memory association
+        """
+        # Parse email
+        parser = Parser()
+        email = parser.parsestr(email_content)
+        
+        # Extract email details
+        sender = email['from']
+        recipient = email['to']
+        subject = email['subject']
+        date = email['date']
+        body = self._get_email_body(email)
+        
+        # Create message object for Mem0
+        message = {
+            "role": "user",
+            "content": f"Email from {sender}: {subject}\n\n{body}"
+        }
+        
+        # Create metadata for better retrieval
+        metadata = {
+            "email_type": "incoming",
+            "sender": sender,
+            "recipient": recipient,
+            "subject": subject,
+            "date": date
+        }
+        
+        # Store in Mem0 with appropriate categories
+        response = self.client.add(
+            messages=[message],
+            user_id=user_id,
+            metadata=metadata,
+            categories=["email", "correspondence"],
+            version="v2"
+        )
+        
+        return response
+    
+    def _get_email_body(self, email):
+        """Extract the body content from an email"""
+        # Simplified extraction - in real-world, handle multipart emails
+        if email.is_multipart():
+            for part in email.walk():
+                if part.get_content_type() == "text/plain":
+                    return part.get_payload(decode=True).decode()
+        else:
+            return email.get_payload(decode=True).decode()
+    
+    def search_emails(self, query, user_id):
+        """
+        Search through stored emails
+        
+        Args:
+            query (str): Search query
+            user_id (str): User identifier
+        """
+        # Search Mem0 for relevant emails
+        results = self.client.search(
+            query=query,
+            user_id=user_id,
+            categories=["email"],
+            output_format="v1.1",
+            version="v2"
+        )
+        
+        return results
+        
+    def get_email_thread(self, subject, user_id):
+        """
+        Retrieve all emails in a thread based on subject
+        
+        Args:
+            subject (str): Email subject to match
+            user_id (str): User identifier
+        """
+        filters = {
+            "AND": [
+                {"user_id": user_id},
+                {"categories": {"contains": "email"}},
+                {"metadata": {"subject": {"contains": subject}}}
+            ]
+        }
+        
+        thread = self.client.get_all(
+            version="v2",
+            filters=filters,
+            output_format="v1.1"
+        )
+        
+        return thread
+
+# Initialize the processor
+processor = EmailProcessor()
+
+# Example raw email
+sample_email = """From: alice@example.com
+To: bob@example.com
+Subject: Meeting Schedule Update
+Date: Mon, 15 Jul 2024 14:22:05 -0700
+
+Hi Bob,
+
+I wanted to update you on the schedule for our upcoming project meeting.
+We'll be meeting this Thursday at 2pm instead of Friday.
+
+Could you please prepare your section of the presentation?
+
+Thanks,
+Alice
+"""
+
+# Process and store the email
+user_id = "bob@example.com"
+processor.process_email(sample_email, user_id)
+
+# Later, search for emails about meetings
+meeting_emails = processor.search_emails("meeting schedule", user_id)
+print(f"Found {len(meeting_emails['results'])} relevant emails")
+```
+
+## Key Features and Benefits
+
+- **Long-term Email Memory**: Store and retrieve email conversations across long periods
+- **Semantic Search**: Find relevant emails even if they don't contain exact keywords
+- **Intelligent Categorization**: Automatically sort emails into meaningful categories
+- **Action Item Extraction**: Identify and track tasks mentioned in emails
+- **Priority Management**: Focus on important emails based on AI-determined priority
+- **Context Awareness**: Maintain thread context for more relevant interactions
+
+## Conclusion
+
+By combining Mem0's memory capabilities with email processing, you can create intelligent email management systems that help users organize, prioritize, and act on their inbox effectively. The advanced capabilities like automatic categorization, action item extraction, and priority management can significantly reduce the time spent on email management, allowing users to focus on more important tasks.
+

docs/examples/llama-index-mem0.mdx

@@ -1,6 +1,8 @@
 ---
 title: LlamaIndex ReAct Agent
 ---
+<Snippet file="paper-release.mdx" />
+
 Create a ReAct Agent with LlamaIndex which uses Mem0 as the memory store.
 
 ### Overview

docs/examples/mem0-agentic-tool.mdx

@@ -0,0 +1,228 @@
+---
+title: Mem0 as an Agentic Tool
+---
+
+<Snippet file="paper-release.mdx" />
+
+Integrate Mem0's memory capabilities with OpenAI's Agents SDK to create AI agents with persistent memory.
+You can create agents that remember past conversations and use that context to provide better responses.
+
+## Installation
+
+First, install the required packages:
+```bash
+pip install mem0ai pydantic openai-agents
+```
+
+You'll also need a custom agents framework for this implementation.
+
+## Setting Up Environment Variables
+
+Store your Mem0 API key as an environment variable:
+
+```bash
+export MEM0_API_KEY="your_mem0_api_key"
+```
+
+Or in your Python script:
+
+```python
+import os
+os.environ["MEM0_API_KEY"] = "your_mem0_api_key"
+```
+
+## Code Structure
+
+The integration consists of three main components:
+
+1. **Context Manager**: Defines user context for memory operations
+2. **Memory Tools**: Functions to add, search, and retrieve memories
+3. **Memory Agent**: An agent configured to use these memory tools
+
+## Step-by-Step Implementation
+
+### 1. Import Dependencies
+
+```python
+from __future__ import annotations
+import os
+import asyncio
+from pydantic import BaseModel
+try:
+    from mem0 import AsyncMemoryClient
+except ImportError:
+    raise ImportError("mem0 is not installed. Please install it using 'pip install mem0ai'.")
+from agents import (
+    Agent,
+    ItemHelpers,
+    MessageOutputItem,
+    RunContextWrapper,
+    Runner,
+    ToolCallItem,
+    ToolCallOutputItem,
+    TResponseInputItem,
+    function_tool,
+)
+```
+
+### 2. Define Memory Context
+
+```python
+class Mem0Context(BaseModel):
+    user_id: str | None = None
+```
+
+### 3. Initialize the Mem0 Client
+
+```python
+client = AsyncMemoryClient(api_key=os.getenv("MEM0_API_KEY"))
+```
+
+### 4. Create Memory Tools
+
+#### Add to Memory
+
+```python
+@function_tool
+async def add_to_memory(
+    context: RunContextWrapper[Mem0Context],
+    content: str,
+) -> str:
+    """
+    Add a message to Mem0
+    Args:
+        content: The content to store in memory.
+    """
+    messages = [{"role": "user", "content": content}]
+    user_id = context.context.user_id or "default_user"
+    await client.add(messages, user_id=user_id)
+    return f"Stored message: {content}"
+```
+
+#### Search Memory
+
+```python
+@function_tool
+async def search_memory(
+    context: RunContextWrapper[Mem0Context],
+    query: str,
+) -> str:
+    """
+    Search for memories in Mem0
+    Args:
+        query: The search query.
+    """
+    user_id = context.context.user_id or "default_user"
+    memories = await client.search(query, user_id=user_id, output_format="v1.1")
+    results = '\n'.join([result["memory"] for result in memories["results"]])
+    return str(results)
+```
+
+#### Get All Memories
+
+```python
+@function_tool
+async def get_all_memory(
+    context: RunContextWrapper[Mem0Context],
+) -> str:
+    """Retrieve all memories from Mem0"""
+    user_id = context.context.user_id or "default_user"
+    memories = await client.get_all(user_id=user_id, output_format="v1.1")
+    results = '\n'.join([result["memory"] for result in memories["results"]])
+    return str(results)
+```
+
+### 5. Configure the Memory Agent
+
+```python
+memory_agent = Agent[Mem0Context](
+    name="Memory Assistant",
+    instructions="""You are a helpful assistant with memory capabilities. You can:
+    1. Store new information using add_to_memory
+    2. Search existing information using search_memory
+    3. Retrieve all stored information using get_all_memory
+    When users ask questions:
+    - If they want to store information, use add_to_memory
+    - If they're searching for specific information, use search_memory
+    - If they want to see everything stored, use get_all_memory""",
+    tools=[add_to_memory, search_memory, get_all_memory],
+)
+```
+
+### 6. Implement the Main Runtime Loop
+
+```python
+async def main():
+    current_agent: Agent[Mem0Context] = memory_agent
+    input_items: list[TResponseInputItem] = []
+    context = Mem0Context()
+    while True:
+        user_input = input("Enter your message (or 'quit' to exit): ")
+        if user_input.lower() == 'quit':
+            break
+        input_items.append({"content": user_input, "role": "user"})
+        result = await Runner.run(current_agent, input_items, context=context)
+        for new_item in result.new_items:
+            agent_name = new_item.agent.name
+            if isinstance(new_item, MessageOutputItem):
+                print(f"{agent_name}: {ItemHelpers.text_message_output(new_item)}")
+            elif isinstance(new_item, ToolCallItem):
+                print(f"{agent_name}: Calling a tool")
+            elif isinstance(new_item, ToolCallOutputItem):
+                print(f"{agent_name}: Tool call output: {new_item.output}")
+            else:
+                print(f"{agent_name}: Skipping item: {new_item.__class__.__name__}")
+        input_items = result.to_input_list()
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Usage Examples
+
+### Storing Information
+
+```
+User: Remember that my favorite color is blue
+Agent: Calling a tool
+Agent: Tool call output: Stored message: my favorite color is blue
+Agent: I've stored that your favorite color is blue in my memory. I'll remember that for future conversations.
+```
+
+### Searching Memory
+
+```
+User: What's my favorite color?
+Agent: Calling a tool
+Agent: Tool call output: my favorite color is blue
+Agent: Your favorite color is blue, based on what you've told me earlier.
+```
+
+### Retrieving All Memories
+
+```
+User: What do you know about me?
+Agent: Calling a tool
+Agent: Tool call output: favorite color is blue
+my birthday is on March 15
+Agent: Based on our previous conversations, I know that:
+1. Your favorite color is blue
+2. Your birthday is on March 15
+```
+
+## Advanced Configuration
+
+### Custom User IDs
+
+You can specify different user IDs to maintain separate memory stores for multiple users:
+
+```python
+context = Mem0Context(user_id="user123")
+```
+
+
+## Resources
+
+- [Mem0 Documentation](https://docs.mem0.ai)
+- [Mem0 Dashboard](https://app.mem0.ai/dashboard)
+- [API Reference](https://docs.mem0.ai/api-reference)

docs/examples/mem0-demo.mdx

@@ -2,6 +2,9 @@
 title: Mem0 Demo
 ---
 
+
+<Snippet file="paper-release.mdx" />
+
 You can create a personalized AI Companion using Mem0. This guide will walk you through the necessary steps and provide the complete setup instructions to get you started.
 
 <video
@@ -13,7 +16,7 @@ You can create a personalized AI Companion using Mem0. This guide will walk you
   src="https://github.com/user-attachments/assets/cebc4f8e-bdb9-4837-868d-13c5ab7bb433"
 ></video>
 
-You can try the [Mem0 Demo](https://mem0.dev/demo) live here.
+You can try the [Mem0 Demo](https://mem0-4vmi.vercel.app) live here.
 
 ## Overview
 

docs/examples/mem0-mastra.mdx

@@ -0,0 +1,128 @@
+---
+title: Mem0 with Mastra
+---
+
+<Snippet file="paper-release.mdx" />
+
+In this example you'll learn how to use the Mem0 to add long-term memory capabilities to [Mastra's agent](https://mastra.ai/) via tool-use.
+This memory integration can work alongside Mastra's [agent memory features](https://mastra.ai/docs/agents/01-agent-memory).
+
+You can find the complete example code in the [Mastra repository](https://github.com/mastra-ai/mastra/tree/main/examples/memory-with-mem0).
+
+## Overview
+
+This guide will show you how to integrate Mem0 with Mastra to add long-term memory capabilities to your agents. We'll create tools that allow agents to save and retrieve memories using Mem0's API.
+
+### Installation
+
+1. **Install the Integration Package**
+
+To install the Mem0 integration, run:
+
+```bash
+npm install @mastra/mem0
+```
+
+2. **Add the Integration to Your Project**
+
+Create a new file for your integrations and import the integration:
+
+```typescript integrations/index.ts
+import { Mem0Integration } from "@mastra/mem0";
+
+export const mem0 = new Mem0Integration({
+  config: {
+    apiKey: process.env.MEM0_API_KEY!,
+    userId: "alice",
+  },
+});
+```
+
+3. **Use the Integration in Tools or Workflows**
+
+You can now use the integration when defining tools for your agents or in workflows.
+
+```typescript tools/index.ts
+import { createTool } from "@mastra/core";
+import { z } from "zod";
+import { mem0 } from "../integrations";
+
+export const mem0RememberTool = createTool({
+  id: "Mem0-remember",
+  description:
+    "Remember your agent memories that you've previously saved using the Mem0-memorize tool.",
+  inputSchema: z.object({
+    question: z
+      .string()
+      .describe("Question used to look up the answer in saved memories."),
+  }),
+  outputSchema: z.object({
+    answer: z.string().describe("Remembered answer"),
+  }),
+  execute: async ({ context }) => {
+    console.log(`Searching memory "${context.question}"`);
+    const memory = await mem0.searchMemory(context.question);
+    console.log(`\nFound memory "${memory}"\n`);
+
+    return {
+      answer: memory,
+    };
+  },
+});
+
+export const mem0MemorizeTool = createTool({
+  id: "Mem0-memorize",
+  description:
+    "Save information to mem0 so you can remember it later using the Mem0-remember tool.",
+  inputSchema: z.object({
+    statement: z.string().describe("A statement to save into memory"),
+  }),
+  execute: async ({ context }) => {
+    console.log(`\nCreating memory "${context.statement}"\n`);
+    // to reduce latency memories can be saved async without blocking tool execution
+    void mem0.createMemory(context.statement).then(() => {
+      console.log(`\nMemory "${context.statement}" saved.\n`);
+    });
+    return { success: true };
+  },
+});
+```
+
+4. **Create a new agent**
+
+```typescript agents/index.ts
+import { openai } from '@ai-sdk/openai';
+import { Agent } from '@mastra/core/agent';
+import { mem0MemorizeTool, mem0RememberTool } from '../tools';
+
+export const mem0Agent = new Agent({
+  name: 'Mem0 Agent',
+  instructions: `
+    You are a helpful assistant that has the ability to memorize and remember facts using Mem0.
+  `,
+  model: openai('gpt-4o'),
+  tools: { mem0RememberTool, mem0MemorizeTool },
+});
+```
+
+5. **Run the agent**
+
+```typescript index.ts
+import { Mastra } from '@mastra/core/mastra';
+import { createLogger } from '@mastra/core/logger';
+
+import { mem0Agent } from './agents';
+
+export const mastra = new Mastra({
+  agents: { mem0Agent },
+  logger: createLogger({
+    name: 'Mastra',
+    level: 'error',
+  }),
+});
+```
+
+In the example above:
+- We import the `@mastra/mem0` integration.
+- We define two tools that uses the Mem0 API client to create new memories and recall previously saved memories.
+- The tool accepts `question` as an input and returns the memory as a string.

docs/examples/mem0-openai-voice-demo.mdx

@@ -0,0 +1,540 @@
+---
+title: 'Mem0 with OpenAI Agents SDK for Voice'
+description: 'Integrate memory capabilities into your voice agents using Mem0 and OpenAI Agents SDK'
+---
+
+<Snippet file="paper-release.mdx" />
+
+# Building Voice Agents with Memory using Mem0 and OpenAI Agents SDK
+
+This guide demonstrates how to combine OpenAI's Agents SDK for voice applications with Mem0's memory capabilities to create a voice assistant that remembers user preferences and past interactions.
+
+## Prerequisites
+
+Before you begin, make sure you have:
+
+1. Installed OpenAI Agents SDK with voice dependencies:
+```bash
+pip install 'openai-agents[voice]'
+```
+
+2. Installed Mem0 SDK:
+```bash
+pip install mem0ai
+```
+
+3. Installed other required dependencies:
+```bash
+pip install numpy sounddevice pydantic
+```
+
+4. Set up your API keys:
+   - OpenAI API key for the Agents SDK
+   - Mem0 API key from the Mem0 Platform
+
+## Code Breakdown
+
+Let's break down the key components of this implementation:
+
+### 1. Setting Up Dependencies and Environment
+
+```python
+# OpenAI Agents SDK imports
+from agents import (
+    Agent,
+    function_tool
+)
+from agents.voice import (
+    AudioInput,
+    SingleAgentVoiceWorkflow,
+    VoicePipeline
+)
+from agents.extensions.handoff_prompt import prompt_with_handoff_instructions
+
+# Mem0 imports
+from mem0 import AsyncMemoryClient
+
+# Set up API keys (replace with your actual keys)
+os.environ["OPENAI_API_KEY"] = "your-openai-api-key"
+os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
+
+# Define a global user ID for simplicity
+USER_ID = "voice_user"
+
+# Initialize Mem0 client
+mem0_client = AsyncMemoryClient()
+```
+
+This section handles:
+- Importing required modules from OpenAI Agents SDK and Mem0
+- Setting up environment variables for API keys
+- Defining a simple user identification system (using a global variable)
+- Initializing the Mem0 client that will handle memory operations
+
+### 2. Memory Tools with Function Decorators
+
+The `@function_tool` decorator transforms Python functions into callable tools for the OpenAI agent. Here are the key memory tools:
+
+#### Storing User Memories
+
+```python
+import logging
+
+# Set up logging at the top of your file
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    force=True
+)
+logger = logging.getLogger("memory_voice_agent")
+
+# Then use logger in your function tools
+@function_tool
+async def save_memories(
+    memory: str
+) -> str:
+    """Store a user memory in memory."""
+    # This will be visible in your console
+    logger.debug(f"Saving memory: {memory} for user {USER_ID}")
+    
+    # Store the preference in Mem0
+    memory_content = f"User memory - {memory}"
+    await mem0_client.add(
+        memory_content,
+        user_id=USER_ID,
+    )
+
+    return f"I've saved your memory: {memory}"
+```
+
+This function:
+- Takes a memory string
+- Creates a formatted memory string
+- Stores it in Mem0 using the `add()` method
+- Includes metadata to categorize the memory for easier retrieval
+- Returns a confirmation message that the agent will speak
+
+#### Finding Relevant Memories
+
+```python
+@function_tool
+async def search_memories(
+    query: str
+) -> str:
+    """
+    Find memories relevant to the current conversation.
+    Args:
+        query: The search query to find relevant memories
+    """
+    print(f"Finding memories related to: {query}")
+    results = await mem0_client.search(
+        query,
+        user_id=USER_ID,
+        limit=5,
+        threshold=0.7,  # Higher threshold for more relevant results
+        output_format="v1.1"
+    )
+    
+    # Format and return the results
+    if not results.get('results', []):
+        return "I don't have any relevant memories about this topic."
+    
+    memories = [f"• {result['memory']}" for result in results.get('results', [])]
+    return "Here's what I remember that might be relevant:\n" + "\n".join(memories)
+```
+
+This tool:
+- Takes a search query string
+- Passes it to Mem0's semantic search to find related memories
+- Sets a threshold for relevance to ensure quality results
+- Returns a formatted list of relevant memories or a default message
+
+### 3. Creating the Voice Agent
+
+```python
+def create_memory_voice_agent():
+    # Create the agent with memory-enabled tools
+    agent = Agent(
+        name="Memory Assistant",
+        instructions=prompt_with_handoff_instructions(
+            """You're speaking to a human, so be polite and concise.
+            Always respond in clear, natural English.
+            You have the ability to remember information about the user.
+            Use the save_memories tool when the user shares an important information worth remembering.
+            Use the search_memories tool when you need context from past conversations or user asks you to recall something.
+            """,
+        ),
+        model="gpt-4o",
+        tools=[save_memories, search_memories],
+    )
+    
+    return agent
+```
+
+This function:
+- Creates an OpenAI Agent with specific instructions
+- Configures it to use gpt-4o (you can use other models)
+- Registers the memory-related tools with the agent
+- Uses `prompt_with_handoff_instructions` to include standard voice agent behaviors
+
+### 4. Microphone Recording Functionality
+
+```python
+async def record_from_microphone(duration=5, samplerate=24000):
+    """Record audio from the microphone for a specified duration."""
+    print(f"Recording for {duration} seconds...")
+    
+    # Create a buffer to store the recorded audio
+    frames = []
+    
+    # Callback function to store audio data
+    def callback(indata, frames_count, time_info, status):
+        frames.append(indata.copy())
+    
+    # Start recording
+    with sd.InputStream(samplerate=samplerate, channels=1, callback=callback, dtype=np.int16):
+        await asyncio.sleep(duration)
+    
+    # Combine all frames into a single numpy array
+    audio_data = np.concatenate(frames)
+    return audio_data
+```
+
+This function:
+- Creates a simple asynchronous microphone recording function
+- Uses the sounddevice library to capture audio input
+- Stores frames in a buffer during recording
+- Combines frames into a single numpy array when complete
+- Returns the audio data for processing
+
+### 5. Main Loop and Voice Processing
+
+```python
+async def main():
+    # Create the agent
+    agent = create_memory_voice_agent()
+    
+    # Set up the voice pipeline
+    pipeline = VoicePipeline(
+        workflow=SingleAgentVoiceWorkflow(agent)
+    )
+    
+    # Configure TTS settings
+    pipeline.config.tts_settings.voice = "alloy"
+    pipeline.config.tts_settings.speed = 1.0
+    
+    try:
+        while True:
+            # Get user input
+            print("\nPress Enter to start recording (or 'q' to quit)...")
+            user_input = input()
+            if user_input.lower() == 'q':
+                break
+            
+            # Record and process audio
+            audio_data = await record_from_microphone(duration=5)
+            audio_input = AudioInput(buffer=audio_data)
+            result = await pipeline.run(audio_input)
+            
+            # Play response and handle events
+            player = sd.OutputStream(samplerate=24000, channels=1, dtype=np.int16)
+            player.start()
+            
+            agent_response = ""
+            print("\nAgent response:")
+            
+            async for event in result.stream():
+                if event.type == "voice_stream_event_audio":
+                    player.write(event.data)
+                elif event.type == "voice_stream_event_content":
+                    content = event.data
+                    agent_response += content
+                    print(content, end="", flush=True)
+            
+            # Save the agent's response to memory
+            if agent_response:
+                try:
+                    await mem0_client.add(
+                        f"Agent response: {agent_response}", 
+                        user_id=USER_ID,
+                        metadata={"type": "agent_response"}
+                    )
+                except Exception as e:
+                    print(f"Failed to store memory: {e}")
+    
+    except KeyboardInterrupt:
+        print("\nExiting...")
+```
+
+This main function orchestrates the entire process:
+1. Creates the memory-enabled voice agent
+2. Sets up the voice pipeline with TTS settings
+3. Implements an interactive loop for recording and processing voice input
+4. Handles streaming of response events (both audio and text)
+5. Automatically saves the agent's responses to memory
+6. Includes proper error handling and exit mechanisms
+
+## Create a Memory-Enabled Voice Agent
+
+Now that we've explained each component, here's the complete implementation that combines OpenAI Agents SDK for voice with Mem0's memory capabilities:
+
+```python
+import asyncio
+import os
+import logging
+from typing import Optional, List, Dict, Any
+import numpy as np
+import sounddevice as sd
+from pydantic import BaseModel
+
+# OpenAI Agents SDK imports
+from agents import (
+    Agent,
+    function_tool
+)
+from agents.voice import (
+    AudioInput,
+    SingleAgentVoiceWorkflow,
+    VoicePipeline
+)
+from agents.extensions.handoff_prompt import prompt_with_handoff_instructions
+
+# Mem0 imports
+from mem0 import AsyncMemoryClient
+
+# Set up API keys (replace with your actual keys)
+os.environ["OPENAI_API_KEY"] = "your-openai-api-key"
+os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
+
+# Define a global user ID for simplicity
+USER_ID = "voice_user"
+
+# Initialize Mem0 client
+mem0_client = AsyncMemoryClient()
+
+# Create tools that utilize Mem0's memory
+@function_tool
+async def save_memories(
+    memory: str
+) -> str:
+    """
+    Store a user memory in memory.
+    Args:
+        memory: The memory to save
+    """
+    print(f"Saving memory: {memory} for user {USER_ID}")
+
+    # Store the preference in Mem0
+    memory_content = f"User memory - {memory}"
+    await mem0_client.add(
+        memory_content,
+        user_id=USER_ID,
+    )
+
+    return f"I've saved your memory: {memory}"
+
+@function_tool
+async def search_memories(
+    query: str
+) -> str:
+    """
+    Find memories relevant to the current conversation.
+    Args:
+        query: The search query to find relevant memories
+    """
+    print(f"Finding memories related to: {query}")
+    results = await mem0_client.search(
+        query,
+        user_id=USER_ID,
+        limit=5,
+        threshold=0.7,  # Higher threshold for more relevant results
+        output_format="v1.1"
+    )
+    
+    # Format and return the results
+    if not results.get('results', []):
+        return "I don't have any relevant memories about this topic."
+    
+    memories = [f"• {result['memory']}" for result in results.get('results', [])]
+    return "Here's what I remember that might be relevant:\n" + "\n".join(memories)
+
+# Create the agent with memory-enabled tools
+def create_memory_voice_agent():
+    # Create the agent with memory-enabled tools
+    agent = Agent(
+        name="Memory Assistant",
+        instructions=prompt_with_handoff_instructions(
+            """You're speaking to a human, so be polite and concise.
+            Always respond in clear, natural English.
+            You have the ability to remember information about the user.
+            Use the save_memories tool when the user shares an important information worth remembering.
+            Use the search_memories tool when you need context from past conversations or user asks you to recall something.
+            """,
+        ),
+        model="gpt-4o",
+        tools=[save_memories, search_memories],
+    )
+    
+    return agent
+
+async def record_from_microphone(duration=5, samplerate=24000):
+    """Record audio from the microphone for a specified duration."""
+    print(f"Recording for {duration} seconds...")
+    
+    # Create a buffer to store the recorded audio
+    frames = []
+    
+    # Callback function to store audio data
+    def callback(indata, frames_count, time_info, status):
+        frames.append(indata.copy())
+    
+    # Start recording
+    with sd.InputStream(samplerate=samplerate, channels=1, callback=callback, dtype=np.int16):
+        await asyncio.sleep(duration)
+    
+    # Combine all frames into a single numpy array
+    audio_data = np.concatenate(frames)
+    return audio_data
+
+async def main():
+    print("Starting Memory Voice Agent")
+    
+    # Create the agent and context
+    agent = create_memory_voice_agent()
+    
+    # Set up the voice pipeline
+    pipeline = VoicePipeline(
+        workflow=SingleAgentVoiceWorkflow(agent)
+    )
+    
+    # Configure TTS settings
+    pipeline.config.tts_settings.voice = "alloy"
+    pipeline.config.tts_settings.speed = 1.0
+    
+    try:
+        while True:
+            # Get user input
+            print("\nPress Enter to start recording (or 'q' to quit)...")
+            user_input = input()
+            if user_input.lower() == 'q':
+                break
+            
+            # Record and process audio
+            audio_data = await record_from_microphone(duration=5)
+            audio_input = AudioInput(buffer=audio_data)
+            
+            print("Processing your request...")
+            
+            # Process the audio input
+            result = await pipeline.run(audio_input)
+            
+            # Create an audio player
+            player = sd.OutputStream(samplerate=24000, channels=1, dtype=np.int16)
+            player.start()
+            
+            # Store the agent's response for adding to memory
+            agent_response = ""
+            
+            print("\nAgent response:")
+            # Play the audio stream as it comes in
+            async for event in result.stream():
+                if event.type == "voice_stream_event_audio":
+                    player.write(event.data)
+                elif event.type == "voice_stream_event_content":
+                    # Accumulate and print the text response
+                    content = event.data
+                    agent_response += content
+                    print(content, end="", flush=True)
+            
+            print("\n")
+            
+            # Example of saving the conversation to Mem0 after completion
+            if agent_response:
+                try:
+                    await mem0_client.add(
+                        f"Agent response: {agent_response}", 
+                        user_id=USER_ID,
+                        metadata={"type": "agent_response"}
+                    )
+                except Exception as e:
+                    print(f"Failed to store memory: {e}")
+    
+    except KeyboardInterrupt:
+        print("\nExiting...")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Key Features of This Implementation
+
+This implementation offers several key features:
+
+1. **Simplified User Management**: Uses a global `USER_ID` variable for simplicity, but can be extended to manage multiple users.
+
+2. **Real Microphone Input**: Includes a `record_from_microphone()` function that captures actual voice input from your microphone.
+
+3. **Interactive Voice Loop**: Implements a continuous interaction loop, allowing for multiple back-and-forth exchanges.
+
+4. **Memory Management Tools**:
+   - `save_memories`: Stores user memories in Mem0
+   - `search_memories`: Searches for relevant past information
+
+5. **Voice Configuration**: Demonstrates how to configure TTS settings for the voice response.
+
+## Running the Example
+
+To run this example:
+
+1. Replace the placeholder API keys with your actual keys
+2. Make sure your microphone is properly connected
+3. Run the script with Python 3.8 or newer
+4. Press Enter to start recording, then speak your request
+5. Press 'q' to quit the application
+
+The agent will listen to your request, process it through the OpenAI model, utilize Mem0 for memory operations as needed, and respond both through text output and voice speech.
+
+## Best Practices for Voice Agents with Memory
+
+1. **Optimizing Memory for Voice**: Keep memories concise and relevant for voice responses.
+
+2. **Forgetting Mechanism**: Implement a way to delete or expire memories that are no longer relevant.
+
+3. **Context Preservation**: Store enough context with each memory to make retrieval effective.
+
+4. **Error Handling**: Implement robust error handling for memory operations, as voice interactions should continue smoothly even if memory operations fail.
+
+## Conclusion
+
+By combining OpenAI's Agents SDK with Mem0's memory capabilities, you can create voice agents that maintain persistent memory of user preferences and past interactions. This significantly enhances the user experience by making conversations more natural and personalized.
+
+As you build your voice application, experiment with different memory strategies and filtering approaches to find the optimal balance between comprehensive memory and efficient retrieval for your specific use case.
+
+## Debugging Function Tools
+
+When working with the OpenAI Agents SDK, you might notice that regular `print()` statements inside `@function_tool` decorated functions don't appear in your console output. This is because the Agents SDK captures and redirects standard output when executing these functions.
+
+To effectively debug your function tools, use Python's `logging` module instead:
+
+```python
+import logging
+
+# Set up logging at the top of your file
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    force=True
+)
+logger = logging.getLogger("memory_voice_agent")
+
+# Then use logger in your function tools
+@function_tool
+async def save_memories(
+    memory: str
+) -> str:
+    """Store a user memory in memory."""
+    # This will be visible in your console
+    logger.debug(f"Saving memory: {memory} for user {USER_ID}")
+    
+    # Rest of your function...
+```

docs/examples/mem0-with-ollama.mdx

@@ -2,6 +2,8 @@
 title: Mem0 with Ollama
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## Running Mem0 Locally with Ollama
 
 Mem0 can be utilized entirely locally by leveraging Ollama for both the embedding model and the language model (LLM). This guide will walk you through the necessary steps and provide the complete code to get you started.

docs/examples/multimodal-demo.mdx

@@ -2,6 +2,8 @@
 title: Multimodal Demo with Mem0
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Enhance your AI interactions with **Mem0**'s multimodal capabilities. Mem0 now supports image understanding, allowing for richer context and more natural interactions across supported AI platforms.
 
 > 🎉 Experience the power of multimodal AI! Test out Mem0's image understanding capabilities at [multimodal-demo.mem0.ai](https://multimodal-demo.mem0.ai)

docs/examples/openai-inbuilt-tools.mdx

@@ -0,0 +1,314 @@
+---
+title: OpenAI Inbuilt Tools
+---
+
+<Snippet file="paper-release.mdx" />
+
+Integrate Mem0’s memory capabilities with OpenAI’s Inbuilt Tools to create AI agents with persistent memory.
+
+## Getting Started
+
+### Installation
+
+```bash
+npm install mem0ai openai zod
+```
+
+## Environment Setup
+
+Save your Mem0 and OpenAI API keys in a `.env` file:
+
+```
+MEM0_API_KEY=your_mem0_api_key
+OPENAI_API_KEY=your_openai_api_key
+```
+
+Get your Mem0 API key from the [Mem0 Dashboard](https://app.mem0.ai/dashboard/api-keys).
+
+### Configuration
+
+```javascript
+const mem0Config = {
+    apiKey: process.env.MEM0_API_KEY,
+    user_id: "sample-user",
+};
+
+const openAIClient = new OpenAI();
+const mem0Client = new MemoryClient(mem0Config);
+```
+
+### Adding Memories
+
+Store user preferences, past interactions, or any relevant information:
+<CodeGroup>
+```javascript JavaScript
+async function addUserPreferences() {
+    const mem0Client = new MemoryClient(mem0Config);
+    
+    const userPreferences = "I Love BMW, Audi and Porsche. I Hate Mercedes. I love Red cars and Maroon cars. I have a budget of 120K to 150K USD. I like Audi the most.";
+    
+    await mem0Client.add([{
+        role: "user",
+        content: userPreferences,
+    }], mem0Config);
+}
+
+await addUserPreferences();
+```
+
+```json Output (Memories)
+ [
+  {
+    "id": "ff9f3367-9e83-415d-b9c5-dc8befd9a4b4",
+    "data": { "memory": "Loves BMW, Audi, and Porsche" },
+    "event": "ADD"
+  },
+  {
+    "id": "04172ce6-3d7b-45a3-b4a1-ee9798593cb4",
+    "data": { "memory": "Hates Mercedes" },
+    "event": "ADD"
+  },
+  {
+    "id": "db363a5d-d258-4953-9e4c-777c120de34d",
+    "data": { "memory": "Loves red cars and maroon cars" },
+    "event": "ADD"
+  },
+  {
+    "id": "5519aaad-a2ac-4c0d-81d7-0d55c6ecdba8",
+    "data": { "memory": "Has a budget of 120K to 150K USD" },
+    "event": "ADD"
+  },
+  {
+    "id": "523b7693-7344-4563-922f-5db08edc8634",
+    "data": { "memory": "Likes Audi the most" },
+    "event": "ADD"
+  }
+]
+```
+</CodeGroup>
+### Retrieving Memories
+
+Search for relevant memories based on the current user input:
+
+```javascript
+const relevantMemories = await mem0Client.search(userInput, mem0Config);
+```
+
+### Structured Responses with Zod
+
+Define structured response schemas to get consistent output formats:
+
+```javascript
+// Define the schema for a car recommendation
+const CarSchema = z.object({
+  car_name: z.string(),
+  car_price: z.string(),
+  car_url: z.string(),
+  car_image: z.string(),
+  car_description: z.string(),
+});
+
+// Schema for a list of car recommendations
+const Cars = z.object({
+  cars: z.array(CarSchema),
+});
+
+// Create a function tool based on the schema
+const carRecommendationTool = zodResponsesFunction({ 
+    name: "carRecommendations", 
+    parameters: Cars 
+});
+
+// Use the tool in your OpenAI request
+const response = await openAIClient.responses.create({
+    model: "gpt-4o",
+    tools: [{ type: "web_search_preview" }, carRecommendationTool],
+    input: `${getMemoryString(relevantMemories)}\n${userInput}`,
+});
+```
+
+### Using Web Search
+
+Combine memory with web search for up-to-date recommendations:
+
+```javascript
+const response = await openAIClient.responses.create({
+    model: "gpt-4o",
+    tools: [{ type: "web_search_preview" }, carRecommendationTool],
+    input: `${getMemoryString(relevantMemories)}\n${userInput}`,
+});
+```
+
+## Examples
+
+### Complete Car Recommendation System
+
+```javascript
+import MemoryClient from "mem0ai";
+import { OpenAI } from "openai";
+import { zodResponsesFunction } from "openai/helpers/zod";
+import { z } from "zod";
+import dotenv from 'dotenv';
+
+dotenv.config();
+
+const mem0Config = {
+    apiKey: process.env.MEM0_API_KEY,
+    user_id: "sample-user",
+};
+
+async function run() {
+    // Responses without memories
+    console.log("\n\nRESPONSES WITHOUT MEMORIES\n\n");
+    await main();
+
+    // Adding sample memories
+    await addSampleMemories();
+
+    // Responses with memories
+    console.log("\n\nRESPONSES WITH MEMORIES\n\n");
+    await main(true);
+}
+
+// OpenAI Response Schema
+const CarSchema = z.object({
+  car_name: z.string(),
+  car_price: z.string(),
+  car_url: z.string(),
+  car_image: z.string(),
+  car_description: z.string(),
+});
+
+const Cars = z.object({
+  cars: z.array(CarSchema),
+});
+
+async function main(memory = false) {
+  const openAIClient = new OpenAI();
+  const mem0Client = new MemoryClient(mem0Config);
+
+  const input = "Suggest me some cars that I can buy today.";
+
+  const tool = zodResponsesFunction({ name: "carRecommendations", parameters: Cars });
+
+  // Store the user input as a memory
+  await mem0Client.add([{
+    role: "user",
+    content: input,
+  }], mem0Config);
+
+  // Search for relevant memories
+  let relevantMemories = []
+  if (memory) {
+    relevantMemories = await mem0Client.search(input, mem0Config);
+  }
+
+  const response = await openAIClient.responses.create({
+    model: "gpt-4o",
+    tools: [{ type: "web_search_preview" }, tool],
+    input: `${getMemoryString(relevantMemories)}\n${input}`,
+  });
+
+  console.log(response.output);
+}
+
+async function addSampleMemories() {
+  const mem0Client = new MemoryClient(mem0Config);
+
+  const myInterests = "I Love BMW, Audi and Porsche. I Hate Mercedes. I love Red cars and Maroon cars. I have a budget of 120K to 150K USD. I like Audi the most.";
+  
+  await mem0Client.add([{
+    role: "user",
+    content: myInterests,
+  }], mem0Config);
+}
+
+const getMemoryString = (memories) => {
+    const MEMORY_STRING_PREFIX = "These are the memories I have stored. Give more weightage to the question by users and try to answer that first. You have to modify your answer based on the memories I have provided. If the memories are irrelevant you can ignore them. Also don't reply to this section of the prompt, or the memories, they are only for your reference. The MEMORIES of the USER are: \n\n";
+    const memoryString = memories.map((mem) => `${mem.memory}`).join("\n") ?? "";
+    return memoryString.length > 0 ? `${MEMORY_STRING_PREFIX}${memoryString}` : "";
+};
+
+run().catch(console.error);
+```
+
+### Responses
+
+<CodeGroup>
+    ```json Without Memories
+    {
+      "cars": [
+        {
+          "car_name": "Toyota Camry",
+          "car_price": "$25,000",
+          "car_url": "https://www.toyota.com/camry/",
+          "car_image": "https://link-to-toyota-camry-image.com",
+          "car_description": "Reliable mid-size sedan with great fuel efficiency."
+        },
+        {
+          "car_name": "Honda Accord",
+          "car_price": "$26,000",
+          "car_url": "https://www.honda.com/accord/",
+          "car_image": "https://link-to-honda-accord-image.com",
+          "car_description": "Comfortable and spacious with advanced safety features."
+        },
+        {
+          "car_name": "Ford Mustang",
+          "car_price": "$28,000",
+          "car_url": "https://www.ford.com/mustang/",
+          "car_image": "https://link-to-ford-mustang-image.com",
+          "car_description": "Iconic sports car with powerful engine options."
+        },
+        {
+          "car_name": "Tesla Model 3",
+          "car_price": "$38,000",
+          "car_url": "https://www.tesla.com/model3",
+          "car_image": "https://link-to-tesla-model3-image.com",
+          "car_description": "Electric vehicle with advanced technology and long range."
+        },
+        {
+          "car_name": "Chevrolet Equinox",
+          "car_price": "$24,000",
+          "car_url": "https://www.chevrolet.com/equinox/",
+          "car_image": "https://link-to-chevron-equinox-image.com",
+          "car_description": "Compact SUV with a spacious interior and user-friendly technology."
+        }
+      ]
+    }
+    ```
+  
+    ```json With Memories
+    {
+      "cars": [
+        {
+          "car_name": "Audi RS7",
+          "car_price": "$118,500",
+          "car_url": "https://www.audiusa.com/us/web/en/models/rs7/2023/overview.html",
+          "car_image": "https://www.audiusa.com/content/dam/nemo/us/models/rs7/my23/gallery/1920x1080_AOZ_A717_191004.jpg",
+          "car_description": "The Audi RS7 is a high-performance hatchback with a sleek design, powerful 591-hp twin-turbo V8, and luxurious interior. It's available in various colors including red."
+        },
+        {
+          "car_name": "Porsche Panamera GTS",
+          "car_price": "$129,300",
+          "car_url": "https://www.porsche.com/usa/models/panamera/panamera-models/panamera-gts/",
+          "car_image": "https://files.porsche.com/filestore/image/multimedia/noneporsche-panamera-gts-sample-m02-high/normal/8a6327c3-6c7f-4c6f-a9a8-fb9f58b21795;sP;twebp/porsche-normal.webp",
+          "car_description": "The Porsche Panamera GTS is a luxury sports sedan with a 473-hp V8 engine, exquisite handling, and available in stunning red. Balances sportiness and comfort."
+        },
+        {
+          "car_name": "BMW M5",
+          "car_price": "$105,500",
+          "car_url": "https://www.bmwusa.com/vehicles/m-models/m5/sedan/overview.html",
+          "car_image": "https://www.bmwusa.com/content/dam/bmwusa/M/m5/2023/bmw-my23-m5-sapphire-black-twilight-purple-exterior-02.jpg",
+          "car_description": "The BMW M5 is a powerhouse sedan with a 600-hp V8 engine, known for its great handling and luxury. It comes in several distinctive colors including maroon."
+        }
+      ]
+    }
+    ```
+</CodeGroup>
+
+## Resources
+
+- [Mem0 Documentation](https://docs.mem0.ai)
+- [Mem0 Dashboard](https://app.mem0.ai/dashboard)
+- [API Reference](https://docs.mem0.ai/api-reference)
+- [OpenAI Documentation](https://platform.openai.com/docs)

docs/examples/personal-ai-tutor.mdx

@@ -2,6 +2,8 @@
 title: Personalized AI Tutor
 ---
 
+<Snippet file="paper-release.mdx" />
+
 You can create a personalized AI Tutor using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
 
 ## Overview
@@ -20,6 +22,7 @@ pip install openai mem0ai
 Below is the complete code to create and interact with a Personalized AI Tutor using Mem0:
 
 ```python
+import os 
 from openai import OpenAI
 from mem0 import Memory
 
@@ -54,22 +57,21 @@ class PersonalAITutor:
         :param question: The question to ask the AI.
         :param user_id: Optional user ID to associate with the memory.
         """
-        # Start a streaming chat completion request to the AI
-        stream = self.client.chat.completions.create(
-            model="gpt-4",
-            stream=True,
-            messages=[
-                {"role": "system", "content": "You are a personal AI Tutor."},
-                {"role": "user", "content": question}
-            ]
+        # Start a streaming response request to the AI
+        response = self.client.responses.create(
+            model="gpt-4o",
+            instructions="You are a personal AI Tutor.",
+            input=question,
+            stream=True
         )
+
         # Store the question in memory
         self.memory.add(question, user_id=user_id, metadata={"app_id": self.app_id})
 
         # Print the response from the AI in real-time
-        for chunk in stream:
-            if chunk.choices[0].delta.content is not None:
-                print(chunk.choices[0].delta.content, end="")
+        for event in response:
+            if event.type == "response.output_text.delta":
+                print(event.delta, end="")
 
     def get_memories(self, user_id=None):
         """

docs/examples/personal-travel-assistant.mdx

@@ -1,6 +1,9 @@
 ---
 title: Personal AI Travel Assistant
 ---
+
+<Snippet file="paper-release.mdx" />
+
 Create a personalized AI Travel Assistant using Mem0. This guide provides step-by-step instructions and the complete code to get you started.
 
 ## Overview
@@ -63,18 +66,23 @@ class PersonalTravelAssistant:
     def ask_question(self, question, user_id):
         # Fetch previous related memories
         previous_memories = self.search_memories(question, user_id=user_id)
-        prompt = question
-        if previous_memories:
-            prompt = f"User input: {question}\n Previous memories: {previous_memories}"
-        self.messages.append({"role": "user", "content": prompt})
 
-        # Generate response using GPT-4o
-        response = self.client.chat.completions.create(
+        # Build the prompt
+        system_message = "You are a personal AI Assistant."
+
+        if previous_memories:
+            prompt = f"{system_message}\n\nUser input: {question}\nPrevious memories: {', '.join(previous_memories)}"
+        else:
+            prompt = f"{system_message}\n\nUser input: {question}"
+
+        # Generate response using Responses API
+        response = self.client.responses.create(
             model="gpt-4o",
-            messages=self.messages
+            input=prompt
         )
-        answer = response.choices[0].message.content
-        self.messages.append({"role": "assistant", "content": answer})
+
+        # Extract answer from the response
+        answer = response.output[0].content[0].text
 
         # Store the question in memory
         self.memory.add(question, user_id=user_id)

docs/examples/personalized-deep-research.mdx

@@ -2,6 +2,8 @@
 title: Personalized Deep Research
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Deep Research is an intelligent agent that synthesizes large amounts of online data and completes complex research tasks, customized to your unique preferences and insights. Built on Mem0's technology, it enhances AI-driven online exploration with personalized memories.
 
 ## Overview

docs/examples/youtube-assistant.mdx

@@ -0,0 +1,58 @@
+---
+title: YouTube Assistant Extension
+---
+
+<Snippet file="paper-release.mdx" />
+
+Enhance your YouTube experience with Mem0's **YouTube Assistant**, a Chrome extension that brings AI-powered chat directly to your YouTube videos. Get instant, personalized answers about video content while leveraging your own knowledge and memories - all without leaving the page.
+
+## Features
+
+- **Contextual AI Chat**: Ask questions about videos you're watching
+- **Seamless Integration**: Chat interface sits alongside YouTube's native UI
+- **Memory Integration**: Personalized responses based on your knowledge through Mem0
+- **Real-Time Memory**: Memories are updated in real-time based on your interactions
+
+## Demo Video
+
+<video
+  autoPlay
+  muted
+  loop
+  playsInline
+  width="700"
+  height="400"
+  src="https://github.com/user-attachments/assets/c0334ccd-311b-4dd7-8034-ef88204fc751"
+></video>
+
+## Installation
+
+This extension is not available on the Chrome Web Store yet. You can install it manually using below method:
+
+### Manual Installation (Developer Mode)
+
+1. **Download the Extension**: Clone or download the extension files from the [Mem0 GitHub repository](https://github.com/mem0ai/mem0/tree/main/examples).
+2. **Build**: Run `npm install` followed by `npm run build` to install the dependencies and build the extension.
+3. **Access Chrome Extensions**: Open Google Chrome and navigate to `chrome://extensions`.
+4. **Enable Developer Mode**: Toggle the "Developer mode" switch in the top right corner.
+5. **Load Unpacked Extension**: Click "Load unpacked" and select the directory containing the extension files.
+6. **Confirm Installation**: The Mem0 YouTube Assistant Extension should now appear in your Chrome toolbar.
+
+## Setup
+
+1. **Configure API Settings**: Click the extension icon and enter your OpenAI API key (required to use the extension)
+2. **Customize Settings**: Configure additional settings such as model, temperature, and memory settings
+3. **Navigate to YouTube**: Start using the assistant on any YouTube video
+4. **Memories**: Enter your Mem0 API key to enable personalized responses, and feed initial memories from settings
+
+## Example Prompts
+
+- "Can you summarize the main points of this video?"
+- "Explain the concept they just mentioned"
+- "How does this relate to what I already know?"
+- "What are some practical applications of this topic related to my work?"
+
+
+## Privacy and Data Security
+
+Your API keys are stored locally in your browser. Your messages are sent to the Mem0 API for extracting and retrieving memories. Mem0 is committed to ensuring your data's privacy and security.

docs/faqs.mdx

@@ -4,6 +4,7 @@ icon: "question"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
 
 <AccordionGroup>
     <Accordion title="How does Mem0 work?">
@@ -125,6 +126,23 @@ iconType: "solid"
         This flexibility allows you to create highly contextually aware AI applications that can adapt to specific user needs and situations. Metadata provides an additional dimension for memory retrieval, enabling more precise and relevant responses.
     </Accordion>
 
+    <Accordion title="How do I disable telemetry in Mem0?">
+        To disable telemetry in Mem0, you can set the `MEM0_TELEMETRY` environment variable to `False`:
+
+        ```bash
+        MEM0_TELEMETRY=False
+        ```
+
+        You can also disable telemetry programmatically in your code:
+
+        ```python
+        import os
+        os.environ["MEM0_TELEMETRY"] = "False"
+        ```
+
+        Setting this environment variable will prevent Mem0 from collecting and sending any usage data, ensuring complete privacy for your application.
+    </Accordion>
+
 </AccordionGroup>
 
 

docs/features.mdx

@@ -4,6 +4,8 @@ icon: "wrench"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## Core features
 
 - **User, Session, and AI Agent Memory**: Retains information across sessions and interactions for users and AI agents, ensuring continuity and context.

docs/features/advanced-retrieval.mdx

@@ -4,6 +4,8 @@ icon: "magnifying-glass"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Mem0's **Advanced Retrieval** feature delivers superior search results by leveraging state-of-the-art search algorithms. Beyond the default search functionality, Mem0 offers the following advanced retrieval modes:
 
 1. **Keyword Search**

docs/features/async-client.mdx

@@ -5,6 +5,7 @@ icon: "bolt"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
 The `AsyncMemoryClient` is an asynchronous client for interacting with the Mem0 API. It provides similar functionality to the synchronous `MemoryClient` but allows for non-blocking operations, which can be beneficial in applications that require high concurrency.
 
 ## Initialization

docs/features/contextual-add.mdx

@@ -0,0 +1,207 @@
+---
+title: Contextual Add (ADD v2)
+icon: "square-plus"
+iconType: "solid"
+---
+
+<Snippet file="paper-release.mdx" />
+
+Mem0 now supports an contextual add version (v2). To use it, set `version="v2"` during the add call. The default version is v1, which is deprecated now. We recommend migrating to `v2` for new applications.
+
+## Key Differences Between v1 and v2
+
+### Version 1 (Legacy)
+In v1 (default), users needed to pass either the entire conversation history or past k messages with each new message to generate properly contextualized memories. This approach required:
+
+- Manually tracking and sending previous messages using a sliding window approach
+- Increased payload sizes as conversations grew longer, requiring careful window size management
+
+<CodeGroup>
+
+```python Python
+# First interaction
+messages1 = [
+    {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},
+    {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."}
+]
+client.add(messages1, user_id="alex")
+
+# Second interaction - must include previous messages for context
+messages2 = [
+    {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},
+    {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."},
+    {"role": "user", "content": "I like to eat sushi, and yesterday I went to Sunnyvale to eat sushi with my friends."},
+    {"role": "assistant", "content": "Sushi is really a tasty choice. What did you do this weekend?"}
+]
+client.add(messages2, user_id="alex")
+```
+
+```javascript JavaScript
+// First interaction
+const messages1 = [
+    {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},
+    {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."}
+];
+client.add(messages1, { user_id: "alex" })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+
+// Second interaction - must include previous messages for context
+const messages2 = [
+    {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},
+    {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."},
+    {"role": "user", "content": "I like to eat sushi, and yesterday I went to Sunnyvale to eat sushi with my friends."},
+    {"role": "assistant", "content": "Sushi is really a tasty choice. What did you do this weekend?"}
+];
+client.add(messages2, { user_id: "alex" })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+```
+
+</CodeGroup>
+
+### Version 2 (Recommended)
+In v2, Mem0 automatically manages conversation context. Users only need to send new messages, and the system will:
+
+- Automatically retrieve relevant conversation history
+- Generate properly contextualized memories
+- Reduce payload sizes and simplify integration
+
+<CodeGroup>
+
+```python Python
+# First interaction
+messages1 = [
+    {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},
+    {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."}
+]
+client.add(messages1, user_id="alex", version="v2")
+
+# Second interaction - only need to send new messages
+messages2 = [
+    {"role": "user", "content": "I like to eat sushi, and yesterday I went to Sunnyvale to eat sushi with my friends."},
+    {"role": "assistant", "content": "Sushi is really a tasty choice. What did you do this weekend?"}
+]
+client.add(messages2, user_id="alex", version="v2")
+```
+
+```javascript JavaScript
+// First interaction
+const messages1 = [
+    {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},
+    {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."}
+];
+client.add(messages1, { user_id: "alex", version: "v2" })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+
+// Second interaction - only need to send new messages
+const messages2 = [
+    {"role": "user", "content": "I like to eat sushi, and yesterday I went to Sunnyvale to eat sushi with my friends."},
+    {"role": "assistant", "content": "Sushi is really a tasty choice. What did you do this weekend?"}
+];
+client.add(messages2, { user_id: "alex", version: "v2" })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+```
+
+</CodeGroup>
+
+## Benefits of Using v2
+
+1. **Simplified Integration**: No need to track and manage conversation history
+2. **Reduced Payload Size**: Only send new messages, not the entire conversation
+3. **Improved Memory Quality**: Automatic context retrieval ensures better memory generation
+
+## Understanding ID Parameters in v2
+
+When using contextual add v2, you have different options for how to organize and retrieve memories:
+
+### Using Only `user_id`
+
+When you provide only a `user_id`:
+
+- Memories are associated with this user's long-term memory store
+- The system will automatically retrieve relevant context from all of the user's previous conversations
+- These memories persist indefinitely across all of the user's sessions
+- Ideal for maintaining persistent user information (preferences, personal details, etc.)
+
+<CodeGroup>
+
+```python Python
+# Adding to long-term user memory
+messages = [
+    {"role": "user", "content": "I'm allergic to peanuts and shellfish."},
+    {"role": "assistant", "content": "I've noted your allergies to peanuts and shellfish."}
+]
+client.add(messages, user_id="alex", version="v2")
+```
+
+```javascript JavaScript
+// Adding to long-term user memory
+const messages = [
+    {"role": "user", "content": "I'm allergic to peanuts and shellfish."},
+    {"role": "assistant", "content": "I've noted your allergies to peanuts and shellfish."}
+];
+client.add(messages, { user_id: "alex", version: "v2" })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+```
+
+</CodeGroup>
+
+### Using `user_id` with `run_id`
+
+When you provide both `user_id` and `run_id`:
+
+- Memories are associated with a specific conversation session or interaction
+- The system will retrieve context primarily from this specific session
+- These memories are still tied to the user but are organized by the specific session
+- Ideal for maintaining context within a specific conversation flow or task
+- Helps prevent context from different conversations from interfering with each other
+
+<CodeGroup>
+
+```python Python
+# Adding to a specific conversation session
+messages = [
+    {"role": "user", "content": "For this trip to Paris, I want to focus on art museums."},
+    {"role": "assistant", "content": "Great! I'll help you plan your Paris trip with a focus on art museums."}
+]
+client.add(messages, user_id="alex", run_id="paris-trip-2024", version="v2")
+
+# Later in the same conversation session
+messages2 = [
+    {"role": "user", "content": "I'd like to visit the Louvre on Monday."},
+    {"role": "assistant", "content": "The Louvre is a great choice for Monday. Would you like information about opening hours?"}
+]
+client.add(messages2, user_id="alex", run_id="paris-trip-2024", version="v2")
+```
+
+```javascript JavaScript
+// Adding to a specific conversation session
+const messages = [
+    {"role": "user", "content": "For this trip to Paris, I want to focus on art museums."},
+    {"role": "assistant", "content": "Great! I'll help you plan your Paris trip with a focus on art museums."}
+];
+client.add(messages, { user_id: "alex", run_id: "paris-trip-2024", version: "v2" })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+
+// Later in the same conversation session
+const messages2 = [
+    {"role": "user", "content": "I'd like to visit the Louvre on Monday."},
+    {"role": "assistant", "content": "The Louvre is a great choice for Monday. Would you like information about opening hours?"}
+];
+client.add(messages2, { user_id: "alex", run_id: "paris-trip-2024", version: "v2" })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+```
+
+</CodeGroup>
+
+Using `run_id` helps you organize memories into logical sessions or tasks, making it easier to maintain context for specific interactions while still associating everything with the user's overall profile.
+
+If you have any questions, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx" />

docs/features/custom-categories.mdx

@@ -5,6 +5,8 @@ icon: "tags"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## How to set custom categories?
 
 You can now create custom categories tailored to your specific needs, instead of using the default categories such as travel, sports, music, and more (see [default categories](#default-categories) below). **When custom categories are provided, they will override the default categories.**

docs/features/custom-fact-extraction-prompt.mdx

@@ -1,25 +1,27 @@
 ---
-title: Custom Prompts
-description: 'Enhance your product experience by adding custom prompts tailored to your needs'
+title: Custom Fact Extraction Prompt
+description: 'Enhance your product experience by adding custom fact extraction prompt tailored to your needs'
 icon: "pencil"
 iconType: "solid"
 ---
 
-## Introduction to Custom Prompts
+<Snippet file="paper-release.mdx" />
 
-Custom prompts allow you to tailor the behavior of your Mem0 instance to specific use cases or domains. 
-By defining a custom prompt, you can control how information is extracted, processed, and stored in your memory system.
+## Introduction to Custom Fact Extraction Prompt
 
-To create an effective custom prompt:
+Custom fact extraction prompt allow you to tailor the behavior of your Mem0 instance to specific use cases or domains. 
+By defining it, you can control how information is extracted from the user's message.
+
+To create an effective custom fact extraction prompt:
 1. Be specific about the information to extract.
 2. Provide few-shot examples to guide the LLM.
 3. Ensure examples follow the format shown below.
 
-Example of a custom prompt:
+Example of a custom fact extraction prompt:
 
 <CodeGroup>
 ```python Python
-custom_prompt = """
+custom_fact_extraction_prompt = """
 Please only extract entities containing customer support information, order details, and user information. 
 Here are some few shot examples:
 
@@ -67,7 +69,7 @@ Return the facts and customer information in a json format as shown above.
 ```
 </CodeGroup>
 
-Here we initialize the custom prompt in the config:
+Here we initialize the custom fact extraction prompt in the config:
 
 <CodeGroup>
 ```python Python
@@ -82,7 +84,7 @@ config = {
             "max_tokens": 2000,
         }
     },
-    "custom_prompt": custom_prompt,
+    "custom_fact_extraction_prompt": custom_fact_extraction_prompt,
     "version": "v1.1"
 }
 
@@ -166,4 +168,4 @@ await memory.add('I like going to hikes', { userId: "user123" });
 ```
 </CodeGroup>
 
-The custom prompt will process both the user and assistant messages to extract relevant information according to the defined format.
+The custom fact extraction prompt will process both the user and assistant messages to extract relevant information according to the defined format.

docs/features/custom-instructions.mdx

@@ -5,6 +5,8 @@ icon: "pencil"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## Introduction to Custom Instructions
 
 Custom instructions allow you to define specific guidelines for your project. This feature helps ensure consistency and provides clear direction for handling project-specific requirements.

docs/features/custom-update-memory-prompt.mdx

@@ -0,0 +1,242 @@
+---
+title: Custom Update Memory Prompt
+icon: "pencil"
+iconType: "solid"
+---
+
+<Snippet file="paper-release.mdx" />
+
+Update memory prompt is a prompt used to determine the action to be performed on the memory. 
+By customizing this prompt, you can control how the memory is updated.  
+
+
+## Introduction  
+Mem0 memory system compares the newly retrieved facts with the existing memory and determines the action to be performed on the memory.  
+The kinds of actions are:
+- Add
+    - Add the newly retrieved facts to the memory.
+- Update
+    - Update the existing memory with the newly retrieved facts.
+- Delete
+    - Delete the existing memory.
+- No Change
+    - Do not make any changes to the memory.
+  
+### Example
+Example of a custom update memory prompt:
+
+<CodeGroup>
+```python Python
+UPDATE_MEMORY_PROMPT = """You are a smart memory manager which controls the memory of a system.
+You can perform four operations: (1) add into the memory, (2) update the memory, (3) delete from the memory, and (4) no change.
+
+Based on the above four operations, the memory will change.
+
+Compare newly retrieved facts with the existing memory. For each new fact, decide whether to:
+- ADD: Add it to the memory as a new element
+- UPDATE: Update an existing memory element
+- DELETE: Delete an existing memory element
+- NONE: Make no change (if the fact is already present or irrelevant)
+
+There are specific guidelines to select which operation to perform:
+
+1. **Add**: If the retrieved facts contain new information not present in the memory, then you have to add it by generating a new ID in the id field.
+- **Example**:
+    - Old Memory:
+        [
+            {
+                "id" : "0",
+                "text" : "User is a software engineer"
+            }
+        ]
+    - Retrieved facts: ["Name is John"]
+    - New Memory:
+        {
+            "memory" : [
+                {
+                    "id" : "0",
+                    "text" : "User is a software engineer",
+                    "event" : "NONE"
+                },
+                {
+                    "id" : "1",
+                    "text" : "Name is John",
+                    "event" : "ADD"
+                }
+            ]
+
+        }
+
+2. **Update**: If the retrieved facts contain information that is already present in the memory but the information is totally different, then you have to update it. 
+If the retrieved fact contains information that conveys the same thing as the elements present in the memory, then you have to keep the fact which has the most information. 
+Example (a) -- if the memory contains "User likes to play cricket" and the retrieved fact is "Loves to play cricket with friends", then update the memory with the retrieved facts.
+Example (b) -- if the memory contains "Likes cheese pizza" and the retrieved fact is "Loves cheese pizza", then you do not need to update it because they convey the same information.
+If the direction is to update the memory, then you have to update it.
+Please keep in mind while updating you have to keep the same ID.
+Please note to return the IDs in the output from the input IDs only and do not generate any new ID.
+- **Example**:
+    - Old Memory:
+        [
+            {
+                "id" : "0",
+                "text" : "I really like cheese pizza"
+            },
+            {
+                "id" : "1",
+                "text" : "User is a software engineer"
+            },
+            {
+                "id" : "2",
+                "text" : "User likes to play cricket"
+            }
+        ]
+    - Retrieved facts: ["Loves chicken pizza", "Loves to play cricket with friends"]
+    - New Memory:
+        {
+        "memory" : [
+                {
+                    "id" : "0",
+                    "text" : "Loves cheese and chicken pizza",
+                    "event" : "UPDATE",
+                    "old_memory" : "I really like cheese pizza"
+                },
+                {
+                    "id" : "1",
+                    "text" : "User is a software engineer",
+                    "event" : "NONE"
+                },
+                {
+                    "id" : "2",
+                    "text" : "Loves to play cricket with friends",
+                    "event" : "UPDATE",
+                    "old_memory" : "User likes to play cricket"
+                }
+            ]
+        }
+
+
+3. **Delete**: If the retrieved facts contain information that contradicts the information present in the memory, then you have to delete it. Or if the direction is to delete the memory, then you have to delete it.
+Please note to return the IDs in the output from the input IDs only and do not generate any new ID.
+- **Example**:
+    - Old Memory:
+        [
+            {
+                "id" : "0",
+                "text" : "Name is John"
+            },
+            {
+                "id" : "1",
+                "text" : "Loves cheese pizza"
+            }
+        ]
+    - Retrieved facts: ["Dislikes cheese pizza"]
+    - New Memory:
+        {
+        "memory" : [
+                {
+                    "id" : "0",
+                    "text" : "Name is John",
+                    "event" : "NONE"
+                },
+                {
+                    "id" : "1",
+                    "text" : "Loves cheese pizza",
+                    "event" : "DELETE"
+                }
+        ]
+        }
+
+4. **No Change**: If the retrieved facts contain information that is already present in the memory, then you do not need to make any changes.
+- **Example**:
+    - Old Memory:
+        [
+            {
+                "id" : "0",
+                "text" : "Name is John"
+            },
+            {
+                "id" : "1",
+                "text" : "Loves cheese pizza"
+            }
+        ]
+    - Retrieved facts: ["Name is John"]
+    - New Memory:
+        {
+        "memory" : [
+                {
+                    "id" : "0",
+                    "text" : "Name is John",
+                    "event" : "NONE"
+                },
+                {
+                    "id" : "1",
+                    "text" : "Loves cheese pizza",
+                    "event" : "NONE"
+                }
+            ]
+        }
+"""
+```
+</CodeGroup>  
+
+## Output format
+The prompt needs to guide the output to follow the structure as shown below:
+<CodeGroup>
+```json Add
+{
+    "memory": [
+        {
+            "id" : "0",
+            "text" : "This information is new",
+            "event" : "ADD"
+        }
+    ]
+}
+```
+
+```json Update
+{
+    "memory": [
+        {
+            "id" : "0",
+            "text" : "This information replaces the old information",
+            "event" : "UPDATE",
+            "old_memory" : "Old information"
+        }
+    ]
+}
+```
+
+```json Delete
+{
+    "memory": [
+        {
+            "id" : "0",
+            "text" : "This information will be deleted",
+            "event" : "DELETE"
+        }
+    ]
+}
+```
+
+```json No Change
+{
+    "memory": [
+        {
+            "id" : "0",
+            "text" : "No changes for this information",
+            "event" : "NONE"
+        }
+    ]
+}
+```
+</CodeGroup>
+  
+  
+## custom update memory prompt vs custom prompt
+
+| Feature | `custom_update_memory_prompt` | `custom_prompt` |
+|---------|-------------------------------|-----------------|
+| Use case | Determine the action to be performed on the memory | Extract the facts from messages |
+| Reference | Retrieved facts from messages and old memory | Messages |
+| Output | Action to be performed on the memory | Extracted facts |

docs/features/direct-import.mdx

@@ -5,6 +5,8 @@ icon: "arrow-right"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## How to use Direct Import?
 The Direct Import feature allows users to skip the memory deduction phase and directly input pre-defined memories into the system for storage and retrieval.
 To enable this feature, you need to set the `infer` parameter to `False` in the `add` method.

docs/features/expiration-date.mdx

@@ -0,0 +1,114 @@
+---
+title: Expiration Date
+description: 'Set time-bound memories in Mem0 with automatic expiration dates to manage temporal information effectively.'
+icon: "clock"
+iconType: "solid"
+---
+
+<Snippet file="paper-release.mdx" />
+
+## Benefits of Memory Expiration
+
+Setting expiration dates for memories offers several advantages:
+
+• **Time-Sensitive Information Management**: Handle information that's only relevant for a specific time period.
+
+• **Event-Based Memory**: Manage information related to upcoming events that becomes irrelevant after the event passes.
+
+These benefits enable more sophisticated memory management for applications where temporal context matters.
+
+## Setting Memory Expiration Date
+
+You can set an expiration date for memories, after which they will no longer be retrieved in searches. This is useful for creating temporary memories or memories that are only relevant for a specific time period.
+
+<CodeGroup>
+
+```python Python
+import datetime
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+messages = [
+    {
+        "role": "user", 
+        "content": "I'll be in San Francisco until end of this month."
+    }
+]
+
+# Set an expiration date for this memory
+client.add(messages=messages, user_id="alex", expiration_date=str(datetime.datetime.now().date() + datetime.timedelta(days=30)))
+
+# You can also use an explicit date string
+client.add(messages=messages, user_id="alex", expiration_date="2023-08-31")
+```
+
+```javascript JavaScript
+import MemoryClient from 'mem0ai';
+const client = new MemoryClient({ apiKey: 'your-api-key' });
+
+const messages = [
+    {
+        "role": "user", 
+        "content": "I'll be in San Francisco until end of this month."
+    }
+];
+
+// Set an expiration date 30 days from now
+const expirationDate = new Date();
+expirationDate.setDate(expirationDate.getDate() + 30);
+client.add(messages, { 
+    user_id: "alex", 
+    expiration_date: expirationDate.toISOString().split('T')[0] 
+})
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+
+// You can also use an explicit date string
+client.add(messages, { 
+    user_id: "alex", 
+    expiration_date: "2023-08-31" 
+})
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+```
+
+```bash cURL
+curl -X POST "https://api.mem0.ai/v1/memories/" \
+     -H "Authorization: Token your-api-key" \
+     -H "Content-Type: application/json" \
+     -d '{
+         "messages": [
+             {
+                "role": "user", 
+                "content": "I'll be in San Francisco until end of this month."
+            }
+         ],
+         "user_id": "alex",
+         "expiration_date": "2023-08-31"
+     }'
+```
+
+```json Output
+{
+    "results": [
+        {
+            "id": "a1b2c3d4-e5f6-4g7h-8i9j-k0l1m2n3o4p5",
+            "data": {
+                "memory": "In San Francisco until end of this month"
+            },
+            "event": "ADD"
+        }
+    ]
+}
+```
+
+</CodeGroup>
+
+<Note>
+Once a memory reaches its expiration date, it won't be included in search or get results, though the data remains stored in the system.
+</Note>
+
+If you have any questions, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx" />

docs/features/feedback-mechanism.mdx

@@ -0,0 +1,64 @@
+---
+title: Feedback Mechanism
+icon: "thumbs-up"
+iconType: "solid"
+---
+
+<Snippet file="paper-release.mdx" />
+
+Mem0's **Feedback Mechanism** allows you to provide feedback on the memories generated by your application. This feedback is used to improve the accuracy of the memories and the search results.
+
+## How it works
+
+The feedback mechanism is a simple API that allows you to provide feedback on the memories generated by your application. The feedback is stored in the database and is used to improve the accuracy of the memories and the search results. Over time, Mem0 continuously learns from this feedback, refining its memory generation and search capabilities for better performance.
+
+## Give Feedback
+
+You can give feedback on a memory by calling the `feedback` method on the Mem0 client.
+
+<CodeGroup>
+
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your_api_key")
+
+client.feedback(memory_id="your-memory-id", feedback="NEGATIVE", feedback_reason="I don't like this memory because it is not relevant.")
+```
+
+```javascript JavaScript
+import MemoryClient from 'mem0ai';
+
+const client = new MemoryClient({ apiKey: 'your-api-key'});
+
+client.feedback({
+    memory_id: "your-memory-id", 
+    feedback: "NEGATIVE", 
+    feedback_reason: "I don't like this memory because it is not relevant."
+})
+```
+
+</CodeGroup>
+
+## Feedback Types
+
+The `feedback` parameter can be one of the following values:
+
+- `POSITIVE`: The memory is useful.
+- `NEGATIVE`: The memory is not useful.
+- `VERY_NEGATIVE`: The memory is not useful at all.
+
+## Parameters
+
+The `feedback` method takes the following parameters:
+
+- `memory_id`: The ID of the memory to give feedback on.
+- `feedback`: The feedback to give on the memory. (Optional)
+- `feedback_reason`: The reason for the feedback. (Optional)
+
+The `feedback_reason` parameter is optional and can be used to provide a reason for the feedback.
+
+<Note>
+You can pass `None` or `null` to the `feedback` and `feedback_reason` parameters to remove the feedback for a memory.
+</Note>
+

docs/features/graph-memory.mdx

@@ -0,0 +1,297 @@
+---
+title: Graph Memory
+icon: "circle-nodes"
+iconType: "solid"
+description: "Enable graph-based memory retrieval for more contextually relevant results"
+---
+
+<Snippet file="paper-release.mdx" />
+
+## Overview
+
+Graph Memory enhances memory pipeline by creating relationships between entities in your data. It builds a network of interconnected information for more contextually relevant search results.
+
+This feature allows your AI applications to understand connections between entities, providing richer context for responses. It's ideal for applications needing relationship tracking and nuanced information retrieval across related memories.
+
+## How Graph Memory Works
+
+The Graph Memory feature analyzes how each entity connects and relates to each other. When enabled:
+
+1. Mem0 automatically builds a graph representation of entities
+2. Retrieval considers graph relationships between entities
+3. Results include entities that may be contextually important even if they're not direct semantic matches
+
+## Using Graph Memory
+
+To use Graph Memory, you need to enable it in your API calls by setting the `enable_graph=True` parameter. You'll also need to specify `output_format="v1.1"` to receive the enriched response format.
+
+### Adding Memories with Graph Memory
+
+When adding new memories, enable Graph Memory to automatically build relationships with existing memories:
+
+<CodeGroup>
+
+```python Python
+from mem0 import MemoryClient
+
+client = MemoryClient(
+    api_key="your-api-key",
+    org_id="your-org-id",
+    project_id="your-project-id"
+)
+
+messages = [
+    {"role": "user", "content": "My name is Joseph"},
+    {"role": "assistant", "content": "Hello Joseph, it's nice to meet you!"},
+    {"role": "user", "content": "I'm from Seattle and I work as a software engineer"}
+]
+
+# Enable graph memory when adding
+client.add(
+    messages, 
+    user_id="joseph", 
+    version="v1", 
+    enable_graph=True, 
+    output_format="v1.1"
+)
+```
+
+```javascript JavaScript
+import { MemoryClient } from "mem0";
+
+const client = new MemoryClient({
+  apiKey: "your-api-key",
+  org_id: "your-org-id",
+  project_id: "your-project-id"
+});
+
+const messages = [
+  { role: "user", content: "My name is Joseph" },
+  { role: "assistant", content: "Hello Joseph, it's nice to meet you!" },
+  { role: "user", content: "I'm from Seattle and I work as a software engineer" }
+];
+
+// Enable graph memory when adding
+await client.add({
+  messages,
+  user_id: "joseph",
+  version: "v1",
+  enable_graph: true,
+  output_format: "v1.1"
+});
+```
+
+```json Output
+{
+  "results": [
+    {
+      "memory": "Name is Joseph",
+      "event": "ADD",
+      "id": "4a5a417a-fa10-43b5-8c53-a77c45e80438"
+    },
+    {
+      "memory": "Is from Seattle",
+      "event": "ADD",
+      "id": "8d268d0f-5452-4714-b27d-ae46f676a49d"
+    },
+    {
+      "memory": "Is a software engineer",
+      "event": "ADD",
+      "id": "5f0a184e-ddea-4fe6-9b92-692d6a901df8"
+    }
+  ]
+}
+```
+</CodeGroup>
+
+The graph memory would look like this:
+
+<Frame>
+  <img src="/images/graph-platform.png" alt="Graph Memory Visualization showing relationships between entities" />
+</Frame>
+
+<Caption>Graph Memory creates a network of relationships between entities, enabling more contextual retrieval</Caption>
+
+
+<Note>
+Response for the graph memory's `add` operation will not be available directly in the response. 
+As adding graph memories is an asynchronous operation due to heavy processing, 
+you can use the `get_all()` endpoint to retrieve the memory with the graph metadata.
+</Note>
+
+
+### Searching with Graph Memory
+
+When searching memories, Graph Memory helps retrieve entities that are contextually important even if they're not direct semantic matches.
+
+<CodeGroup>
+
+```python Python
+# Search with graph memory enabled
+results = client.search(
+    "what is my name?", 
+    user_id="joseph", 
+    enable_graph=True, 
+    output_format="v1.1"
+)
+
+print(results)
+```
+
+```javascript JavaScript
+// Search with graph memory enabled
+const results = await client.search({
+  query: "what is my name?",
+  user_id: "joseph",
+  enable_graph: true,
+  output_format: "v1.1"
+});
+
+console.log(results);
+```
+
+```json Output
+{
+  "results": [
+    {
+      "id": "4a5a417a-fa10-43b5-8c53-a77c45e80438",
+      "memory": "Name is Joseph",
+      "user_id": "joseph",
+      "metadata": null,
+      "categories": ["personal_details"],
+      "immutable": false,
+      "created_at": "2025-03-19T09:09:00.146390-07:00",
+      "updated_at": "2025-03-19T09:09:00.146404-07:00",
+      "score": 0.3621795393335552
+    },
+    {
+      "id": "8d268d0f-5452-4714-b27d-ae46f676a49d",
+      "memory": "Is from Seattle",
+      "user_id": "joseph",
+      "metadata": null,
+      "categories": ["personal_details"],
+      "immutable": false,
+      "created_at": "2025-03-19T09:09:00.170680-07:00",
+      "updated_at": "2025-03-19T09:09:00.170692-07:00",
+      "score": 0.31212713194651254
+    }
+  ],
+  "relations": [
+    {
+      "source": "joseph",
+      "source_type": "person",
+      "relationship": "name",
+      "target": "joseph",
+      "target_type": "person",
+      "score": 0.39
+    }
+  ]
+}
+```
+
+</CodeGroup>
+
+### Retrieving All Memories with Graph Memory
+
+When retrieving all memories, Graph Memory provides additional relationship context:
+
+<CodeGroup>
+
+```python Python
+# Get all memories with graph context
+memories = client.get_all(
+    user_id="joseph", 
+    enable_graph=True, 
+    output_format="v1.1"
+)
+
+print(memories)
+```
+
+```javascript JavaScript
+// Get all memories with graph context
+const memories = await client.getAll({
+  user_id: "joseph",
+  enable_graph: true,
+  output_format: "v1.1"
+});
+
+console.log(memories);
+```
+
+```json Output
+{
+  "results": [
+    {
+      "id": "5f0a184e-ddea-4fe6-9b92-692d6a901df8",
+      "memory": "Is a software engineer",
+      "user_id": "joseph",
+      "metadata": null,
+      "categories": ["professional_details"],
+      "immutable": false,
+      "created_at": "2025-03-19T09:09:00.194116-07:00",
+      "updated_at": "2025-03-19T09:09:00.194128-07:00",
+    },
+    {
+      "id": "8d268d0f-5452-4714-b27d-ae46f676a49d",
+      "memory": "Is from Seattle",
+      "user_id": "joseph",
+      "metadata": null,
+      "categories": ["personal_details"],
+      "immutable": false,
+      "created_at": "2025-03-19T09:09:00.170680-07:00",
+      "updated_at": "2025-03-19T09:09:00.170692-07:00",
+    },
+    {
+      "id": "4a5a417a-fa10-43b5-8c53-a77c45e80438",
+      "memory": "Name is Joseph",
+      "user_id": "joseph",
+      "metadata": null,
+      "categories": ["personal_details"],
+      "immutable": false,
+      "created_at": "2025-03-19T09:09:00.146390-07:00",
+      "updated_at": "2025-03-19T09:09:00.146404-07:00",
+    }
+  ],
+  "relations": [
+    {
+      "source": "joseph",
+      "source_type": "person",
+      "relationship": "name",
+      "target": "joseph",
+      "target_type": "person"
+    },
+    {
+      "source": "joseph",
+      "source_type": "person",
+      "relationship": "city",
+      "target": "seattle",
+      "target_type": "city"
+    },
+    {
+      "source": "joseph",
+      "source_type": "person",
+      "relationship": "job",
+      "target": "software engineer",
+      "target_type": "job"
+    }
+  ]
+}
+```
+
+</CodeGroup>
+
+## Best Practices
+
+- Enable Graph Memory for applications where understanding context and relationships between memories is important
+- Graph Memory works best with a rich history of related conversations
+- Consider Graph Memory for long-running assistants that need to track evolving information
+
+## Performance Considerations
+
+Graph Memory requires additional processing and may increase response times slightly for very large memory stores. However, for most use cases, the improved retrieval quality outweighs the minimal performance impact.
+
+If you have any questions, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx" />
+

docs/features/memory-export.mdx

@@ -5,6 +5,8 @@ icon: "file-export"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## Overview
 
 The Memory Export feature allows you to create structured exports of memories using customizable Pydantic schemas. This process enables you to transform your stored memories into specific data formats that match your needs. You can apply various filters to narrow down which memories to export and define exactly how the data should be structured.
@@ -71,13 +73,39 @@ Here's an example schema for extracting professional profile information:
 
 ### Submit Export Job
 
+You can optionally provide additional instructions to guide how memories are processed and structured during export using the `export_instructions` parameter.
+
 <CodeGroup>
 
 ```python Python
+# Basic export request
 response = client.create_memory_export(
     schema=json_schema,
-    user_id="user123"
+    user_id="alice"
 )
+
+# Export with custom instructions
+export_instructions = """
+1. Create a comprehensive profile with detailed information in each category
+2. Only mark fields as "None" when absolutely no relevant information exists
+3. Base all information directly on the user's memories
+4. When contradictions exist, prioritize the most recent information
+5. Clearly distinguish between factual statements and inferences
+"""
+
+# For create operation, using only user_id filter as requested
+filters = {
+    "AND": [
+        {"user_id": "alex"}
+    ]
+}
+
+response = client.create_memory_export(
+    schema=json_schema,
+    filters=filters,
+    export_instructions=export_instructions  # Optional
+)
+
 print(response)
 ```
 
@@ -87,7 +115,8 @@ curl -X POST "https://api.mem0.ai/v1/memories/export/" \
      -H "Content-Type: application/json" \
      -d '{
          "schema": {json_schema},
-         "user_id": "user123"
+         "user_id": "alice",
+         "export_instructions": "1. Create a comprehensive profile with detailed information\n2. Only mark fields as \"None\" when absolutely no relevant information exists"
      }'
 ```
 
@@ -107,12 +136,20 @@ Once the export job is complete, you can retrieve the structured data:
 <CodeGroup>
 
 ```python Python
-response = client.get_memory_export(user_id="user123")
+# Corrected date range (assuming you meant July 10 to July 20)
+filters = {
+    "AND": [
+        {"created_at": {"gte": "2024-07-10", "lte": "2024-07-20"}},
+        {"user_id": "alex"}
+    ]
+}
+
+response = client.get_memory_export(filters=filters)
 print(response)
 ```
 
 ```bash cURL
-curl -X GET "https://api.mem0.ai/v1/memories/export/?user_id=user123" \
+curl -X GET "https://api.mem0.ai/v1/memories/export/?user_id=alice" \
      -H "Authorization: Token your-api-key"
 ```
 
@@ -137,6 +174,7 @@ You can apply various filters to customize which memories are included in the ex
 - `agent_id`: Filter memories by specific agent
 - `run_id`: Filter memories by specific run
 - `session_id`: Filter memories by specific session
+- `created_at`: Filter memories by date
 
 <Note>
 The export process may take some time to complete, especially when dealing with a large number of memories or complex schemas.

docs/features/multimodal-support.mdx

@@ -1,15 +1,17 @@
 ---
 title: Multimodal Support
-description: Integrate images into your interactions with Mem0
+description: Integrate images and documents into your interactions with Mem0
 icon: "image"
 iconType: "solid"
 ---
 
-Mem0 extends its capabilities beyond text by supporting multimodal data, including images. With this feature, users can seamlessly integrate images into their interactions—allowing Mem0 to extract relevant information from visual content and enrich the memory system.
+<Snippet file="paper-release.mdx" />
+
+Mem0 extends its capabilities beyond text by supporting multimodal data, including images and documents. With this feature, users can seamlessly integrate visual and document content into their interactions—allowing Mem0 to extract relevant information from various media types and enrich the memory system.
 
 ## How It Works
 
-When a user submits an image, Mem0 processes it to extract textual information and other pertinent details. These details are then added to the user's memory, enhancing the system's ability to understand and recall visual inputs.
+When a user submits an image or document, Mem0 processes it to extract textual information and other pertinent details. These details are then added to the user's memory, enhancing the system's ability to understand and recall multimodal inputs.
 
 <CodeGroup>
 ```python Python
@@ -90,11 +92,18 @@ await client.add(messages, { user_id: "alice" })
 ```
 </CodeGroup>
 
-## Image Integration Methods
+## Supported Media Types
 
-Mem0 supports incorporating images into user interactions using two primary methods: by providing an image URL or by using a Base64-encoded image. The examples below demonstrate both approaches.
+Mem0 currently supports the following media types:
 
-## 1. Using an Image URL (Recommended)
+1. **Images** - JPG, PNG, and other common image formats
+2. **Documents** - MDX, TXT, and PDF files
+
+## Integration Methods
+
+### 1. Images
+
+#### Using an Image URL (Recommended)
 
 You can include an image by providing its direct URL. This method is simple and efficient for online images.
 
@@ -115,7 +124,7 @@ image_message = {
 client.add([image_message], user_id="alice")
 ```
 
-## 2. Using Base64 Image Encoding for Local Files
+#### Using Base64 Image Encoding for Local Files
 
 For local images—or when embedding the image directly is preferable—you can use a Base64-encoded string.
 
@@ -164,7 +173,134 @@ const imageMessage = {
 await client.add([imageMessage], { user_id: "alice" })
 ```
 </CodeGroup>
-Using these methods, you can seamlessly incorporate images into your interactions, further enhancing Mem0's multimodal capabilities.
+
+### 2. Text Documents (MDX/TXT)
+
+Mem0 supports both online and local text documents in MDX or TXT format.
+
+#### Using a Document URL
+
+```python
+# Define the document URL
+document_url = "https://www.w3.org/TR/2003/REC-PNG-20031110/iso_8859-1.txt"
+
+# Create the message dictionary with the document URL
+document_message = {
+    "role": "user",
+    "content": {
+        "type": "mdx_url",
+        "mdx_url": {
+            "url": document_url
+        }
+    }
+}
+client.add([document_message], user_id="alice")
+```
+
+#### Using Base64 Encoding for Local Documents
+
+```python
+import base64
+
+# Path to the document file
+document_path = "path/to/your/document.txt"
+
+# Function to convert file to Base64
+def file_to_base64(file_path):
+    with open(file_path, "rb") as file:
+        return base64.b64encode(file.read()).decode('utf-8')
+
+# Encode the document in Base64
+base64_document = file_to_base64(document_path)
+
+# Create the message dictionary with the Base64-encoded document
+document_message = {
+    "role": "user",
+    "content": {
+        "type": "mdx_url",
+        "mdx_url": {
+            "url": base64_document
+        }
+    }
+}
+client.add([document_message], user_id="alice")
+```
+
+### 3. PDF Documents
+
+Mem0 supports PDF documents via URL.
+
+```python
+# Define the PDF URL
+pdf_url = "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
+
+# Create the message dictionary with the PDF URL
+pdf_message = {
+    "role": "user",
+    "content": {
+        "type": "pdf_url",
+        "pdf_url": {
+            "url": pdf_url
+        }
+    }
+}
+client.add([pdf_message], user_id="alice")
+```
+
+## Complete Example with Multiple File Types
+
+Here's a comprehensive example showing how to work with different file types:
+
+```python
+import base64
+from mem0 import MemoryClient
+
+client = MemoryClient()
+
+def file_to_base64(file_path):
+    with open(file_path, "rb") as file:
+        return base64.b64encode(file.read()).decode('utf-8')
+
+# Example 1: Using an image URL
+image_message = {
+    "role": "user",
+    "content": {
+        "type": "image_url",
+        "image_url": {
+            "url": "https://example.com/sample-image.jpg"
+        }
+    }
+}
+
+# Example 2: Using a text document URL
+text_message = {
+    "role": "user",
+    "content": {
+        "type": "mdx_url",
+        "mdx_url": {
+            "url": "https://www.w3.org/TR/2003/REC-PNG-20031110/iso_8859-1.txt"
+        }
+    }
+}
+
+# Example 3: Using a PDF URL
+pdf_message = {
+    "role": "user",
+    "content": {
+        "type": "pdf_url",
+        "pdf_url": {
+            "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
+        }
+    }
+}
+
+# Add each message to the memory system
+client.add([image_message], user_id="alice")
+client.add([text_message], user_id="alice")
+client.add([pdf_message], user_id="alice")
+```
+
+Using these methods, you can seamlessly incorporate various media types into your interactions, further enhancing Mem0's multimodal capabilities.
 
 If you have any questions, please feel free to reach out to us using one of the following methods:
 

docs/features/openai_compatibility.mdx

@@ -4,6 +4,8 @@ icon: "code"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Mem0 can be easily integrated into chat applications to enhance conversational agents with structured memory. Mem0's APIs are designed to be compatible with OpenAI's, with the goal of making it easy to leverage Mem0 in applications you may have already built.
 
 If you have a `Mem0 API key`, you can use it to initialize the client. Alternatively, you can initialize Mem0 without an API key if you're using it locally.

docs/features/platform-overview.mdx

@@ -4,6 +4,8 @@ icon: "info"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Learn about the key features and capabilities that make Mem0 a powerful platform for memory management and retrieval.
 
 ## Core Features
@@ -12,6 +14,9 @@ Learn about the key features and capabilities that make Mem0 a powerful platform
   <Card title="Advanced Retrieval" icon="magnifying-glass" href="/features/advanced-retrieval">
     Superior search results using state-of-the-art algorithms, including keyword search, reranking, and filtering capabilities.
   </Card>
+  <Card title="Contextual Add" icon="square-plus" href="/features/contextual-add">
+    Only send your latest conversation history - we automatically retrieve the rest and generate properly contextualized memories.
+  </Card>
   <Card title="Multimodal Support" icon="photo-film" href="/features/multimodal-support">
     Process and analyze various types of content including images.
   </Card>
@@ -33,6 +38,9 @@ Learn about the key features and capabilities that make Mem0 a powerful platform
   <Card title="Memory Export" icon="file-export" href="/features/memory-export">
     Export memories in structured formats using customizable Pydantic schemas.
   </Card>
+  <Card title="Graph Memory" icon="graph" href="/features/graph-memory">
+    Add memories in the form of nodes and edges in a graph database and search for related memories.
+  </Card>
 </CardGroup>
 
 ## Getting Help

docs/features/selective-memory.mdx

@@ -5,6 +5,8 @@ icon: "filter"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## Benefits of Memory Customization
 
 Memory customization offers several key benefits:
@@ -93,7 +95,7 @@ messages = [
 
 <CodeGroup>
 ```python Code
-client.add(messages, user_id="alice", includes=includes)
+client.add(messages, user_id="alice", excludes=excludes)
 ```
 
 ```json Stored Memories

docs/features/timestamp.mdx

@@ -0,0 +1,138 @@
+---
+title: Memory Timestamps
+description: 'Add timestamps to your memories to maintain chronological accuracy and historical context'
+icon: "clock"
+iconType: "solid"
+---
+
+<Snippet file="paper-release.mdx" />
+
+## Overview
+
+The Memory Timestamps feature allows you to specify when a memory was created, regardless of when it's actually added to the system. This powerful capability enables you to:
+
+- Maintain accurate chronological ordering of memories
+- Import historical data with proper timestamps
+- Create memories that reflect when events actually occurred
+- Build timelines with precise temporal information
+
+By leveraging custom timestamps, you can ensure that your memory system maintains an accurate representation of when information was generated or events occurred.
+
+## Benefits of Custom Timestamps
+
+Custom timestamps offer several important benefits:
+
+• **Historical Accuracy**: Preserve the exact timing of past events and information.
+
+• **Data Migration**: Seamlessly migrate existing data while maintaining original timestamps.
+
+• **Time-Sensitive Analysis**: Enable time-based analysis and pattern recognition across memories.
+
+• **Consistent Chronology**: Maintain proper ordering of memories for coherent storytelling.
+
+## Using Custom Timestamps
+
+When adding new memories, you can specify a custom timestamp to indicate when the memory was created. This timestamp will be used instead of the current time.
+
+### Adding Memories with Custom Timestamps
+
+<CodeGroup>
+
+```python Python
+import os
+import time
+from datetime import datetime, timedelta
+
+from mem0 import MemoryClient
+
+os.environ["MEM0_API_KEY"] = "your-api-key"
+
+client = MemoryClient()
+
+# Get the current time
+current_time = datetime.now()
+
+# Calculate 5 days ago
+five_days_ago = current_time - timedelta(days=5)
+
+# Convert to Unix timestamp (seconds since epoch)
+unix_timestamp = int(five_days_ago.timestamp())
+
+# Add memory with custom timestamp
+client.add("I'm travelling to SF", user_id="user1", timestamp=unix_timestamp)
+```
+
+```javascript JavaScript
+import MemoryClient from 'mem0ai';
+const client = new MemoryClient({ apiKey: 'your-api-key' });
+
+// Get the current time
+const currentTime = new Date();
+
+// Calculate 5 days ago
+const fiveDaysAgo = new Date();
+fiveDaysAgo.setDate(currentTime.getDate() - 5);
+
+// Convert to Unix timestamp (seconds since epoch)
+const unixTimestamp = Math.floor(fiveDaysAgo.getTime() / 1000);
+
+// Add memory with custom timestamp
+client.add("I'm travelling to SF", { user_id: "user1", timestamp: unixTimestamp })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+```
+
+```bash cURL
+curl -X POST "https://api.mem0.ai/v1/memories/" \
+     -H "Authorization: Token your-api-key" \
+     -H "Content-Type: application/json" \
+     -d '{
+         "messages": [{"role": "user", "content": "I'm travelling to SF"}],
+         "user_id": "user1",
+         "timestamp": 1721577600
+     }'
+```
+
+```json Output
+{
+    "results": [
+        {
+            "id": "a1b2c3d4-e5f6-4g7h-8i9j-k0l1m2n3o4p5",
+            "data": {"memory": "Travelling to SF"},
+            "event": "ADD"
+        }
+    ]
+}
+```
+
+</CodeGroup>
+
+### Timestamp Format
+
+When specifying a custom timestamp, you should provide a Unix timestamp (seconds since epoch). This is an integer representing the number of seconds that have elapsed since January 1, 1970 (UTC).
+
+For example, to create a memory with a timestamp of January 1, 2023:
+
+<CodeGroup>
+
+```python Python
+# January 1, 2023 timestamp
+january_2023_timestamp = 1672531200  # Unix timestamp for 2023-01-01 00:00:00 UTC
+
+client.add("Important historical information", user_id="user1", timestamp=january_2023_timestamp)
+```
+
+```javascript JavaScript
+// January 1, 2023 timestamp
+const january2023Timestamp = 1672531200;  // Unix timestamp for 2023-01-01 00:00:00 UTC
+
+client.add("Important historical information", { user_id: "user1", timestamp: january2023Timestamp })
+    .then(response => console.log(response))
+    .catch(error => console.error(error));
+```
+
+</CodeGroup>
+
+If you have any questions, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx" />

docs/features/webhooks.mdx

@@ -5,6 +5,8 @@ icon: "webhook"
 iconType: "solid"
 ---
 
+<Snippet file="paper-release.mdx" />
+
 ## Overview
 
 Webhooks enable real-time notifications for memory events in your Mem0 project. Webhooks are configured at the project level, meaning each webhook is tied to a specific project and receives events solely from that project. You can configure webhooks to send HTTP POST requests to your specified URLs whenever memories are created, updated, or deleted.

docs/integrations.mdx

@@ -3,6 +3,8 @@ title: Overview
 description: How to integrate Mem0 into other frameworks
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Mem0 seamlessly integrates with popular AI frameworks and tools to enhance your LLM-based applications with persistent memory capabilities. By integrating Mem0, your applications benefit from:
 
 - Enhanced context management across multiple frameworks
@@ -220,4 +222,104 @@ Here are the available integrations for Mem0:
   >
     Integrate Mem0 as an MCP Server in Cursor.
   </Card>
+  <Card
+    title="Livekit"
+    icon={
+      <svg
+        viewBox="0 0 24 24"
+        xmlns="http://www.w3.org/2000/svg"
+        width="24"
+        height="24"
+      >
+        <text
+          x="12"
+          y="16"
+          fontFamily="Arial"
+          fontSize="12"
+          textAnchor="middle"
+          fill="currentColor"
+          fontWeight="bold"
+        >
+          LK
+        </text>
+      </svg>
+    }
+    href="/integrations/livekit"
+  >
+    Integrate Mem0 with Livekit for voice agents.
+  </Card>
+  <Card
+    title="ElevenLabs"
+    icon={
+      <svg
+        xmlns="http://www.w3.org/2000/svg"
+        width="24"
+        height="24"
+        viewBox="0 0 24 24"
+        fill="none"
+      >
+        <rect width="24" height="24" fill="white"/>
+        <rect x="8" y="4" width="2" height="16" fill="black"/>
+        <rect x="14" y="4" width="2" height="16" fill="black"/>
+      </svg>
+    }
+    href="/integrations/elevenlabs"
+  >
+    Build voice agents with memory using ElevenLabs Conversational AI.
+  </Card>
+  <Card
+    title="Pipecat"
+    icon={
+      <svg
+        viewBox="0 0 24 24"
+        xmlns="http://www.w3.org/2000/svg"
+        width="24"
+        height="24"
+      >
+        <path d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm0 18c-4.41 0-8-3.59-8-8s3.59-8 8-8 8 3.59 8 8-3.59 8-8 8z" fill="currentColor"/>
+        <circle cx="8.5" cy="9" r="1.5" fill="currentColor"/>
+        <circle cx="15.5" cy="9" r="1.5" fill="currentColor"/>
+        <path d="M12 16c1.66 0 3-1.34 3-3H9c0 1.66 1.34 3 3 3z" fill="currentColor"/>
+        <path d="M17.5 12c-.83 0-1.5-.67-1.5-1.5s.67-1.5 1.5-1.5 1.5.67 1.5 1.5-.67 1.5-1.5 1.5z" fill="currentColor"/>
+        <path d="M6.5 12c-.83 0-1.5-.67-1.5-1.5S5.67 9 6.5 9s1.5.67 1.5 1.5S7.33 12 6.5 12z" fill="currentColor"/>
+      </svg>
+    } 
+    href="/integrations/pipecat"
+  >
+    Build conversational AI agents with memory using Pipecat.
+  </Card>
+  <Card
+    title="Agno"
+    icon={
+      <svg
+        xmlns="http://www.w3.org/2000/svg"
+        width="24"
+        height="24"
+        viewBox="0 0 24 24"
+        fill="none"
+      >
+        <path d="M8 4h8v12h8" stroke="currentColor" strokeWidth="2" fill="none" transform="rotate(15, 12, 12)"/>
+      </svg>
+    }
+    href="/integrations/agno"
+  >
+    Build autonomous agents with memory using Agno framework.
+  </Card>
+  <Card
+    title="Keywords AI"
+    icon={
+      <svg
+        xmlns="http://www.w3.org/2000/svg"
+        width="24"
+        height="24"
+        viewBox="0 0 24 24"
+        fill="none"
+      >
+        <path fill-rule="evenodd" clip-rule="evenodd" d="M9.07513 1.1863C9.21663 1.07722 9.39144 1.01009 9.56624 1.01009C9.83261 1.01009 10.0823 1.12756 10.2405 1.33734L15.0101 7.4964V12.4136L16.4335 13.8401C16.7582 14.1673 16.7582 14.7043 16.4335 15.0316C16.1089 15.3588 15.5762 15.3588 15.2515 15.0316L13.3453 13.1016V8.07538L8.92529 2.36944V2.36105C8.64228 2.00024 8.70887 1.4716 9.07513 1.1863ZM18.976 14.4133C18.8344 14.3778 18.7003 14.3042 18.5894 14.1925L16.9163 12.5059C16.7249 12.3129 16.6416 12.0528 16.6749 11.8094V6.88385H16.6499L11.8553 0.691225C11.7282 0.529117 11.6716 0.333133 11.6803 0.140562C11.134 0.0481292 10.5726 0 10 0C4.47715 0 0 4.47715 0 10C0 15.5228 4.47715 20 10 20C13.9387 20 17.3456 17.7229 18.976 14.4133Z" fill="currentColor"></path>
+      </svg>
+    }
+    href="/integrations/keywords"
+  >
+    Build AI applications with persistent memory and comprehensive LLM observability.
+  </Card>
 </CardGroup>

docs/integrations/agno.mdx

@@ -0,0 +1,174 @@
+---
+title: Agno
+---
+<Snippet file="paper-release.mdx" />
+
+Integrate [**Mem0**](https://github.com/mem0ai/mem0) with [Agno](https://github.com/agno-agi/agno), a Python framework for building autonomous agents. This integration enables Agno agents to access persistent memory across conversations, enhancing context retention and personalization.
+
+## Overview
+
+1. 🧠 Store and retrieve memories from Mem0 within Agno agents
+2. 🖼️ Support for multimodal interactions (text and images)
+3. 🔍 Semantic search for relevant past conversations
+4. 🌐 Personalized responses based on user history
+
+## Prerequisites
+
+Before setting up Mem0 with Agno, ensure you have:
+
+1. Installed the required packages:
+```bash
+pip install agno-ai mem0ai
+```
+
+2. Valid API keys:
+   - [Mem0 API Key](https://app.mem0.ai/dashboard/api-keys)
+   - OpenAI API Key (for the agent model)
+
+## Integration Example
+
+The following example demonstrates how to create an Agno agent with Mem0 memory integration, including support for image processing:
+
+```python
+import base64
+from pathlib import Path
+from typing import Optional
+
+from agno.agent import Agent
+from agno.media import Image
+from agno.models.openai import OpenAIChat
+from mem0 import MemoryClient
+
+
+# Initialize the Mem0 client
+client = MemoryClient()
+
+# Define the agent
+agent = Agent(
+    name="Personal Agent",
+    model=OpenAIChat(id="gpt-4"),
+    description="You are a helpful personal agent that helps me with day to day activities."
+                "You can process both text and images.",
+    markdown=True
+)
+
+
+def chat_user(
+    user_input: Optional[str] = None,
+    user_id: str = "user_123",
+    image_path: Optional[str] = None
+) -> str:
+    """
+    Handle user input with memory integration, supporting both text and images.
+
+    Args:
+        user_input: The user's text input
+        user_id: Unique identifier for the user
+        image_path: Path to an image file if provided
+
+    Returns:
+        The agent's response as a string
+    """
+    if image_path:
+        # Convert image to base64
+        with open(image_path, "rb") as image_file:
+            base64_image = base64.b64encode(image_file.read()).decode("utf-8")
+
+        # Create message objects for text and image
+        messages = []
+
+        if user_input:
+            messages.append({
+                "role": "user",
+                "content": user_input
+            })
+
+        messages.append({
+            "role": "user",
+            "content": {
+                "type": "image_url",
+                "image_url": {
+                    "url": f"data:image/jpeg;base64,{base64_image}"
+                }
+            }
+        })
+
+        # Store messages in memory
+        client.add(messages, user_id=user_id)
+        print("✅ Image and text stored in memory.")
+
+    if user_input:
+        # Search for relevant memories
+        memories = client.search(user_input, user_id=user_id)
+        memory_context = "\n".join(f"- {m['memory']}" for m in memories)
+
+        # Construct the prompt
+        prompt = f"""
+You are a helpful personal assistant who helps users with their day-to-day activities and keeps track of everything.
+
+Your task is to:
+1. Analyze the given image (if present) and extract meaningful details to answer the user's question.
+2. Use your past memory of the user to personalize your answer.
+3. Combine the image content and memory to generate a helpful, context-aware response.
+
+Here is what I remember about the user:
+{memory_context}
+
+User question:
+{user_input}
+"""
+        # Get response from agent
+        if image_path:
+            response = agent.run(prompt, images=[Image(filepath=Path(image_path))])
+        else:
+            response = agent.run(prompt)
+
+        # Store the interaction in memory
+        client.add(f"User: {user_input}\nAssistant: {response.content}", user_id=user_id)
+        return response.content
+
+    return "No user input or image provided."
+
+
+# Example Usage
+if __name__ == "__main__":
+    response = chat_user(
+        "This is the picture of what I brought with me in the trip to Bahamas",
+        image_path="travel_items.jpeg",
+        user_id="user_123"
+    )
+    print(response)
+```
+
+## Key Features
+
+### 1. Multimodal Memory Storage
+
+The integration supports storing both text and image data:
+
+- **Text Storage**: Conversation history is saved in a structured format
+- **Image Analysis**: Agents can analyze images and store visual information
+- **Combined Context**: Memory retrieval combines both text and visual data
+
+### 2. Personalized Agent Responses
+
+Improve your agent's context awareness:
+
+- **Memory Retrieval**: Semantic search finds relevant past interactions
+- **User Preferences**: Personalize responses based on stored user information
+- **Continuity**: Maintain conversation threads across multiple sessions
+
+### 3. Flexible Configuration
+
+Customize the integration to your needs:
+
+- **User Identification**: Organize memories by user ID
+- **Memory Search**: Configure search relevance and result count
+- **Memory Formatting**: Support for various OpenAI message formats
+
+## Help & Resources
+
+- [Agno Documentation](https://docs.agno.com/introduction)
+- [Mem0 Platform](https://app.mem0.ai/)
+
+<Snippet file="get-help.mdx" />

docs/integrations/autogen.mdx

@@ -1,5 +1,7 @@
 Build conversational AI agents with memory capabilities. This integration combines AutoGen for creating AI agents with Mem0 for memory management, enabling context-aware and personalized interactions.
 
+<Snippet file="paper-release.mdx" />
+
 ## Overview
 
 In this guide, we'll explore an example of creating a conversational AI system with memory:

docs/integrations/crewai.mdx

@@ -2,6 +2,8 @@
 title: CrewAI
 ---
 
+<Snippet file="paper-release.mdx" />
+
 Build an AI system that combines CrewAI's agent-based architecture with Mem0's memory capabilities. This integration enables persistent memory across agent interactions and personalized task execution based on user history.
 
 ## Overview

docs/integrations/dify.mdx

@@ -2,6 +2,8 @@
 title: Dify
 ---
 
+<Snippet file="paper-release.mdx" />
+
 # Integrating Mem0 with Dify AI
 
 Mem0 brings a robust memory layer to Dify AI, empowering your AI agents with persistent conversation storage and retrieval capabilities. With Mem0, your Dify applications gain the ability to recall past interactions and maintain context, ensuring more natural and insightful conversations.