Logo
Deploy Now

Categories

AI Database Machine Learning Search Engine RAG Vector Database Embeddings

Stars

29,115

Forks

2,453

Watchers

135

Developer links

Last Updated: 08-21-2026 09:44 AM (UTC)

Chroma

With over 29,000 GitHub stars and deep integrations into LangChain, LlamaIndex, and CrewAI, Chroma has become the default vector database for developers building retrieval-augmented generation pipelines and AI agent memory systems. Its core API consists of just four functions — create, add, query, and delete — making it the fastest path from zero to semantic search, while the underlying Rust engine handles tokenization, embedding, HNSW indexing, and similarity scoring automatically. Chroma supports dense vector search via HNSW with configurable distance metrics including L2, cosine similarity, and inner product, sparse vector search using SPLADE, full-text BM25 keyword search, and regex matching, all combinable in hybrid queries through a single unified interface. Metadata filtering at query time uses MongoDB-style operators including $eq, $ne, $gt, $lt, $in, and logical combinators $and and $or, enabling precise result scoping without post-processing. The multimodal pipeline powered by OpenCLIP embeds text and images into a shared vector space, allowing cross-modal retrieval where text queries return relevant images and vice versa. Deployment options range from embedded mode via PersistentClient for notebooks and prototypes, to client-server mode with Docker for production, to Chroma Cloud for serverless scalability. Official Python and JavaScript SDKs provide identical APIs, and embedding function integrations support OpenAI, Cohere, Hugging Face, Google, Ollama, and custom models. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Chroma

Benefits

  • Simplest API for Vector Search
  • Four core functions — create, add, query, delete — with automatic tokenization, embedding generation, and HNSW indexing handle the entire pipeline from raw text to similarity results.
  • Hybrid Search in One Query
  • Combine dense vector search, sparse SPLADE vectors, BM25 full-text search, regex matching, and metadata filtering in a single unified query interface without external dependencies.
  • Multimodal Text and Image Search
  • OpenCLIP embedding functions map text and images into shared vector spaces, enabling cross-modal retrieval where text queries return relevant images and vice versa.
  • Any Embedding Model Supported
  • Built-in integrations with OpenAI, Cohere, Hugging Face Sentence Transformers, Google, Ollama, and custom embedding functions let you switch models without changing application code.

Features

  • HNSW Vector Index
  • Approximate nearest neighbor search with configurable distance metrics including L2, cosine similarity, and inner product, optimized for high-dimensional embedding spaces.
  • Metadata Filtering
  • MongoDB-style query operators including $eq, $ne, $gt, $lt, $in with $and and $or logical combinators enable precise result scoping at query time without post-processing.
  • Docker Server Mode
  • Production deployment via official Docker image exposes a REST API on port 8000, supporting persistent storage, authentication, and multi-client concurrent access.
  • LangChain Integration
  • Native vector store integration with LangChain, LlamaIndex, CrewAI, and other AI frameworks enables plug-and-play RAG pipeline construction with minimal configuration.
  • Python and JavaScript SDKs
  • Identical APIs in both Python and JavaScript with full type annotations, comprehensive test coverage, and async support for building AI applications in either ecosystem.