# Creating a Movie Recommender **URL:** \ **Category:** Show the Community!\ **Created:** [August 24, 2021, 2:47pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190 "2021-08-24T14:47:43Z")\ **Posts on this page:** 12\ **Page:** 3
**Author:** ![bhutanisanyam1](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/bhutanisanyam1/32/18_2.png) [@bhutanisanyam1](https://community.wandb.ai/u/bhutanisanyam1)\ **Post date:** [October 19, 2021, 3:14pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/42 "2021-10-19T15:14:27Z")
This isn’t spamming at all! Please feel free to chat here as much as you like 😃 We’re honored to be a part of your project! 🙏 ---
**Author:** ![bbischof-wandb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/bbischof-wandb/32/398_2.png) [@bbischof-wandb](https://community.wandb.ai/u/bbischof-wandb)\ **Post date:** [October 20, 2021, 9:21pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/43 "2021-10-20T21:21:47Z")
This sounds great; I recommend FastAPI and/or Streamlit for the super easiest way to spin up an app to serve recs ---
**Author:** ![jimmiemunyi](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/jimmiemunyi/32/190_2.png) [@jimmiemunyi](https://community.wandb.ai/u/jimmiemunyi)\ **Post date:** [October 28, 2021, 5:09am UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/44 "2021-10-28T05:09:05Z")
can you give an overview FastAPI and Strealmit together… ---
**Author:** ![bbischof-wandb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/bbischof-wandb/32/398_2.png) [@bbischof-wandb](https://community.wandb.ai/u/bbischof-wandb)\ **Post date:** [October 28, 2021, 5:26am UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/45 "2021-10-28T05:26:54Z")
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 ---
**Author:** ![ravimashru](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/ravimashru/32/116_2.png) [@ravimashru](https://community.wandb.ai/u/ravimashru)\ **Post date:** [October 28, 2021, 8:10pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/46 "2021-10-28T20:10:24Z")
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? ---
**Author:** ![bbischof-wandb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/bbischof-wandb/32/398_2.png) [@bbischof-wandb](https://community.wandb.ai/u/bbischof-wandb)\ **Post date:** [October 28, 2021, 8:11pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/47 "2021-10-28T20:11:46Z")
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). ---
**Author:** ![ravimashru](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/ravimashru/32/116_2.png) [@ravimashru](https://community.wandb.ai/u/ravimashru)\ **Post date:** [October 28, 2021, 8:15pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/48 "2021-10-28T20:15:37Z")
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 😃 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. 🤔 ---
**Author:** ![bhutanisanyam1](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/bhutanisanyam1/32/18_2.png) [@bhutanisanyam1](https://community.wandb.ai/u/bhutanisanyam1)\ **Post date:** [October 28, 2021, 8:16pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/49 "2021-10-28T20:16:20Z")
I think it might be possible to train a fastai model, save it and infer via barebones torch 🤔 ---
**Author:** ![ravimashru](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/ravimashru/32/116_2.png) [@ravimashru](https://community.wandb.ai/u/ravimashru)\ **Post date:** [October 28, 2021, 8:18pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/50 "2021-10-28T20:18:25Z")
Oh that makes sense. I just did a quick search and barebones torch is ~267MB without CUDA so that might work! ---
**Author:** ![ravimashru](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/ravimashru/32/116_2.png) [@ravimashru](https://community.wandb.ai/u/ravimashru)\ **Post date:** [February 16, 2022, 1:47pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/51 "2022-02-16T13:47:44Z")
Hello everyone 👋 Sorry, this project was on hold for quite some time because life happened. 😅 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](https://calendar.google.com/event?action=TEMPLATE&tmeid=N3M3cmp2aDcwOGZydGRjc29nZWg0MXQwZG8gYXY0NWhqbTBxcWNsbHQ5am4xNmFmbDRmamdAZw&tmsrc=av45hjm0qqcllt9jn16afl4fjg%40group.calendar.google.com)) to talk about where we are and what we do next. Please feel free to join if you’re interested as well. 🙂 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) ---
**Author:** ![hello34](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/hello34/32/289_2.png) [@hello34](https://community.wandb.ai/u/hello34)\ **Post date:** [February 28, 2022, 7:15am UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/52 "2022-02-28T07:15:44Z")
We met again yesterday to discuss on implementation of Recommendations API endpoints around 7PM IST. We have completed on [Recommendations API implementation](https://github.com/fast-recsys/movie-recommender-backend/pull/4). 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 ---
**Author:** ![\_scott](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/_scott/32/95_2.png) [@\_scott](https://community.wandb.ai/u/_scott)\ **Post date:** [April 20, 2022, 3:49pm UTC](https://community.wandb.ai/t/creating-a-movie-recommender/190/53 "2022-04-20T15:49:30Z")
Nice work getting this project back on track! [Previous page](https://community.wandb.ai/t/creating-a-movie-recommender/190.md?page=2)