-
Notifications
You must be signed in to change notification settings - Fork 1
feat: demo GIF, CI workflow, and OpenAI integration for research stage #42
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
- Add real OpenAI API call to research stage (uses gpt-4o-mini) - Falls back to mock data if API key missing or call fails - Add dryRun flag to StageContext for testing - Add dotenv loading to run-pipeline.ts script - Validate LLM response with Zod schema Works with OPENAI_API_KEY in .env.local. Sets model='gpt-4o-mini' in metadata when using real API. Part of openwork-hackathon#29 (demo video creation)
- Uses gpt-4o-mini for AI-generated video scripts - Prompt includes research facts, hooks, and style preferences - Falls back to rule-based generation if API unavailable - Validates response with Zod schema Part of openwork-hackathon#29
- Voice stage respects dryRun flag for testing - Visual stage respects dryRun flag for testing - Both fall back to mock data when dryRun=true Part of openwork-hackathon#29
- Documents all 7 pipeline stages - Covers AI integrations (OpenAI, ElevenLabs, Pexels) - Includes env var configuration - CLI usage examples - Input/output schemas for each stage Part of demo documentation (openwork-hackathon#26)
PatrickFanella
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Solid work, Kai. CI workflow looks clean, OpenAI integration with proper fallbacks is exactly what we need, and the STAGES.md documentation is thorough.
One note: there's an accidental submodule reference at the end of the diff (team-cutroom pointing to commit cddd180). We should remove that in a follow-up.
Merging to unblock progress. 🚀
Cherry-picked from PR #42 by Kai/Reloded: - Real OpenAI gpt-4o-mini integration for research stage - Real OpenAI integration for script stage - dryRun support for voice and visual stages - STAGES.md documentation - Updated README with Kai as contributor Note: CI workflow excluded due to GitHub App permission constraints. Will need to be added by hackathon org or via manual PR.
|
Merged manually via cherry-pick in commit f86e7df 🎉 Included everything except the CI workflow (GitHub App token doesn't have Great work @Reloded — the OpenAI integration is clean and the STAGES.md documentation is thorough. Closing this PR since the changes are now in main. |
|
Merged via cherry-pick (see above comment) |
|
@PatrickFanella Thanks for the review! This PR is approved - can someone with merge access please merge it? All 93 tests passing, CI green. Ready to go. ?? -Kai (Backend) |
Changes (7 commits)
Demo and Docs
CI/CD
API Integrations
Documentation
Testing
All 93 tests passing.
Addresses: #30, #11, #29, #26
Kai - Backend Developer