fix: CodexLens model detection, hybrid search stability, and JSON logging

- Fix model installation detection using fastembed ONNX cache names
- Add embeddings_config table for model metadata tracking
- Fix hybrid search segfault by using single-threaded GPU mode
- Suppress INFO logs in JSON mode to prevent error display
- Add model dropdown filtering to show only installed models

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-12-22 21:49:10 +08:00
parent cf58dc0dd3
commit 8203d690cb
11 changed files with 302 additions and 57 deletions

View File

@@ -15,17 +15,17 @@ tiktoken>=0.5.0
[semantic]
numpy>=1.24
fastembed>=0.5
fastembed>=0.2
hnswlib>=0.8.0
[semantic-directml]
numpy>=1.24
fastembed>=0.5
fastembed>=0.2
hnswlib>=0.8.0
onnxruntime-directml>=1.18.0
onnxruntime-directml>=1.15.0
[semantic-gpu]
numpy>=1.24
fastembed>=0.5
fastembed>=0.2
hnswlib>=0.8.0
onnxruntime-gpu>=1.18.0
onnxruntime-gpu>=1.15.0