Project Insight: Streamlit, Fastapi, HuggingFace and all the goodness

Project Insight

Project Code


Project Insight is designed to create NLP as a service with code base for both front end GUI ( streamlit ) and backend server ( FastApi ) the usage of transformers models on various downstream NLP task.

The downstream NLP tasks covered:

  • News Classification
  • Entity Recognition
  • Sentiment Analysis
  • Summarization
  • Information Extraction To Do

The user can select different models from the drop down to run the inference.

The users can also directly use the backend fastapi server to have a command line inference.

Features of the solution

  • Python Code Base : Built using Fastapi and Streamlit making the complete code base in Python.
  • Expandable : The backend is desinged in a way that it can be expanded with more Transformer based models and it will be available in the front end app automatically.

Hello @Abhishek_Mishra , welcome to the community !

This looks amazing :blush: Thanks a lot for sharing! I love the combination of Streamlit + FastAPI (I have internal projects on the Streamlit/FastAPI/Postgres stack xD) and I’ve always wanted to try Huggingface so I’ll definitely try this. And it looks very well documented :upside_down_face:

In the Readme of the project, can you add the command to run the docker container so anyone just has to copy/paste from it? You could also add a docker compose file at the root of the project so running it becomes a oneliner

Awesome work,

1 Like

Hi @andfanilo, thank you for the feedback and recommendations.
I will add the docker commands in the readme.

This is my first rodeo with Docker so i am not very well versed with the docker compose aspect. So it might take a while. :upside_down_face:

Any feedback around improvement and contributions are most welcomed! :slight_smile:

1 Like

Hi team,
I have update the project. The backend is now designed with Microservices architecture in mind. With every NLP service running its own server and tied together with nginx.

@andfanilo i have added instructions to run the application. With docker compose to spin up all the services.