diff --git a/LLM.md b/LLM.md index e6e0ac6a4..1b98a3abf 100644 --- a/LLM.md +++ b/LLM.md @@ -86,7 +86,6 @@ const memory = new Memory({ const result = await memory.add('My name is John', { userId: 'john' }); ``` - ## Core API Reference ### Memory Class (Self-Hosted) @@ -323,11 +322,13 @@ config = MemoryConfig( - **supabase** - Supabase vector - **baidu** - Baidu vector database - **langchain** - LangChain vector stores +- **databricks** - Databricks vector stores #### Graph Store Providers (3 supported) - **neo4j** - Neo4j graph database - **memgraph** - Memgraph - **neptune** - AWS Neptune Analytics +- **kuzu** - Kuzu Graph database ### Configuration Examples @@ -415,6 +416,54 @@ config = MemoryConfig( ) ``` +#### LLM Providers +- **OpenAI** - GPT-4, GPT-3.5-turbo, and structured outputs +- **Anthropic** - Claude models with advanced reasoning +- **Google AI** - Gemini models for multimodal applications +- **AWS Bedrock** - Enterprise-grade AWS managed models +- **Azure OpenAI** - Microsoft Azure hosted OpenAI models +- **Groq** - High-performance LPU optimized models +- **Together** - Open-source model inference platform +- **Ollama** - Local model deployment for privacy +- **vLLM** - High-performance inference framework +- **LM Studio** - Local model management +- **DeepSeek** - Advanced reasoning models +- **Sarvam** - Indian language models +- **XAI** - xAI models +- **LiteLLM** - Unified LLM interface +- **LangChain** - LangChain LLM integration + +#### Vector Store Providers +- **Chroma** - AI-native open-source vector database +- **Qdrant** - High-performance vector similarity search +- **Pinecone** - Managed vector database with serverless options +- **Weaviate** - Open-source vector search engine +- **PGVector** - PostgreSQL extension for vector search +- **Milvus** - Open-source vector database for scale +- **Redis** - Real-time vector storage with Redis Stack +- **Supabase** - Open-source Firebase alternative +- **Upstash Vector** - Serverless vector database +- **Elasticsearch** - Distributed search and analytics +- **OpenSearch** - Open-source search and analytics +- **FAISS** - Facebook AI Similarity Search +- **MongoDB** - Document database with vector search +- **Azure AI Search** - Microsoft's search service +- **Vertex AI Vector Search** - Google Cloud vector search +- **Databricks Vector Search** - Delta Lake integration +- **Baidu** - Baidu vector database +- **LangChain** - LangChain vector store integration + +#### Embedding Providers +- **OpenAI** - High-quality text embeddings +- **Azure OpenAI** - Enterprise Azure-hosted embeddings +- **Google AI** - Gemini embedding models +- **AWS Bedrock** - Amazon embedding models +- **Hugging Face** - Open-source embedding models +- **Vertex AI** - Google Cloud enterprise embeddings +- **Ollama** - Local embedding models +- **Together** - Open-source model embeddings +- **LM Studio** - Local model embeddings +- **LangChain** - LangChain embedder integration ## TypeScript/JavaScript SDK @@ -569,6 +618,7 @@ print(result["relations"]) # Graph relationships - **Neo4j**: Full-featured graph database with Cypher queries - **Memgraph**: High-performance in-memory graph database - **Neptune**: AWS managed graph database service +- **kuzu** - OSS Kuzu Graph database ### Multimodal Memory diff --git a/docs/changelog.mdx b/docs/changelog.mdx index 92607d77e..81b0cf300 100644 --- a/docs/changelog.mdx +++ b/docs/changelog.mdx @@ -7,21 +7,33 @@ mode: "wide" + **New Features:** -- **Databricks Vector Search:** Added comprehensive support for Databricks Vector Search as a vector store provider - - Delta Sync Index integration with automatic synchronization from Delta tables - - Dual authentication support (Service Principal and Personal Access Token) - - Both STANDARD and STORAGE_OPTIMIZED endpoint types supported - - Self-managed and Databricks-computed embedding options - - Auto-creation of endpoints and indexes when not present - - Unity Catalog integration for secure data governance +- **Pinecone:** Added namespace support and improved type safety +- **Milvus:** Added db_name field to MilvusDBConfig +- **Vector Stores:** Added multi-id filters support +- **Vercel AI SDK:** Migration to AI SDK V5.0 +- **Python Support:** Added Python 3.12 support +- **Graph Memory:** Added sanitizer methods for nodes and relationships +- **LLM Monitoring:** Added monitoring callback support **Improvements:** -- **Documentation:** - - Added detailed Databricks Vector Search configuration guide with authentication methods - - Updated vector databases overview to include Databricks option - - Enhanced vector store documentation with embedding configuration examples +- **Performance:** Improved async handling in AsyncMemory class +- **Documentation:** Added async add announcement, personalized search docs, Neptune examples, V5 migration docs +- **Configuration:** Refactored base class config for LLMs, added sslmode for pgvector +- **Dependencies:** Updated psycopg to version 3, updated Docker compose + +**Bug Fixes:** +- **Tests:** Fixed failing tests and restricted package versions +- **Memgraph:** Fixed async attribute errors, n_embeddings usage, and indexing issues +- **Vector Stores:** Fixed Qdrant cloud indexing, Neo4j Cypher syntax, and LLM parameters +- **Graph Store:** Fixed LM config prioritization +- **Dependencies:** Fixed JSON import for psycopg + +**Refactoring:** +- **Google AI:** Refactored from Gemini to Google AI +- **Base Classes:** Refactored LLM base class configuration diff --git a/docs/components/vectordbs/overview.mdx b/docs/components/vectordbs/overview.mdx index 922493eeb..1b4c97c9e 100644 --- a/docs/components/vectordbs/overview.mdx +++ b/docs/components/vectordbs/overview.mdx @@ -23,7 +23,6 @@ See the list of supported vector databases below. - @@ -32,6 +31,7 @@ See the list of supported vector databases below. + ## Usage diff --git a/docs/docs.json b/docs/docs.json index c6c745ee7..629bf1aa0 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -160,7 +160,8 @@ "components/vectordbs/dbs/weaviate", "components/vectordbs/dbs/faiss", "components/vectordbs/dbs/langchain", - "components/vectordbs/dbs/baidu" + "components/vectordbs/dbs/baidu", + "components/vectordbs/dbs/databricks" ] } ] diff --git a/docs/examples/aws_example.mdx b/docs/examples/aws_example.mdx index c8a6b3428..cdd121edd 100644 --- a/docs/examples/aws_example.mdx +++ b/docs/examples/aws_example.mdx @@ -1,5 +1,5 @@ --- -title: Amazon Stack: AWS Bedrock, AOSS, and Neptune Analytics +title: "Amazon Stack: AWS Bedrock, AOSS, and Neptune Analytics" --- This example demonstrates how to configure and use the `mem0ai` SDK with **AWS Bedrock**, **OpenSearch Service (AOSS)**, and **AWS Neptune Analytics** for persistent memory capabilities in Python. diff --git a/docs/llms.txt b/docs/llms.txt index 38cf59c01..5a35e8aba 100644 --- a/docs/llms.txt +++ b/docs/llms.txt @@ -62,6 +62,16 @@ Key differentiators: - [AWS Bedrock](https://docs.mem0.ai/components/llms/models/aws_bedrock): Enterprise-grade AWS managed model integration - [Azure OpenAI](https://docs.mem0.ai/components/llms/models/azure_openai): Microsoft Azure hosted OpenAI models for enterprise environments - [Ollama](https://docs.mem0.ai/components/llms/models/ollama): Local model deployment for privacy-focused applications +- [vLLM](https://docs.mem0.ai/components/llms/models/vllm): High-performance inference framework +- [LM Studio](https://docs.mem0.ai/components/llms/models/lmstudio): Local model management and deployment +- [Together](https://docs.mem0.ai/components/llms/models/together): Open-source model inference platform +- [DeepSeek](https://docs.mem0.ai/components/llms/models/deepseek): Advanced reasoning models +- [Sarvam](https://docs.mem0.ai/components/llms/models/sarvam): Indian language models +- [XAI](https://docs.mem0.ai/components/llms/models/xai): xAI models integration +- [LiteLLM](https://docs.mem0.ai/components/llms/models/litellm): Unified LLM interface and proxy +- [LangChain](https://docs.mem0.ai/components/llms/models/langchain): LangChain LLM integration +- [OpenAI Structured](https://docs.mem0.ai/components/llms/models/openai_structured): OpenAI with structured output support +- [Azure OpenAI Structured](https://docs.mem0.ai/components/llms/models/azure_openai_structured): Azure OpenAI with structured outputs ### Supported Vector Databases @@ -72,14 +82,30 @@ Key differentiators: - [PGVector](https://docs.mem0.ai/components/vectordbs/dbs/pgvector): PostgreSQL extension for vector similarity search - [Milvus](https://docs.mem0.ai/components/vectordbs/dbs/milvus): Open-source vector database for AI applications at scale - [Redis](https://docs.mem0.ai/components/vectordbs/dbs/redis): Real-time vector storage and search with Redis Stack +- [Supabase](https://docs.mem0.ai/components/vectordbs/dbs/supabase): Open-source Firebase alternative with vector support +- [Upstash Vector](https://docs.mem0.ai/components/vectordbs/dbs/upstash_vector): Serverless vector database +- [Elasticsearch](https://docs.mem0.ai/components/vectordbs/dbs/elasticsearch): Distributed search and analytics engine +- [OpenSearch](https://docs.mem0.ai/components/vectordbs/dbs/opensearch): Open-source search and analytics platform +- [FAISS](https://docs.mem0.ai/components/vectordbs/dbs/faiss): Facebook AI Similarity Search library +- [MongoDB](https://docs.mem0.ai/components/vectordbs/dbs/mongodb): Document database with vector search capabilities +- [Azure AI Search](https://docs.mem0.ai/components/vectordbs/dbs/azure_ai_search): Microsoft's enterprise search service +- [Vertex AI Vector Search](https://docs.mem0.ai/components/vectordbs/dbs/vertex_ai_vector_search): Google Cloud's vector search service +- [Databricks](https://docs.mem0.ai/components/vectordbs/dbs/databricks): Delta Lake integration for vector search +- [Baidu](https://docs.mem0.ai/components/vectordbs/dbs/baidu): Baidu vector database integration +- [LangChain](https://docs.mem0.ai/components/vectordbs/dbs/langchain): LangChain vector store integration ### Supported Embeddings - [OpenAI Embeddings](https://docs.mem0.ai/components/embedders/models/openai): High-quality text embeddings with customizable dimensions - [Azure OpenAI Embeddings](https://docs.mem0.ai/components/embedders/models/azure_openai): Enterprise Azure-hosted embedding models +- [Google AI](https://docs.mem0.ai/components/embedders/models/google_ai): Gemini embedding models +- [AWS Bedrock](https://docs.mem0.ai/components/embedders/models/aws_bedrock): Amazon embedding models through Bedrock - [Hugging Face](https://docs.mem0.ai/components/embedders/models/hugging_face): Open-source embedding models for local deployment -- [Vertex AI](https://docs.mem0.ai/components/embedders/models/google_ai): Google Cloud's enterprise embedding models -- [Ollama Embeddings](https://docs.mem0.ai/components/embedders/models/ollama): Local embedding models for privacy-focused applications +- [Vertex AI](https://docs.mem0.ai/components/embedders/models/vertexai): Google Cloud's enterprise embedding models +- [Ollama](https://docs.mem0.ai/components/embedders/models/ollama): Local embedding models for privacy-focused applications +- [Together](https://docs.mem0.ai/components/embedders/models/together): Open-source model embeddings +- [LM Studio](https://docs.mem0.ai/components/embedders/models/lmstudio): Local model embeddings +- [LangChain](https://docs.mem0.ai/components/embedders/models/langchain): LangChain embedder integration ## Integrations @@ -114,4 +140,4 @@ Key differentiators: - [FAQs](https://docs.mem0.ai/faqs): Frequently asked questions about Mem0's capabilities and implementation details - [Changelog](https://docs.mem0.ai/changelog): Detailed product updates and version history for tracking new features and improvements - [Contributing Guide](https://docs.mem0.ai/contributing/development): Guidelines for contributing to Mem0's open-source development -- [OpenMemory](https://docs.mem0.ai/openmemory/overview): Open-source memory infrastructure for research and experimentation \ No newline at end of file +- [OpenMemory](https://docs.mem0.ai/openmemory/overview): Open-source memory infrastructure for research and experimentation