ChromaDB
ChromaDB (also known as Chroma or chroma-core) is an open-source vector database focused on LLM applications, emphasizing simplicity and in-memory HNSW-based dense vector search. It is suited for prototyping, metadata filtering, and offers a user-friendly interface for building and testing vector search applications, though it currently lacks hybrid and distributed features.
About this tool
ChromaDB
Website: https://www.trychroma.com/
Category: Vector Database Engines
Tags: open-source, in-memory, vector-search, llm
Description
ChromaDB (also known as Chroma or chroma-core) is an open-source vector database focused on large language model (LLM) applications. It emphasizes simplicity and offers in-memory HNSW-based dense vector search. ChromaDB is well-suited for rapid prototyping, metadata filtering, and provides a user-friendly interface for building and testing vector search applications. It currently does not support hybrid or distributed features.
Features
- Open-source under the Apache 2.0 License
- In-memory database for fast operations
- Dense vector search using HNSW (Hierarchical Navigable Small World) algorithm
- Embeddings support
- Full-text search capabilities
- Document storage
- Metadata filtering for advanced querying
- Multimodal retrieval (e.g., images)
- User-friendly interface for building and testing applications
- Python & JavaScript SDKs for quick start and integration
- Cloud deployment options (upcoming fully-managed cloud version)
- Integrations with other tools and platforms
Pricing
ChromaDB is free and open-source under the Apache 2.0 License.