mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-09 02:24:11 +08:00
b9b2932f50
- Introduced a new JSON file for verbose output of the Codex Lens search results. - Added unit tests for binary search functionality in `test_stage1_binary_search_uses_chunk_lines.py`. - Implemented regression tests for staged cascade Stage 2 expansion depth in `test_staged_cascade_lsp_depth.py`. - Created unit tests for staged cascade Stage 2 realtime LSP graph expansion in `test_staged_cascade_realtime_lsp.py`. - Enhanced the ChainSearchEngine to respect configuration settings for staged LSP depth and improve search accuracy.
CodexLens
CodexLens is a multi-modal code analysis platform designed to provide comprehensive code understanding and analysis capabilities.
Features
- Multi-language Support: Analyze code in Python, JavaScript, TypeScript and more using Tree-sitter parsers
- Semantic Search: Find relevant code snippets using semantic understanding with fastembed and HNSWLIB
- Code Parsing: Advanced code structure parsing with tree-sitter
- Flexible Architecture: Modular design for easy extension and customization
Installation
Basic Installation
pip install codex-lens
With Semantic Search
pip install codex-lens[semantic]
With GPU Acceleration (NVIDIA CUDA)
pip install codex-lens[semantic-gpu]
With DirectML (Windows - NVIDIA/AMD/Intel)
pip install codex-lens[semantic-directml]
With All Optional Features
pip install codex-lens[full]
Requirements
- Python >= 3.10
- See
pyproject.tomlfor detailed dependency list
Development
This project uses setuptools for building and packaging.
License
MIT License
Authors
CodexLens Contributors