HaileyTQuach/docchat-docling
DocChat is an AI-powered Multi-Agent RAG system using Docling for structured document parsing and BM25 + vector search retrievers to retrieve fact-checked answers from PDFs, DOCX, and text files, preventing hallucinations. 🚀
Built on a multi-agent architecture where a Research Agent generates answers and a Verification Agent fact-checks them against source documents with automatic self-correction loops. Integrates Docling for PDF/DOCX parsing, LangChain with ChromaDB for hybrid BM25 + vector retrieval, and OpenAI LLMs, while a Gradio interface enables dynamic document selection when multiple files are uploaded.
No commits in the last 6 months.
Stars
40
Forks
30
Language
Python
License
—
Category
Last pushed
Oct 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/HaileyTQuach/docchat-docling"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tonykipkemboi/ollama_pdf_rag
A full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with...
IDinsight/ask-a-question
Trustworthy question-answering AI plugin for chatbots in the social sector with advanced content...
reasonmethis/docdocgo-core
Automate web research way beyond the first page of search results; curate knowledge bases to chat with.
pathway-labs/dropbox-ai-chat
AI-powered Dropbox search tool for private documents
rahmansahinler1/doclink
AI Document Assistant