Hugging Face's logo

Spaces:
p3rc03
/
2B
Sleeping

App Files Community
2B / README.md
37-AN
Initial commit for Hugging Face Space deployment
4fe6054
preview code
|
raw
history blame
2.19 kB
metadata
title: Personal AI Assistant with RAG
emoji: 🤗
colorFrom: indigo
colorTo: purple
sdk: docker
app_port: 7860
pinned: true
license: mit

Personal AI Assistant with RAG

A powerful personal AI assistant that uses Retrieval-Augmented Generation (RAG) to provide responses based on your documents and notes.

Features

  • Uses free Hugging Face models for language processing and embeddings
  • Stores and retrieves information in a vector database
  • Upload PDF, TXT, and CSV files to expand the knowledge base
  • Add direct text input to your knowledge base
  • View sources for AI responses
  • Conversation history tracking

How to Use

  1. Upload Documents: Use the sidebar to upload files (PDF, TXT, CSV)
  2. Add Text: Enter text directly into the knowledge base
  3. Ask Questions: Chat with the assistant about your documents
  4. View Sources: See where information is coming from

Deployment

Local Deployment

To run the app locally:

  1. Clone this repository
  2. Install requirements: pip install -r requirements.txt
  3. Run the Streamlit UI: python run.py --ui
  4. Or run the API server: python run.py --api

Deploying to Hugging Face Spaces

This application can be easily deployed to Hugging Face Spaces for free hosting:

  1. Make sure you have a Hugging Face account
  2. Create a Hugging Face API token at https://huggingface.co/settings/tokens
  3. Run the deployment script: python deploy_to_hf.py
  4. Follow the prompts to enter your username, token, and space name
  5. Wait for the deployment to complete

If you encounter any issues during deployment, run python check_git_status.py to diagnose and fix common problems.

The deployment process:

  • Creates a Hugging Face Space using the Spaces SDK
  • Configures git for pushing to Hugging Face
  • Pushes your code to the Space
  • Builds and deploys the Docker container automatically

Built With

  • Hugging Face Models
    • LLM: google/flan-t5-large
    • Embeddings: sentence-transformers/all-MiniLM-L6-v2
  • LangChain for orchestration
  • Qdrant for vector storage
  • Streamlit for UI

Created by p3rc03

License

MIT License - See LICENSE file for details