wafflecomposite/langchain-ask-pdf-local
An AI-app that allows you to upload a PDF and ask questions about it. It uses StableVicuna 13B and runs locally.
Implements a full RAG (retrieval-augmented generation) pipeline using LangChain, substituting OpenAI's proprietary embeddings and LLM with open-source alternatives: all-MiniLM-L6-v2 for semantic search and StableVicuna-13B quantized to GGML format for inference. The system runs entirely on CPU without GPU acceleration, packaged as a Streamlit web interface for PDF ingestion and question-answering workflows.
No commits in the last 6 months.
Stars
93
Forks
9
Language
Python
License
—
Category
Last pushed
May 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/wafflecomposite/langchain-ask-pdf-local"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yesbhautik/Talk-with-PDF
An interactive AI chatbot for querying and discussing the contents of PDF documents using...
amithkoujalgi/ollama-pdf-bot
A bot that accepts PDF docs and lets you ask questions on it.
alphasecio/groq
A Streamlit chatbot with memory for running open-source text models on Groq.
nehalvaghasiya/interview-bot
AI-powered virtual interview bot to simulate real interview practice.
IonMich/batch-doc-vqa
Ask a question about a document collection and extract structured responses