Spaces:
Sleeping
Sleeping
|
Download README.md from memoona-nz/AI_pdf_reader: direct link, hf CLI and curl.
- Browser
- Download file 1.72 kB
-
https://huggingface.co/spaces/memoona-nz/AI_pdf_reader/resolve/main/README.md
- Command line
-
hf download hf://spaces/memoona-nz/AI_pdf_reader/README.md
-
curl -L -o README.md https://huggingface.co/spaces/memoona-nz/AI_pdf_reader/resolve/main/README.md
1.72 kB
A newer version of the Gradio SDK is available: 6.32.0
metadata
title: AI PDF Q&A Chatbot
emoji: π
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.31.0
app_file: app.py
pinned: false
π AI PDF Q&A Chatbot (RAG System)
An AI-powered PDF Question Answering chatbot built using:
- LangChain
- FAISS
- Hugging Face Transformers
- FLAN-T5
- Gradio
Upload PDF documents and ask questions from them using Retrieval-Augmented Generation (RAG).
π Features
β
Extract and split document text
β
Semantic search using embeddings
β
Retrieval-Augmented Generation (RAG)
β
Detailed educational answers
β
Modern Gradio UI
π§ Model Used
Text Generation
- google/flan-t5-base
Embeddings
- sentence-transformers/all-MiniLM-L6-v2
π¦ Technologies
- Python
- Gradio
- LangChain
- FAISS
- Transformers
- PyTorch
βΆοΈ Run Locally
Install dependencies:
pip install -r requirements.txt
Run app:
python app.py
π Deploy on Hugging Face Spaces
- Create a new Space
- Select:
- SDK: Gradio
- Upload:
- app.py
- requirements.txt
- README.md
The app will build automatically.
β οΈ Important Notes
- First startup may take time because models download automatically.
- CPU Spaces are supported.
- No API key required.
- Recommended Space Hardware:
- CPU Basic or higher
π How It Works
- Upload PDFs
- Documents are split into chunks
- Embeddings are generated
- FAISS stores vectors
- Relevant chunks are retrieved
- FLAN-T5 generates detailed answers
π©βπ» Author
Built using Hugging Face + Gradio + LangChain.