chroma and chromadb-tutorial
Chroma is the core database system while the tutorial repository is educational documentation that teaches users how to use that same database system, making them complements in a learning progression rather than competitors or siblings.
About chroma
chroma-core/chroma
Open-source search and retrieval database for AI applications.
Supports hybrid search combining vector similarity with full-text matching, automatic embedding generation, and metadata filtering via a minimal 4-function API. Built with in-memory and persistent storage modes, plus client-server architecture for production deployments. Provides native Python and JavaScript clients with optional cloud hosting, integrating seamlessly into LLM frameworks and RAG pipelines.
About chromadb-tutorial
neo-con/chromadb-tutorial
This repo is a beginner's guide to using Chroma. It covers all the major features including adding data, querying collections, updating and deleting data, and using different embedding functions. Each topic has its own dedicated folder with a detailed README and corresponding Python scripts for a practical understanding.
Demonstrates metadata-driven filtering through `where` clause syntax for refined collection queries beyond similarity search. Covers multiple embedding function integrations including OpenAI APIs and custom embedding implementations, enabling flexible semantic search workflows. The modular structure isolates upsert semantics and vector retrieval patterns, making it accessible for building RAG and semantic search applications.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work