chroma

Open-source vector DB for storing embeddings and metadata. Supports semantic search, filtering, and RAG. Best for local, open-source projects.

• Embedding database for AI applications
• Stores embeddings and metadata with full-text and vector search
• Supports metadata filtering and semantic search
• Simple 4-function API for easy integration

• Store embeddings and metadata
• Perform vector and full-text search
• Filter by metadata with logical and comparison operators
• Simple 4-function API
• Scales from notebooks to production
• Open-source (Apache 2.0 license)
• Persistent storage to disk
• Supports custom and third-party embedding functions

1. 1.Install via pip or npm
2. 2.Create a collection with optional embedding function
3. 3.Add documents with metadata and IDs
4. 4.Query with text or metadata filters
5. 5.Update or delete documents by ID or filter
6. 6.Use persistent storage for data retention