Multi-Source Q&A Assistant

Project Overview

Multi-Source Question & Answer Assistant is an intelligent Streamlit application that allows users to upload and query multiple document sources using advanced AI-powered retrieval techniques.

---

Features

• Upload and process multiple document types:
  • PDF files
  • Text files
  • Web URLs
• Context-aware question answering
• Semantic search across uploaded documents
• Powered by Google's Gemini and Hugging Face embeddings

---

Prerequisites

• Python 3.8+
• Google API Key
• Hugging Face account (for embeddings)

---

Installation

1. Clone the repository:

git clone https://github.com/eslammohamedtolba/Multiple-Source-Question-Answer-Assistant.git
cd Multiple-Source-Question-Answer-Assistant

2. Create a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install dependencies:

pip install streamlit langchain-google-genai langchain-huggingface langchain-chroma python-dotenv pymupdf requests beautifulsoup4 sentence-transformers

4. Set up environment variables:

• Create a .env file in the project root
• Add your Google API key:

GOOGLE_API_KEY=your_google_api_key_here

---

Usage

Run the Streamlit application:

streamlit run app.py

---

How to Use

1. Upload your documents (PDFs, text files, or URLs)
2. Click "Process Sources"
3. Ask questions about your uploaded documents

---

Technologies Used

• Streamlit
• LangChain
• Google Gemini AI
• Hugging Face Embeddings
• Chroma Vector Store

---

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.