index_codebase
Create vector embeddings for semantic code search across 50+ programming languages. Use this initial indexing tool to prepare your codebase for AI-assisted analysis and cross-file relationship understanding.
Instructions
Index a codebase for semantic code search. USE THIS FIRST before search_code. Required once per project - creates vector embeddings for 50+ languages. After initial indexing, use update_index for incremental updates.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| directory | No | Path to the directory to index (defaults to current directory) | . |
| force | No | Force re-indexing even if index exists | |
| exclude | No | Additional glob patterns to exclude | |
| concurrency | No | Number of files to process in parallel (default: 4) |