README.md

metadata

title: Document Assistant
emoji: 📄
colorFrom: blue
colorTo: yellow
sdk: gradio
sdk_version: 5.4.0
python_version: '3.11'
app_file: app.py
pinned: false

Document Assistant (SPJIMR Branded)

A simple, document-aware chatbot built with Gradio, FAISS, and Hugging Face Inference API.

Features

• File Support: PDF, DOCX, TXT.
• RAG Engine: Uses Sentence-Transformers for embeddings and FAISS for fast retrieval.
• UI: Customized Gradio Blocks with SPJIMR branding (Deep Blue & Gold).
• LLM: Powered by Mistral-7B via Hugging Face Inference API.

Local Setup

1. Clone this repository.
2. Install dependencies:

   pip install -r requirements.txt
   

3. Set your Hugging Face Token (required for LLM access):
   • Windows (PowerShell): $env:HF_TOKEN="your_token_here"
   • Linux/Mac: export HF_TOKEN="your_token_here"
4. Run the app:

   python app.py
   

Deployment to Hugging Face Spaces

1. Create a new Space on Hugging Face.
2. Select Gradio as the SDK.
3. Upload app.py and requirements.txt.
4. Go to Settings > Variables and Secrets.
5. Add a new Secret:
   • Key: HF_TOKEN
   • Value: Your Hugging Face User Access Token (from hf.co/settings/tokens).
6. The Space will build and deploy automatically!

Built with

• Gradio
• FAISS
• Sentence-Transformers
• Hugging Face Inference API