Skip to main content
Glama

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 repository

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repo_pathYes
exclude_dirsNo
output_formatNotext

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Elmoaid/TempoGraph'

If you have feedback or need assistance with the MCP directory API, please join our Discord server