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

# Search Vector Store

Search a vector store for relevant chunks based on a query and file attributes filter.

## Path Parameters

<ParamField path="vector_store_id" type="string" required>
  The ID of the vector store to search.
</ParamField>

## Request Body

<ParamField body="query" type="string" required>
  A query string for a search. Can also be an array of strings for multi-query search.
</ParamField>

<ParamField body="max_num_results" type="integer">
  The maximum number of results to return. This number should be between 1 and 50 inclusive.
</ParamField>

<ParamField body="filters" type="object">
  A filter to apply based on file attributes.

  Example:

  ```json theme={null}
  {
    "file_id": "file-abc123"
  }
  ```
</ParamField>

<ParamField body="ranking_options" type="object">
  Ranking options for search.

  <Expandable title="properties">
    <ParamField body="ranker" type="string">
      The ranking algorithm to use. Options include:

      * `default_2024_08_21`: Default ranking algorithm
    </ParamField>

    <ParamField body="score_threshold" type="number">
      Minimum score threshold for results.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="rewrite_query" type="boolean">
  Whether to rewrite the natural language query for vector search.
</ParamField>

## Response

Returns a list of search results with relevant chunks.

<ResponseField name="data" type="array">
  Array of search result objects.

  <Expandable title="Search result object">
    <ResponseField name="type" type="string">
      The type of the object, always `vector_store.search_result`.
    </ResponseField>

    <ResponseField name="score" type="number">
      The relevance score of the chunk.
    </ResponseField>

    <ResponseField name="content" type="string">
      The text content of the chunk.
    </ResponseField>

    <ResponseField name="file_id" type="string">
      The ID of the file this chunk came from.
    </ResponseField>

    <ResponseField name="metadata" type="object">
      Metadata about the chunk location within the file.
    </ResponseField>
  </Expandable>
</ResponseField>

<RequestExample>
  ```python Python theme={null}
  from openai import OpenAI
  client = OpenAI()

  results = client.beta.vector_stores.search(
      vector_store_id="vs_abc123",
      query="How do I reset my password?",
      max_num_results=5
  )

  for result in results.data:
      print(f"Score: {result.score}")
      print(f"Content: {result.content}")
      print(f"File: {result.file_id}")
      print("---")
  ```

  ```javascript Node.js theme={null}
  import OpenAI from "openai";
  const openai = new OpenAI();

  const results = await openai.beta.vectorStores.search(
    "vs_abc123",
    {
      query: "How do I reset my password?",
      max_num_results: 5
    }
  );

  for (const result of results.data) {
    console.log(`Score: ${result.score}`);
    console.log(`Content: ${result.content}`);
    console.log(`File: ${result.file_id}`);
    console.log("---");
  }
  ```

  ```bash cURL theme={null}
  curl https://api.openai.com/v1/vector_stores/vs_abc123/search \\
    -H "Authorization: Bearer $OPENAI_API_KEY" \\
    -H "Content-Type: application/json" \\
    -H "OpenAI-Beta: assistants=v2" \\
    -d '{
      "query": "How do I reset my password?",
      "max_num_results": 5
    }'
  ```
</RequestExample>

<ResponseExample>
  ```json theme={null}
  {
    "object": "list",
    "data": [
      {
        "type": "vector_store.search_result",
        "score": 0.95,
        "content": "To reset your password, click on the 'Forgot Password' link on the login page...",
        "file_id": "file-abc123",
        "metadata": {
          "page": 5,
          "chunk_id": "chunk_789"
        }
      },
      {
        "type": "vector_store.search_result",
        "score": 0.87,
        "content": "Password reset instructions: Navigate to Settings > Security > Reset Password...",
        "file_id": "file-abc456",
        "metadata": {
          "page": 12,
          "chunk_id": "chunk_456"
        }
      }
    ]
  }
  ```
</ResponseExample>