intersystems-community/iris-vector-rag

Enterprise RAG pipelines with native IRIS vector search. 6 production implementations with RAGAS evaluation, LangChain, AWS/Azure configs. No external VectorDB required.

53
/ 100
Established

Implements six modular RAG architectures (basic, reranking, CRAG, GraphRAG, multi-query fusion, ColBERT) with unified LangChain/RAGAS-compatible APIs enabling single-line pipeline switching. Native IRIS vector search uses HNSW indexing with automatic schema management, connection pooling, and ACID transaction support, eliminating external vector database dependencies. Integrates with LangChain, RAGAS evaluation metrics, and cloud deployments (AWS/Azure) while supporting advanced retrieval strategies including cross-encoder reranking, knowledge graph fusion, and late-interaction embeddings.

Available on PyPI.

Maintenance 13 / 25
Adoption 9 / 25
Maturity 18 / 25
Community 13 / 25

How are scores calculated?

Stars

4

Forks

2

Language

Python

License

MIT

Last pushed

Mar 10, 2026

Monthly downloads

271

Commits (30d)

0

Dependencies

23

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/intersystems-community/iris-vector-rag"

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