Creating a Movie Recommender

Show the Community!
42

This isn’t spamming at all!

Please feel free to chat here as much as you like :smiley: We’re honored to be a part of your project! :pray:

1 Like
43

This sounds great; I recommend FastAPI and/or Streamlit for the super easiest way to spin up an app to serve recs

2 Likes
44

can you give an overview FastAPI and Strealmit together…

45

Yea sure;

I used fastApi to wrap the model and handle db access. I then call to the api with stream lit to handle all the ui interaction. I think these days I might try gradio though. The more I look at it the more I like it

2 Likes
46

This is cool. I assume anything that allows a Python runtime would do for hosting the model + FastAPI wrapper. Do you have any “favorite” services (e.g. Heroku) for this?

1 Like
47

Totally reasonable; I’ve used docker containers on AWS personally, but I see little danger in trying Heroku (from my relatively basic experience with it).

1 Like
48

I think I tried deploying a fastai model wrapped with FastAPI on Heroku once but fastai and its dependencies are so HUGE that they exceeded the space allowed on the free tier :smiley:

It would be nice to have an “inference” version of fastai - something lightweight with minimal dependencies to use in web apps. Maybe something like this exists and I just don’t know about it. :thinking:

1 Like
49

I think it might be possible to train a fastai model, save it and infer via barebones torch :thinking:

2 Likes
50

Oh that makes sense. I just did a quick search and barebones torch is ~267MB without CUDA so that might work!

3 Likes
51

Hello everyone :wave:

Sorry, this project was on hold for quite some time because life happened. :sweat_smile: I’d love to get back on this project and see it to completion.

@hello34, @pooja_srivastava and I will be having a call at 7 pm IST tomorrow (calendar invite) to talk about where we are and what we do next. Please feel free to join if you’re interested as well. :slight_smile:

EDIT (meeting notes):

  • All endpoints implemented, the inference endpoint for getting recommendations remains
  • Documentation and tests need to be added
  • Stretch goal: add CI using GitHub Actions (after the tests have been added)
1 Like
52

We met again yesterday to discuss on implementation of Recommendations API endpoints around 7PM IST.

We have completed on Recommendations API implementation. Now the things to do in future meetings are:

  • Frontend implementation (two pages)
  • CI using Github Action
  • Documentation and tests to modified
  • Any code refactoring for backend-api
1 Like
53

Nice work getting this project back on track!

1 Like