embed_repo
Generate embeddings for semantic search across codebase symbols to enable hybrid search combining full-text and vector similarity.
Instructions
Generate embeddings for semantic search across all symbols in the codebase.
Run after index_repo to enable hybrid search (FTS5 + vector similarity).
Uses BAAI/bge-small-en-v1.5 (33MB, runs locally on CPU, no API keys).
Only embeds symbols without existing vectors — fast on subsequent runs.
Requires: pip install tempograph[semantic]
repo_path: absolute path to repositoryInput Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| repo_path | Yes | ||
| exclude_dirs | No | ||
| output_format | No | text |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |