Search and folder contextualized content recommendations

Background

We've worked to develop deep learning models for providing content recommendations. These models use contextual information, such as the title, description, and metadata of a topic/folder content node and its ancestors, to provide content recommendations from our public catalog of channels. Eventually, the end goal is to use these capabilities for curriculum alignment by taking a curriculum skeleton (parsed from curriculum documents) and filling in the structure with content using this recommendation engine.

Story

As a user opted-in to new 'AI' Studio capabilities, who is interested in curating the most applicable resources from Studio's public catalog for my channel, I would like the ability to obtain a list of recommendations for a channel folder I'm editing. I would like the ability to then import selected resources from those recommendations which I find applicable to my channel and its folder.

Requirements

All UI features should be controlled by the 'Al' capabilities feature flag
Deep learning models should be hosted on HuggingFace
The backend should properly restrict outbound API calls to HuggingFace by validating the user has the feature flag enabled

Out of Scope

Building the feedback architecture to track implicit and explicit feedback on recommendations, except for integrating that architecture into search recommendations
```
### In-progress/Complete Tasks
```
[ ] https://github.com/learningequality/studio/issues/4280
[ ] https://github.com/learningequality/studio/issues/4275
[ ] https://github.com/learningequality/studio/issues/4276
[ ] https://github.com/learningequality/studio/issues/4296
[ ] https://github.com/learningequality/studio/issues/4302
[ ] https://github.com/learningequality/studio/issues/4284
[ ] https://github.com/learningequality/studio/issues/4285
[ ] https://github.com/learningequality/studio/issues/4294
[ ] https://github.com/learningequality/studio/issues/4295
[ ] https://github.com/learningequality/studio/issues/4392
[ ] https://github.com/learningequality/studio/issues/4399
[ ] https://github.com/learningequality/studio/issues/4341
[ ] https://github.com/learningequality/studio/issues/4290
[ ] https://github.com/learningequality/studio/issues/4450
[ ] https://github.com/learningequality/studio/issues/4447
[ ] https://github.com/learningequality/studio/issues/4448
[ ] https://github.com/learningequality/studio/issues/4455
[ ] https://github.com/learningequality/studio/issues/4565
[ ] https://github.com/learningequality/studio/issues/4566
[ ] https://github.com/learningequality/studio/issues/4567

### Feature Tasks
- [ ] Implement the feedback architecture
- [ ] Implement exportation of content metadata and text in a format that recommendations models can understand
- [ ] Setup the recommendations model infrastructure for production deploys
- [ ] Move matching algorithms to curriculum-automation repo
- [ ] Improve developer experience while setting up studio for curriculum alignment development

### To Spec / In Speccing

### Ready For Dev
- [ ] https://github.com/learningequality/studio/issues/4450
- [ ] https://github.com/learningequality/studio/issues/4438
- [ ] https://github.com/learningequality/studio/issues/4450

learningequality / studio