Create Vector Store

POST /v1/vector_stores

Python

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)

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);

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"]
  }'

{
  "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
}

Create a vector store.

Request Body

name · string

The name of the vector store.

file_ids · array

A list of File IDs that the vector store should use. Useful for tools like file_search that can access files.

description · string

A description for the vector store. Can be used to describe the vector store’s purpose.

expires_after · object

The expiration policy for a vector store.

Show properties

anchor · string · required

Anchor timestamp after which the expiration policy applies. Supported anchors: last_active_at.

days · integer · required

The number of days after the anchor time that the vector store will expire.

chunking_strategy · 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.

metadata · 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.

Response

Returns a VectorStore object.

id · string

The identifier, which can be referenced in API endpoints.

object · string

The object type, always vector_store.

name · string

The name of the vector store.

status · string

The status of the vector store. One of:

• expired
• in_progress
• completed

file_counts · object

Counts of files by status.

Show properties

in_progress · integer

The number of files that are currently being processed.

completed · integer

The number of files that have been successfully processed.

failed · integer

The number of files that have failed to process.

cancelled · integer

The number of files that were cancelled.

total · integer

The total number of files.

created_at · integer

The Unix timestamp (in seconds) for when the vector store was created.

usage_bytes · integer

The total number of bytes used by the files in the vector store.

Python

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)

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);

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"]
  }'

{
  "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
}