README.md

metadata

title: Pdf RAG Chatbot
emoji: 🏢
colorFrom: gray
colorTo: yellow
sdk: gradio
sdk_version: 6.2.0
app_file: app.py
pinned: false
short_description: 'Chat with your pdf '

📄 PDF RAG Chatbot

A Retrieval Augmented Generation (RAG) chatbot that allows you to upload PDF documents and have conversations based on their content using AI.

Tech Stack

• UI: Gradio
• LLM: Groq (Llama 3.3 70B)
• Framework: LangChain
• Embeddings: HuggingFace (all-MiniLM-L6-v2)
• Vector Store: FAISS
• PDF Processing: PyPDF

Installation

1. Clone the repository:

git clone <your-repo-url>
cd pdf-rag-chatbot

2. Install dependencies:

pip install -r requirements.txt

3. Set up your Groq API key:

export GROQ_API_KEY="your-api-key-here"

Get your free API key from Groq Console

Usage

1. Run the application:

python app.py

2. Open your browser to the displayed URL (usually http://localhost:7860)

3. Upload a PDF file

4. Wait for processing to complete

5. Start asking questions about the PDF content!

How It Works

1. PDF Processing: The uploaded PDF is split into smaller chunks
2. Embedding: Each chunk is converted into a vector embedding
3. Vector Storage: Embeddings are stored in FAISS for fast retrieval
4. Query: When you ask a question, the system finds the most relevant chunks
5. Response: The LLM generates an answer based on the retrieved context

Environment Variables

• GROQ_API_KEY: Your Groq API key (required)

Deployment

Hugging Face Spaces

1. Create a new Space on Hugging Face
2. Upload all files
3. Add GROQ_API_KEY to Space secrets
4. Your app will be live!

Local Development

python app.py

Example Questions

After uploading a PDF, you can ask questions like:

• "What is the main topic of this document?"
• "Summarize the key points"
• "What does the document say about [specific topic]?"
• "Can you explain [concept] from the document?"