chaas/vector-service
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 1 Wiki Activity Actions
12 commits 1 branch 0 tags 63 KiB
Commit graph

2 commits

Author SHA1 Message Date
Christoph Haas
111af2d66e Switch to bge-small-en-v1.5 for asymmetric query/passage embeddings
All checks were successful
Build and push container image / build-and-push (push) Successful in 4m10s
Details 
Replace all-MiniLM-L6-v2 with bge-small-en-v1.5, which separates
short search queries from package descriptions via the retrieval
instruction. Requests now default to query mode and opt out with
type=passage for documents. Uses the export's pooled, L2-normalized
sentence_embedding output instead of manual mean pooling.
 2026-09-13 22:10:01 +02:00
Christoph Haas
6101df3bfe Initial Python implementation with ONNX Runtime 
- Multi-stage Docker build (simplified to single-stage with pre-converted ONNX)
- HTTP server with ONNX inference
- API secret authentication
- Uses pre-converted all-MiniLM-L6-v2 ONNX model from onnx-community
- Image size: ~373 MB

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
 2026-06-28 12:04:00 +02:00