This is a simple fastapi app that provides a clean interface to enable a conversation with any pdf. You can enter a link to a pdf hosted online or upload your own pdf. The app will then extract the text from the pdf, create embeddings from the text and use them with the openai api to generate a response to a question you ask. It will also return a source for the part of the text it used to generate the response and the page number.
Try the demo at: https://www.dara.chat
Screen.Recording.2023-04-04.at.7.46.09.AM.mov
git clone https://github.com/mukulpatnaik/researchgpt.git
cd researchgpt
pip install -r requirements.txt
You also need redis for storing the embeddings locally on your machine. You can find installation instructions here: https://redis.io/docs/getting-started/installation/. To start the db, run the following command in your terminal.
On MacOS:
redis-server
On Windows:
sudo service redis-server start
You need to have an openai api key and set it as the environment variable 'OPENAI_API_KEY'.
uvicorn main:app --reload
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
If you would like to collaborate on this project, please reach out to me at [email protected] or find me on twitter