Skip to content

Conversation

@sttruji
Copy link
Contributor

@sttruji sttruji commented Dec 17, 2025

No description provided.

Jay Chao and others added 6 commits November 9, 2025 01:37
- Added vector_search_service.py with Qdrant integration
  * store_canvas_embedding() for storing 512-dim CLIP embeddings
  * search_by_embedding() for similarity search
  * batch operations and collection management
- Updated search_algorithms.py to use real embeddings
  * Replaced random score stubs with CLIP-based semantic search
  * text_search() now uses embed_text() + vector similarity
  * image_search() now uses embed_image() + vector similarity
  * Graceful fallback to random if AI services unavailable
- Added Qdrant configuration to config.py
- Added dependencies: qdrant-client, torch, open_clip_torch, pillow
- Added Qdrant service to docker-compose.yml
- Created setup guides for local development

Ready for testing - NOT pushed to remote yet
Outlines how to get the embedding worker up / qdrant db for working ai search example
Removed detailed next steps for AI search implementation, including completed tasks, missing features, and implementation order.
@vercel
Copy link

vercel bot commented Dec 17, 2025

@sttruji is attempting to deploy a commit to the ResilientDB's projects Team on Vercel.

A member of the Team first needs to authorize it.

@bchou9 bchou9 merged commit ff57af5 into ResilientApp:main Dec 21, 2025
1 check failed
bchou9 added a commit that referenced this pull request Dec 21, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants