Spaces:
Sleeping
Sleeping
|
Download README.md from sunbal7/PDFQueryApplication: direct link, hf CLI and curl.
- Browser
- Download file 1.2 kB
-
https://huggingface.co/spaces/sunbal7/PDFQueryApplication/resolve/main/README.md
- Command line
-
hf download hf://spaces/sunbal7/PDFQueryApplication/README.md
-
curl -L -o README.md https://huggingface.co/spaces/sunbal7/PDFQueryApplication/resolve/main/README.md
1.2 kB
A newer version of the Streamlit SDK is available: 1.67.0
metadata
title: π RAG-based PDF Query Application
emoji: π
colorFrom: purple
colorTo: blue
sdk: streamlit
sdk_version: 1.42.0
app_file: app.py
pinned: false
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
π RAG-based PDF Query Application
This application leverages Retrieval-Augmented Generation (RAG) to enable users to ask questions about a PDF document. The PDF is processed and split into chunks, which are then indexed and used to find the most relevant information when the user submits a query.
Features
- Upload a PDF and ask questions based on its contents.
- PDF is processed using PyMuPDF and text is split into chunks.
- FAISS is used to create an index for quick retrieval of relevant text chunks.
- The application uses the Groq API for generating answers based on the retrieved context.
How it works
- Upload a PDF document.
- The application extracts text from the PDF and splits it into smaller chunks.
- A FAISS index is built using embeddings of these chunks.
- When you submit a query, the system retrieves the most relevant chunks and sends them to the Groq API to generate an answer.