gustavz/DataChad
Ask questions about any data source by leveraging langchains
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.
Stars
324
Forks
75
Language
Python
License
Apache-2.0
Category
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.
Related tools
leanderme/sytora
A sophisticated smart symptom search engine
e-m3din4/booby-trap-pdf
Embed malware, apks, executables or any other binary file into a PDF, or generate a PDF with...
knowledge-ukraine/medlocalgpt
⚕️ Applying LLM-powered AI Agents to Support for Physical Rehabilitation & Telerehabilitation...
Dr-Hutchinson/nicolay
Nicolay is a digital history experiment that uses artificial intelligence to explore the...
Rakshath66/Chat-With-Your-PDF
Streamlit-based chatbot to interact with PDFs using Retrieval-Augmented Generation (RAG), FAISS,...