Chat with PDF (or any other document)

This is still very much a work in progress, meaning it ain't production-ready (and to be fair to myself, it was a good excuse to try out ChatGPT 😃).

Usage

Make a copy of .env.dev file named .env, and make sure all the ENVIRONMENT_VARIABLES are set - of importance, the OPENAI_API_KEY must be present and set.

cp .env.dev .env  # make a copy of .env.dev called .env

Development (for now 😂)

Prerequisites:

• Python
• Pipenv
• Git
• Obtain an OpenAI API Key

With Docker:

Make sure you have both docker and docker-compose installed locally.

docker-compose -f .devops/docker-compose.yml up --build

Without Docker:

$ git clone https://github.com/clovisphere/chat-with-pdf.git  # clone the repo
$ cd chat-with-pdf  # cd into project root
$ pipenv install # install dependencies
$ pipenv shell  # activate virtualenv
$ python -m streamlit run app.py # or streamlit run app.py

If all went well, your app should be available on http://127.0.0.1:8501

Author

Clovis Mugaruka

• github.com/clovisphere
• twitter/clovisphere

License

Copyright ©️ 2023, Clovis Mugaruka.
Released under the MIT License.