/Multiple-Document-Chat

Multiple Document Chat with Langchain, OpenAI, HuggingFace using Streamlit interface

Primary LanguagePython

Multiple Document Chat with Langchain, OpenAI, and HuggingFace

In this project, we are going implement a multiple document question and answer We can import many PDFs and chat using OpenAI or HuggingFace API The frontend framework is Streamlit, a powerful tool to fast prototype and implement

In order to achieve a great result, we will use the best available technologies and methods through Deep Learning models

  • 📚 'Streamlit official site' - link
  • 📚 'Langchain official site' - link
  • 📚 'OpenAI official site' - link
  • 📚 'HuggingFace official site' - link

Step by Step

  1. Clone the repository to your local machine

  2. Create a python .venv environment and activate it

  3. Install the requirements -> pip install requirements.txt

  4. Generate your access tokens on OpenAI and HuggingFace account

  5. Create a file called ".env" and insert the bellow info:

    5.1 OPENAI_API_KEY='your_key'
    5.2 HUGGINGFACEHUB_API_TOKEN='your_key'

  6. Execute streamlit at terminal -> streamlit run app.py

  7. Just use it on browser

  8. Load the files on the sidebar

  9. Click on a 'process' button to process the documents

  10. Start chatting

Next Steps

  1. Test other APIs and Embeddings
  2. Deploy on AWS