atlas_search
Find relevant code snippets using hybrid search that combines vector similarity and keyword matching to locate specific implementations or concepts in indexed codebases.
Instructions
Perform a semantic hybrid search on the indexed source code.
This tool combines vector similarity (cosine) and full-text keyword search (BM25) to find the most relevant code snippets (chunks) based on the user's query intent. Use this tool when looking for specific implementations, where functions or features are defined, or to locate code matching a certain concept or task.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The natural language search term or description of the code to find. | |
| top_k | No | Maximum number of results to return (integer between 1 and 50). Defaults to 5. | |
| repo | No | Optional repository name to filter results. | |
| language | No | Optional programming language to filter results (e.g., 'python', 'javascript', 'go'). | |
| path_prefix | No | Optional file path prefix to restrict the search to a specific directory (e.g., 'src/controllers'). | |
| include_content | No | When false, omits the 'content' field from results to save tokens, returning only metadata and location (file_path, lines, symbol, type, language, score). Defaults to true. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |