alexander-zuev/kollektiv-rag

The open source chat powered by LLMs with RAG. Kollektiv makes it easy to sync your custom data sources and get accurate, contextual replies.

Archived
33
/ 100
Emerging

Combines FireCrawl web scraping with ChromaDB vector storage and multi-query expansion to build searchable knowledge bases from documentation sites. Uses OpenAI embeddings for semantic search, Cohere re-ranking to improve result relevancy, and Claude 3.5 Sonnet for response generation, all exposed through a FastAPI backend with Chainlit chat UI. Targets library and framework documentation with dynamic system prompts that auto-summarize embedded docs to reduce hallucinations.

No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

88

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Feb 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/alexander-zuev/kollektiv-rag"

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