Chat with your PDF documents using AI — upload one or multiple files and ask questions in plain English.
Upload one or more PDF files and ask questions about their content. The app extracts text from the PDFs, sends it to a Groq-hosted LLaMA model as context, and answers strictly from the document — no hallucinations from outside knowledge.
- Multi-PDF support — upload multiple files at once, all merged into one context
- Chat history — model remembers last 10 messages in the conversation
- Fast inference — Groq LLaMA 3.1 8B responds in under 2 seconds
- Strict grounding — answers only from the document, not from training data
git clone https://github.com/YOUR_USERNAME/pdf-chatbot.git
cd pdf-chatbot
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txtcp .env.example .env.env:
GROQ_API_KEY=your_groq_key_here
Get a free key at console.groq.com.
streamlit run app.pyOpens at http://localhost:8501.
- Push to GitHub
- Go to share.streamlit.io
- Connect your repo, add
GROQ_API_KEYin Secrets - Deploy
| Layer | Technology |
|---|---|
| UI | Streamlit |
| PDF parsing | pypdf |
| LLM | Groq API — LLaMA 3.1 8B Instant |
| Config | python-dotenv |
MIT