gustavz/DataChad

Ask questions about any data source by leveraging langchains

49
/ 100
Emerging

Embeds documents into vector stores (ActiveLoop Hub or local alternatives) and chains them with LLMs via LangChain for retrieval-augmented generation, supporting multiple file formats, custom model/embedding selection, and local-only deployment. Creates curated "Smart FAQ" vector stores alongside knowledge bases to improve response relevance. Includes chat history caching and streaming responses via a Streamlit interface, with modular backend decoupled from the frontend for flexibility.

324 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

324

Forks

75

Language

Python

License

Apache-2.0

Last pushed

Feb 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/gustavz/DataChad"

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