FlagOpen/FlagEmbedding

Retrieval and Retrieval-augmented LLMs

79
/ 100
Verified

Provides dense, sparse, and multi-vector embedding models (including BGE-M3 supporting 100+ languages and 8K context) alongside rerankers and multimodal variants for comprehensive semantic search and RAG pipelines. Built on transformer architectures with support for in-context learning, token compression, and unified retrieval methods—integrates seamlessly with vector databases and LLM frameworks via HuggingFace.

11,395 stars. Used by 10 other packages. Actively maintained with 17 commits in the last 30 days. Available on PyPI.

Maintenance 20 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

11,395

Forks

842

Language

Python

License

MIT

Last pushed

Mar 10, 2026

Commits (30d)

17

Dependencies

9

Reverse dependents

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/FlagOpen/FlagEmbedding"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.