> ## 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.

# Create Vector Store

Create a vector store.

## Request Body

<ParamField body="name" type="string">
  The name of the vector store.
</ParamField>

<ParamField body="file_ids" type="array">
  A list of [File](/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files.
</ParamField>

<ParamField body="description" type="string">
  A description for the vector store. Can be used to describe the vector store's purpose.
</ParamField>

<ParamField body="expires_after" type="object">
  The expiration policy for a vector store.

  <Expandable title="properties">
    <ParamField body="anchor" type="string" required>
      Anchor timestamp after which the expiration policy applies. Supported anchors: `last_active_at`.
    </ParamField>

    <ParamField body="days" type="integer" required>
      The number of days after the anchor time that the vector store will expire.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="chunking_strategy" type="object">
  The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty.
</ParamField>

<ParamField body="metadata" type="object">
  Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format.

  Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
</ParamField>

## Response

Returns a `VectorStore` object.

<ResponseField name="id" type="string">
  The identifier, which can be referenced in API endpoints.
</ResponseField>

<ResponseField name="object" type="string">
  The object type, always `vector_store`.
</ResponseField>

<ResponseField name="name" type="string">
  The name of the vector store.
</ResponseField>

<ResponseField name="status" type="string">
  The status of the vector store. One of:

  * `expired`
  * `in_progress`
  * `completed`
</ResponseField>

<ResponseField name="file_counts" type="object">
  Counts of files by status.

  <Expandable title="properties">
    <ResponseField name="in_progress" type="integer">
      The number of files that are currently being processed.
    </ResponseField>

    <ResponseField name="completed" type="integer">
      The number of files that have been successfully processed.
    </ResponseField>

    <ResponseField name="failed" type="integer">
      The number of files that have failed to process.
    </ResponseField>

    <ResponseField name="cancelled" type="integer">
      The number of files that were cancelled.
    </ResponseField>

    <ResponseField name="total" type="integer">
      The total number of files.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="created_at" type="integer">
  The Unix timestamp (in seconds) for when the vector store was created.
</ResponseField>

<ResponseField name="usage_bytes" type="integer">
  The total number of bytes used by the files in the vector store.
</ResponseField>

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

  vector_store = client.beta.vector_stores.create(
      name="Product Documentation",
      file_ids=["file-abc123", "file-abc456"],
      metadata={"project": "customer_support"}
  )

  print(vector_store.id)
  ```

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

  const vectorStore = await openai.beta.vectorStores.create({
    name: "Product Documentation",
    file_ids: ["file-abc123", "file-abc456"],
    metadata: { project: "customer_support" }
  });

  console.log(vectorStore.id);
  ```

  ```bash cURL theme={null}
  curl https://api.openai.com/v1/vector_stores \\
    -H "Authorization: Bearer $OPENAI_API_KEY" \\
    -H "Content-Type: application/json" \\
    -H "OpenAI-Beta: assistants=v2" \\
    -d '{
      "name": "Product Documentation",
      "file_ids": ["file-abc123", "file-abc456"]
    }'
  ```
</RequestExample>

<ResponseExample>
  ```json theme={null}
  {
    "id": "vs_abc123",
    "object": "vector_store",
    "name": "Product Documentation",
    "status": "in_progress",
    "usage_bytes": 0,
    "created_at": 1699061776,
    "file_counts": {
      "in_progress": 2,
      "completed": 0,
      "failed": 0,
      "cancelled": 0,
      "total": 2
    },
    "metadata": {
      "project": "customer_support"
    },
    "expires_after": null,
    "expires_at": null
  }
  ```
</ResponseExample>