Add graph expansion and cross-encoder reranking features

- Implemented GraphExpander to enhance search results with related symbols using precomputed neighbors.
- Added CrossEncoderReranker for second-stage search ranking, allowing for improved result scoring.
- Created migrations to establish necessary database tables for relationships and graph neighbors.
- Developed tests for graph expansion functionality, ensuring related results are populated correctly.
- Enhanced performance benchmarks for cross-encoder reranking latency and graph expansion overhead.
- Updated schema cleanup tests to reflect changes in versioning and deprecated fields.
- Added new test cases for Treesitter parser to validate relationship extraction with alias resolution.
This commit is contained in:
catlog22
2025-12-31 16:58:59 +08:00
parent 4bde13e83a
commit 31a45f1f30
27 changed files with 2566 additions and 97 deletions

View File

@@ -49,6 +49,12 @@ semantic-directml = [
"onnxruntime-directml>=1.15.0", # DirectML support
]
# Cross-encoder reranking (second-stage, optional)
# Install with: pip install codexlens[reranker]
reranker = [
"sentence-transformers>=2.2",
]
# Encoding detection for non-UTF8 files
encoding = [
"chardet>=5.0",