agentskillexchange Search large codebases and structured document trees without embeddings before building heavier retrieval stacks with TreeSearch
Index docs and source trees into structure-aware search so you can answer targeted questions quickly without a vector database or brittle grep sprawl.
Prerequisites
TreeSearch Python package or Rust CLI, local codebase or document corpus, and optional SQLite-backed index storage
Installation
Use the upstream install or setup path that matches your environment:
- pip install -U pytreesearch
- brew tap shibing624/tap
- brew install treesearch
- cargo install treesearch
Requirements and caveats from upstream:
- TreeSearch is a structure-aware document retrieval library. No vector embeddings. No chunk splitting. SQLite FTS5 keyword matching over document tree structures. Supports Markdown, plain text, code files (Python A...
Python Library
Basic usage or getting-started notes:
bash
Then use it in code:
from treesearch import TreeSearch
Extracted from upstream docs: https://raw.githubusercontent.com/shibing624/TreeSearch/HEAD/README.md