vexor 0.2.0

A vector-powered CLI for semantic search over filenames.

Vexor

---

Vexor is a vector-powered CLI that searches file names semantically. It uses Google GenAI's gemini-embedding-001 model to embed file names and queries, then ranks matches with cosine similarity.

Install

Download from releases without python, or with:

pip install vexor # or use pipx, uv

The CLI entry point is vexor.

Configure

Set the Gemini API key once and reuse it everywhere:

vexor config --set-api-key "YOUR_KEY"

Optional defaults:

vexor config --set-model gemini-embedding-001
vexor config --set-batch-size 0   # 0 = single request

Configuration is stored in ~/.vexor/config.json.

Workflow

1. Index the project root (includes every subdirectory):

   vexor index --path ~/projects/demo --include-hidden
   

2. Search from anywhere, pointing to the same path:

   vexor search "api client config" --path ~/projects/demo --top 5
   

   Output example:

   Vexor semantic file search results
   ──────────────────────────────────
   1   0.923   ./src/config_loader.py
   2   0.871   ./src/utils/config_parse.py
   3   0.809   ./tests/test_config_loader.py
   

Tips:

• Keep one index per project root; subdirectories need separate indexes only if you explicitly run vexor index on them.
• Hidden files are included only if both index and search use --include-hidden.

Commands

Command	Description
vexor index --path PATH [--include-hidden] [--clear]	Recursively scans PATH, embeds file names, and writes a cache under ~/.vexor.
vexor search QUERY --path PATH [--top K] [--include-hidden]	Loads the cached embeddings for PATH and ranks matches for QUERY.
vexor doctor	Checks whether the vexor command is available on the current PATH.
vexor update	Fetches the latest release version and shows links to update via GitHub or PyPI.
vexor config --set-api-key/--clear-api-key	Manage the stored Gemini API key.
vexor config --set-model/--set-batch-size/--show	Manage default model and batch size.