feat: Implement CodexLens multi-provider embedding rotation management

- Added functions to get and update CodexLens embedding rotation configuration.
- Introduced functionality to retrieve enabled embedding providers for rotation.
- Created endpoints for managing rotation configuration via API.
- Enhanced dashboard UI to support multi-provider rotation configuration.
- Updated internationalization strings for new rotation features.
- Adjusted CLI commands and embedding manager to support increased concurrency limits.
- Modified hybrid search weights for improved ranking behavior.
This commit is contained in:
catlog22
2025-12-25 14:13:27 +08:00
parent dfa8b541b4
commit 8e744597d1
12 changed files with 713 additions and 20 deletions

View File

@@ -27,11 +27,11 @@ class HybridSearchEngine:
default_weights: Default RRF weights for each source
"""
# Default RRF weights (exact: 40%, fuzzy: 30%, vector: 30%)
# Default RRF weights (vector: 60%, exact: 30%, fuzzy: 10%)
DEFAULT_WEIGHTS = {
"exact": 0.4,
"fuzzy": 0.3,
"vector": 0.3,
"exact": 0.3,
"fuzzy": 0.1,
"vector": 0.6,
}
def __init__(self, weights: Optional[Dict[str, float]] = None):