A document analyzer backed by local Large Language Models (LLMs).

• Install the backend, Ollama. On Mac, it is recommended to use homebrew to install Ollama:

brew install ollama

• Make sure to start the Ollam server:

brew service start ollama

• Create a new virtual environment and install the required packages with environment.yml

• Install DocSage as a package:

pip install -e .

• Start the webapp with the following command:

streamlit run ollama_rag_streamlit.py

To learn more about the retrieval-augmented generation (RAG) model used here, please go through the notebooks in the notebooks directory.

See the LICENSE file for license rights and limitations (MIT).