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

# Query Data

> Retrieve relevant document chunks based on a query.

### Body

<ParamField body="query" type="string" required>
  The question or text you want to find matches for in the vector store.
</ParamField>

<ParamField body="topK" type="number">
  The maximum number of chunks to return. Defaults to `5`.
</ParamField>

### Response

<ResponseField name="query" type="string">
  The original query.
</ResponseField>

<ResponseField name="hits" type="array">
  An array of retrieved chunk objects.

  <Expandable title="Hit Object">
    <ResponseField name="id" type="string">The vector ID.</ResponseField>
    <ResponseField name="score" type="number">Similarity score.</ResponseField>
    <ResponseField name="text" type="string">The chunk content.</ResponseField>
    <ResponseField name="title" type="string">The origin document title.</ResponseField>
  </Expandable>
</ResponseField>

```json Example Request theme={null}
{
  "query": "How do I configure the RAG server?",
  "topK": 3
}
```

```json Example Response theme={null}
{
  "query": "How do I configure the RAG server?",
  "hits": [
    {
      "id": "chunk-123",
      "score": 0.89,
      "text": "The RAG server is configured via the .ragtoolkit workspace...",
      "title": "Server Manual"
    }
  ]
}
```