> ## Documentation Index
> Fetch the complete documentation index at: https://vecgrep.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# search_code

> Semantically search an indexed codebase

## Overview

Embeds the query and performs cosine similarity search against indexed code chunks, returning the most semantically relevant snippets with file paths and line numbers.

If the codebase is not yet indexed, it will be indexed automatically first.

## Parameters

| Parameter   | Type      | Default  | Description                                                                                        |
| ----------- | --------- | -------- | -------------------------------------------------------------------------------------------------- |
| `query`     | `string`  | required | Natural language description of what you're looking for                                            |
| `path`      | `string`  | required | Absolute path to the codebase root directory                                                       |
| `top_k`     | `integer` | `8`      | Number of results to return (1–20)                                                                 |
| `min_score` | `float`   | `0.35`   | Minimum cosine similarity threshold. Results below this are filtered out. Set to `0.0` to disable. |

## Example

```
search_code("how does user authentication work", "/path/to/myproject")
```

**Returns:**

```
[1] src/auth.py:45-72 (score: 0.87)
def authenticate_user(token: str) -> User:
    ...

[2] src/middleware.py:12-28 (score: 0.81)
...
```

## Notes

* Queries are limited to 500 characters
* Results include file path, line range, similarity score, and the code snippet
* Auto-indexes on first call if no index exists for the given path
* `min_score` is clamped to `[0.0, 1.0]`. The default of `0.35` removes noisy low-confidence matches without affecting relevant results
* Use `hybrid_search` when you also want graph-structural context in the results