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

6 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
1b4d24cada Prefer build-time version over runtime SOURCE_COMMIT (Coolify sets HEAD)
All checks were successful
Build and push container image / build-and-push (push) Successful in 4m50s
Details
2026-08-22 11:59:14 +02:00
Christoph Haas
434adf1f66 ffs 2026-08-22 10:33:53 +02:00
Christoph Haas
a046f3e0da add logging 2026-08-21 23:36:41 +02:00
Christoph Haas
cc8974d6b7 Add health check endpoint at /ok 
- Returns {"status": "ok"} as JSON
- No authentication required
- Useful for Kubernetes liveness/readiness probes

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
 2026-06-28 15:54:58 +02:00
Christoph Haas
21d467a284 Add Go implementation with ONNX Runtime 
- Use golang:1.23-bookworm as builder
- Use debian:bookworm-slim as runtime
- Use github.com/yalue/onnxruntime_go for ONNX inference
- Use github.com/sugarme/tokenizer for tokenization
- Download ONNX Runtime v1.27.0 shared library
- Download model.onnx and model.onnx_data from onnx-community
- Support API_SECRET environment variable for authentication
- Final image size: ~266 MB

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
 2026-06-28 12:35:31 +02:00