feat: use tutor configs to select model, key and options in litellm

[Henrrypg]

This pull request introduces several important updates to both the backend and frontend of the openedx_ai_extensions project, focusing on improved configuration management, plugin integration with Tutor, and enhancements to build and packaging processes. The most significant changes include the migration to a centralized configuration object for AI model settings, the addition of Tutor plugin hooks and patch management, and updates to frontend package naming and build scripts.

Configuration and Backend Updates:

• Migrated AI model and API key settings to a centralized OPENEDX_AI_EXTENSIONS configuration object, which is now read from environment variables and used throughout the backend, replacing individual settings like AI_MODEL and OPENAI_API_KEY. [1] [2] [3]
• Updated backend setup to use pathlib.Path for more robust file handling when reading README.md and CHANGELOG.rst files. [1] [2]

Tutor Plugin Integration:

• Added a new Tutor plugin definition in plugin.py, including default configuration values, build context management, patch file integration, and UI slot configuration for the learning experience. [1] [2]
• Introduced multiple patch files to automate backend and frontend installation within Tutor Docker images, ensuring the plugin is correctly integrated into Open edX environments. [1] [2] [3] [4] [5]

Frontend and Build Process Improvements:

• Renamed the frontend package to @openedx/openedx-ai-extensions-ui for consistency with backend naming conventions.
• Improved the frontend Makefile to handle the absence of the LICENSE file gracefully during the build process.

Versioning:

• Set the backend package version to 20.0.0 in __about__.py.

These changes collectively improve the maintainability, deployment, and extensibility of the openedx_ai_extensions plugin within the Open edX ecosystem.

[openedx-webhooks]

Thanks for the pull request, @Henrrypg!

This repository is currently maintained by @felipemontoya.

Once you've gone through the following steps feel free to tag them in a comment and let them know that your changes are ready for engineering review.

🔘 Get product approval

If you haven't already, check this list to see if your contribution needs to go through the product review process.

• If it does, you'll need to submit a product proposal for your contribution, and have it reviewed by the Product Working Group.
  • This process (including the steps you'll need to take) is documented here.
• If it doesn't, simply proceed with the next step.

🔘 Provide context

To help your reviewers and other members of the community understand the purpose and larger context of your changes, feel free to add as much of the following information to the PR description as you can:

• Dependencies

  This PR must be merged before / after / at the same time as ...

• Blockers

  This PR is waiting for OEP-1234 to be accepted.

• Timeline information

  This PR must be merged by XX date because ...

• Partner information

  This is for a course on edx.org.

• Supporting documentation
• Relevant Open edX discussion forum threads

🔘 Get a green build

If one or more checks are failing, continue working on your changes until this is no longer the case and your build turns green.

---

Where can I find more information?

If you'd like to get more details on all aspects of the review process for open source pull requests (OSPRs), check out the following resources:

• Overview of Review Process for Community Contributions
• Pull Request Status Guide
• Making changes to your pull request

When can I expect my changes to be merged?

Our goal is to get community contributions seen and reviewed as efficiently as possible.

However, the amount of time that it takes to review and merge a PR can vary significantly based on factors such as:

• The size and impact of the changes that it introduces
• The need for product review
• Maintenance status of the parent repository

💡 As a result it may take up to several weeks or months to complete a review and merge your PR.

[felipemontoya]

I changed the base so that this PR only reflects the changes meant to use tutor configs as a way of passing the secret key for openai or other llm providers

[felipemontoya]

we can write the default as put_your_api_key_here

[felipemontoya]

you can use a deep update of dict here so that incomplete dicts update the default

[felipemontoya]

By deleting the branch that was target here I inadvertedly deleted the PR. I'm opening again and moving to track main since the tutor PR was merged

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 67.90%. Comparing base (363eff3) to head (d82be77).
⚠️ Report is 6 commits behind head on main.

Additional details and impacted files

@@             Coverage Diff             @@
##             main      #19       +/-   ##
===========================================
+ Coverage   46.62%   67.90%   +21.28%     
===========================================
  Files          17       16        -1     
  Lines         311      349       +38     
  Branches       20       23        +3     
===========================================
+ Hits          145      237       +92     
+ Misses        166      108       -58     
- Partials        0        4        +4     

Flag	Coverage Δ
unittests	67.90% <ø> (+21.28%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[felipemontoya]

@Henrrypg I rebased and updated this PR according to our call.

Now the tutor config accepts either one variable with the key or the complete dict for AI_EXTENSIONS.

you can use any of this examples. If you use them all at once, AI_EXTENSIONS will override AI_EXTENSIONS_OPENAI_API_KEY or anthropic.

# simple version
AI_EXTENSIONS_OPENAI_API_KEY: sk-...
AI_EXTENSIONS_ANTHROPIC_API_KEY: sk-...

# advanced
AI_EXTENSIONS:
  anthropic:
    API_KEY: sk-....
    LITELLM_MODEL: claude-3-haiku-20240307
    MAX_TOKENS: 8400
    TEMPERATURE: 1
    TIMEOUT: 600

[Henrrypg]

@felipemontoya It's working fine for me, i just add some tests to pass checks

[felipemontoya]

This has been tested by me and Henrry and we also used this code to deploy to the sandbox at:

https://takoradi.edunext.cloud/