mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-09 02:24:11 +08:00
71faaf43a8
删除 SPLADE 稀疏神经搜索后端和 hybrid_cascade 策略，
将搜索架构从 6 种后端简化为 4 种（FTS Exact/Fuzzy, Binary Vector, Dense Vector, LSP）。
主要变更：
- 删除 splade_encoder.py, splade_index.py, migration_009 等 4 个文件
- 移除 config.py 中 SPLADE 相关配置（enable_splade, splade_model 等）
- DEFAULT_WEIGHTS 改为 FTS 权重 {exact:0.25, fuzzy:0.1, vector:0.5, lsp:0.15}
- 删除 hybrid_cascade_search()，所有 cascade fallback 改为 self.search()
- API fusion_strategy='hybrid' 向后兼容映射到 binary_rerank
- 删除 CLI index_splade/splade_status 命令和 --method splade
- 更新测试、基准测试和文档
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