Chat with one or more PDF files entirely on your computer using Ollama.
This project uses qwen3:8b for PDF question answering. It is a strong quality-and-speed choice for this computer's 16 GB of RAM and occupies about 5.2 GB when downloaded.
-
Install Ollama for Windows.
-
Open PowerShell and download the model:
ollama pull qwen3:8b
-
Install the Python dependencies:
python -m pip install -r requirements.txt
-
Run the app:
python -m streamlit run app.py
Ollama serves its local API at http://localhost:11434; it does not need an API key. Set OLLAMA_BASE_URL in .env only if your Ollama server uses a different address.