mburaksayici/smallevals

smallevals — CPU-fast, GPU-blazing fast offline retrieval evaluation for RAG systems with tiny QA models.

35
/ 100
Emerging

Supports vector database abstraction across 8+ backends (Chroma, Elasticsearch, Milvus, pgvector, Qdrant, Weaviate, FAISS, Pinecone), abstracting vector DB operations behind a unified interface. Generates synthetic evaluation datasets and retrieval metrics by prompting QAG-0.6B (a Qwen-based model) to create questions from document chunks, then measures if the vector DB retrieves those chunks in top-k results. Includes a Dash-based dashboard for visualizing retrieval scores and includes a CLI for batch synthetic QA generation from local documents.

Available on PyPI.

No License
Maintenance 6 / 25
Adoption 10 / 25
Maturity 10 / 25
Community 9 / 25

How are scores calculated?

Stars

18

Forks

2

Language

Python

License

Last pushed

Dec 04, 2025

Monthly downloads

41

Commits (30d)

0

Dependencies

28

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/mburaksayici/smallevals"

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