diff --git a/docs/api-reference/introduction.mdx b/docs/api-reference/introduction.mdx index 8897c1d9..c471f638 100644 --- a/docs/api-reference/introduction.mdx +++ b/docs/api-reference/introduction.mdx @@ -172,7 +172,7 @@ X-RateLimit-Reset: 1627849200 ### Completed ✅ - Core mem0 integration -- Database connections (Neo4j, Qdrant) +- Database connections (Neo4j, Supabase) - LLM provider support (Ollama, OpenAI) - Configuration management diff --git a/docs/components/vectordbs/config.mdx b/docs/components/vectordbs/config.mdx index ac4272ca..ff8e823c 100644 --- a/docs/components/vectordbs/config.mdx +++ b/docs/components/vectordbs/config.mdx @@ -10,7 +10,7 @@ iconType: "solid" The `config` is defined as an object with two main keys: - `vector_store`: Specifies the vector database provider and its configuration - - `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus", "upstash_vector", "azure_ai_search", "vertex_ai_vector_search") + - `provider`: The name of the vector database (e.g., "chroma", "pgvector", "supabase", "milvus", "upstash_vector", "azure_ai_search", "vertex_ai_vector_search") - `config`: A nested dictionary containing provider-specific settings diff --git a/docs/components/vectordbs/overview.mdx b/docs/components/vectordbs/overview.mdx index 1c0ac10d..19bed622 100644 --- a/docs/components/vectordbs/overview.mdx +++ b/docs/components/vectordbs/overview.mdx @@ -13,7 +13,7 @@ Mem0 includes built-in support for various popular databases. Memory can utilize See the list of supported vector databases below. - The following vector databases are supported in the Python implementation. The TypeScript implementation currently only supports Qdrant, Redis,Vectorize and in-memory vector database. + The following vector databases are supported in the Python implementation. The TypeScript implementation currently only supports Qdrant, Redis, Vectorize and in-memory vector database. @@ -37,7 +37,7 @@ See the list of supported vector databases below. ## Usage -To utilize a vector database, you must provide a configuration to customize its usage. If no configuration is supplied, a default configuration will be applied, and `Qdrant` will be used as the vector database. +To utilize a vector database, you must provide a configuration to customize its usage. If no configuration is supplied, a default configuration will be applied, and `Supabase` (with pgvector) will be used as the vector database. For a comprehensive list of available parameters for vector database configuration, please refer to [Config](./config). diff --git a/docs/development.mdx b/docs/development.mdx index 2e7924ac..28beb92e 100644 --- a/docs/development.mdx +++ b/docs/development.mdx @@ -14,7 +14,7 @@ description: 'Complete development environment setup and workflow' ├── test_basic.py # Basic functionality tests ├── test_openai.py # OpenAI integration test ├── test_all_connections.py # Comprehensive connection tests -├── docker-compose.yml # Neo4j & Qdrant containers +├── docker-compose.yml # Neo4j container (Supabase is external) ├── .env # Environment variables └── docs/ # Documentation (Mintlify) ``` @@ -24,7 +24,7 @@ description: 'Complete development environment setup and workflow' | Component | Status | Port | Description | |-----------|--------|------|-------------| | Neo4j | ✅ READY | 7474/7687 | Graph memory storage | -| Qdrant | ✅ READY | 6333/6334 | Vector memory storage | +| Supabase | ✅ READY | 8000/5435 | Vector & database storage (self-hosted) | | Ollama | ✅ READY | 11434 | Local LLM processing | | Mem0 Core | ✅ READY | - | Memory management system v0.1.115 | diff --git a/docs/essentials/architecture.mdx b/docs/essentials/architecture.mdx index c86f714e..a460e1bc 100644 --- a/docs/essentials/architecture.mdx +++ b/docs/essentials/architecture.mdx @@ -12,12 +12,12 @@ graph TB A[AI Applications] --> B[MCP Server - Port 8765] B --> C[Memory API - Port 8080] C --> D[Mem0 Core v0.1.115] - D --> E[Vector Store - Qdrant] + D --> E[Vector Store - Supabase] D --> F[Graph Store - Neo4j] D --> G[LLM Provider] G --> H[Ollama - Port 11434] G --> I[OpenAI/Remote APIs] - E --> J[Qdrant - Port 6333] + E --> J[Supabase - Port 8000/5435] F --> K[Neo4j - Port 7687] ``` @@ -28,10 +28,10 @@ graph TB - **Purpose**: Central memory management and coordination - **Features**: Memory operations, provider abstraction, configuration management -### Vector Storage (Qdrant) -- **Port**: 6333 (REST), 6334 (gRPC) -- **Purpose**: High-performance vector search and similarity matching -- **Features**: Collections management, semantic search, embeddings storage +### Vector Storage (Supabase) +- **Port**: 8000 (API), 5435 (PostgreSQL) +- **Purpose**: High-performance vector search with pgvector and database storage +- **Features**: PostgreSQL with pgvector, semantic search, embeddings storage, relational data ### Graph Storage (Neo4j) - **Port**: 7474 (HTTP), 7687 (Bolt) @@ -57,13 +57,13 @@ graph TB 1. **Input**: User messages or content 2. **Processing**: LLM extracts facts and relationships 3. **Storage**: - - Facts stored as vectors in Qdrant + - Facts stored as vectors in Supabase (pgvector) - Relationships stored as graph in Neo4j 4. **Indexing**: Content indexed for fast retrieval ### Memory Retrieval 1. **Query**: Semantic search query -2. **Vector Search**: Qdrant finds similar memories +2. **Vector Search**: Supabase finds similar memories using pgvector 3. **Graph Traversal**: Neo4j provides contextual relationships 4. **Ranking**: Combined scoring and relevance 5. **Response**: Structured memory results @@ -74,12 +74,12 @@ graph TB ```bash # Core Services NEO4J_URI=bolt://localhost:7687 -QDRANT_URL=http://localhost:6333 +SUPABASE_URL=http://localhost:8000 OLLAMA_BASE_URL=http://localhost:11434 # Provider Selection LLM_PROVIDER=ollama # or openai -VECTOR_STORE=qdrant +VECTOR_STORE=supabase GRAPH_STORE=neo4j ``` @@ -87,7 +87,7 @@ GRAPH_STORE=neo4j The system supports multiple providers through a unified interface: - **LLM Providers**: OpenAI, Ollama, Anthropic, etc. -- **Vector Stores**: Qdrant, Pinecone, Weaviate, etc. +- **Vector Stores**: Supabase (pgvector), Qdrant, Pinecone, Weaviate, etc. - **Graph Stores**: Neo4j, Amazon Neptune, etc. ## Security Architecture @@ -110,7 +110,7 @@ The system supports multiple providers through a unified interface: ## Scalability Considerations ### Horizontal Scaling -- Qdrant cluster support +- Supabase horizontal scaling support - Neo4j clustering capabilities - Load balancing for API layer diff --git a/docs/examples/mem0-with-ollama.mdx b/docs/examples/mem0-with-ollama.mdx index a4257ae2..001a21f1 100644 --- a/docs/examples/mem0-with-ollama.mdx +++ b/docs/examples/mem0-with-ollama.mdx @@ -26,11 +26,10 @@ from mem0 import Memory config = { "vector_store": { - "provider": "qdrant", + "provider": "supabase", "config": { - "collection_name": "test", - "host": "localhost", - "port": 6333, + "connection_string": "postgresql://supabase_admin:your_password@localhost:5435/postgres", + "collection_name": "memories", "embedding_model_dims": 768, # Change this according to your local model's dimensions }, }, @@ -66,7 +65,7 @@ memories = m.get_all(user_id="john") ### Key Points - **Configuration**: The setup involves configuring the vector store, language model, and embedding model to use local resources. -- **Vector Store**: Qdrant is used as the vector store, running on localhost. +- **Vector Store**: Supabase with pgvector is used as the vector store, running on localhost. - **Language Model**: Ollama is used as the LLM provider, with the "llama3.1:latest" model. - **Embedding Model**: Ollama is also used for embeddings, with the "nomic-embed-text:latest" model. diff --git a/docs/integrations/llama-index.mdx b/docs/integrations/llama-index.mdx index e3d37ccd..c797218e 100644 --- a/docs/integrations/llama-index.mdx +++ b/docs/integrations/llama-index.mdx @@ -69,11 +69,10 @@ Set your Mem0 OSS by providing configuration details: ```python config = { "vector_store": { - "provider": "qdrant", + "provider": "supabase", "config": { - "collection_name": "test_9", - "host": "localhost", - "port": 6333, + "connection_string": "postgresql://supabase_admin:your_password@localhost:5435/postgres", + "collection_name": "memories", "embedding_model_dims": 1536, # Change this according to your local model's dimensions }, }, diff --git a/docs/mint.json b/docs/mint.json index 6ace4fab..5b3df279 100644 --- a/docs/mint.json +++ b/docs/mint.json @@ -72,7 +72,6 @@ "group": "Database Integration", "pages": [ "database/neo4j", - "database/qdrant", "database/supabase" ] }, diff --git a/docs/open-source/python-quickstart.mdx b/docs/open-source/python-quickstart.mdx index 00f54703..edb8363a 100644 --- a/docs/open-source/python-quickstart.mdx +++ b/docs/open-source/python-quickstart.mdx @@ -45,17 +45,16 @@ m = AsyncMemory() If you want to run Mem0 in production, initialize using the following method: -Run Qdrant first: +Run Supabase first: ```bash -docker pull qdrant/qdrant +# Ensure you have Supabase running locally +# See https://supabase.com/docs/guides/self-hosting/docker for setup -docker run -p 6333:6333 -p 6334:6334 \ - -v $(pwd)/qdrant_storage:/qdrant/storage:z \ - qdrant/qdrant +docker compose up -d ``` -Then, instantiate memory with qdrant server: +Then, instantiate memory with Supabase server: ```python import os @@ -65,10 +64,10 @@ os.environ["OPENAI_API_KEY"] = "your-api-key" config = { "vector_store": { - "provider": "qdrant", + "provider": "supabase", "config": { - "host": "localhost", - "port": 6333, + "connection_string": "postgresql://supabase_admin:your_password@localhost:5435/postgres", + "collection_name": "memories", } }, } diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx index ff684740..5e0253aa 100644 --- a/docs/quickstart.mdx +++ b/docs/quickstart.mdx @@ -7,7 +7,7 @@ description: 'Get your Mem0 Memory System running in under 5 minutes' - Required for Neo4j and Qdrant containers + Required for Neo4j container (Supabase already running) For the mem0 core system and API @@ -19,9 +19,13 @@ description: 'Get your Mem0 Memory System running in under 5 minutes' ### Step 1: Start Database Services ```bash -docker compose up -d neo4j qdrant +docker compose up -d neo4j ``` + +Supabase is already running as part of your existing infrastructure on the localai network. + + ### Step 2: Test Your Installation ```bash