ikantkode/pdfLLM
pdfLLM is a completely open source, proof of concept RAG app.
Implements hybrid retrieval combining vector similarity search in Qdrant with entity-relationship indexing in Dgraph, processing documents into 500-token chunks and supporting 11+ file formats including OCR-capable image types. Built on PostgreSQL for session management and Celery for asynchronous multi-file processing, it enables category-based document organization with custom prompts and dual query modes (Master Chat across all documents or Category Chat for scoped retrieval).
187 stars. No commits in the last 6 months.
Stars
187
Forks
17
Language
Python
License
MIT
Category
Last pushed
Sep 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ikantkode/pdfLLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vndee/local-assistant-examples
Build your own ChatPDF and run it locally
datvodinh/rag-chatbot
Chat with multiple PDFs locally
shibing624/ChatPDF
RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF....
couchbase-examples/rag-demo
A RAG demo using LangChain that allows you to chat with your uploaded PDF documents
docqai/docq
Private ChatGPT/Perplexity. Securely unlocks knowledge from confidential business information.