Add AI assistant#54
Conversation
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
amrabed
force-pushed
the
feat/ai-assistant-14015290105785623889
branch
from
d2dc43a to
5abccf3
Compare
|
- Install Vercel AI SDK, Google Generative AI, Firebase Admin, and Upstash Redis. - Implement Firebase Admin singleton and vector search queries. - Create a seed script to process data files and populate Firestore vector store. - Implement a streaming API route with RAG and rate limiting. - Create a floating chat widget with Markdown support and auto-scroll. - Add GitHub Actions workflow for automated re-seeding. - Update environment variable documentation.
…xt injection and enable dynamic API routes
…ntation to src/components/chat/
amrabed
force-pushed
the
feat/ai-assistant-14015290105785623889
branch
from
964fb86 to
ee4af64
Compare
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
- Implement RAG-based AI assistant using Vercel AI SDK and Google Gemini. - Set up Firestore vector search with a robust data seeding script. - Create a floating chat widget with Markdown support and auto-scroll. - Update GitHub Actions workflows to use pnpm and pinned SHAs for security. - Fix CI failures related to package manager mismatch and TypeScript errors. - Add comprehensive implementation specs in .vibe/specs/add-ai-agent.
|
| run: mise run deploy | ||
| env: | ||
| FIREBASE_TOKEN: ${{ secrets.FIREBASE_TOKEN }} | ||
| run: pnpm run build && firebase deploy --only hosting --token "${{ secrets.FIREBASE_TOKEN }}" |
2 participants
I have implemented a complete RAG-based AI assistant for the portfolio.
Key features:
text-embedding-004to generate embeddings for project data andgemini-1.5-flashfor the chat response. Context is retrieved from a Firestore vector store..ts,.tsx, and.jsonfiles insrc/data/, converting complex objects to human-readable text before embedding.next/dynamicconstraints and missing environment variables during the build process to ensure a stable production deployment.PR created automatically by Jules for task 14015290105785623889 started by @amrabed