Skip to content
Primary navigation

Suggested
API Dashboard
API Reference
Vector Stores

Create vector store

POST/vector_stores

Create a vector store.

Body ParametersJSONExpand Collapse
chunking_strategy: optional AutoFileChunkingStrategyParam { type } or StaticFileChunkingStrategyObjectParam { static, type }

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.

One of the following:
AutoFileChunkingStrategyParam = object { type }

The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.

type: "auto"

Always auto.

StaticFileChunkingStrategyObjectParam = object { static, type }

Customize your own chunking strategy by setting chunk size and chunk overlap.

static: StaticFileChunkingStrategy { chunk_overlap_tokens, max_chunk_size_tokens }
chunk_overlap_tokens: number

The number of tokens that overlap between chunks. The default value is 400.

Note that the overlap must not exceed half of max_chunk_size_tokens.

max_chunk_size_tokens: number

The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.

minimum100
maximum4096
type: "static"

Always static.

description: optional string

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

expires_after: optional object { anchor, days }

The expiration policy for a vector store.

anchor: "last_active_at"

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

days: number

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

minimum1
maximum365
file_ids: optional array of string

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

metadata: optional Metadata

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, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

name: optional string

The name of the vector store.

ReturnsExpand Collapse
VectorStore = object { id, created_at, file_counts, 8 more }

A vector store is a collection of processed files can be used by the file_search tool.

id: string

The identifier, which can be referenced in API endpoints.

created_at: number

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

file_counts: object { cancelled, completed, failed, 2 more }
cancelled: number

The number of files that were cancelled.

completed: number

The number of files that have been successfully processed.

failed: number

The number of files that have failed to process.

in_progress: number

The number of files that are currently being processed.

total: number

The total number of files.

last_active_at: number

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

metadata: Metadata

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, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

name: string

The name of the vector store.

object: "vector_store"

The object type, which is always vector_store.

status: "expired" or "in_progress" or "completed"

The status of the vector store, which can be either expired, in_progress, or completed. A status of completed indicates that the vector store is ready for use.

One of the following:
"expired"
"in_progress"
"completed"
usage_bytes: number

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

expires_after: optional object { anchor, days }

The expiration policy for a vector store.

anchor: "last_active_at"

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

days: number

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

minimum1
maximum365
expires_at: optional number

The Unix timestamp (in seconds) for when the vector store will expire.

Create vector store

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": "Support FAQ"
  }'

{
  "id": "vs_abc123",
  "object": "vector_store",
  "created_at": 1699061776,
  "name": "Support FAQ",
  "description": "Contains commonly asked questions and answers, organized by topic.",
  "bytes": 139920,
  "file_counts": {
    "in_progress": 0,
    "completed": 3,
    "failed": 0,
    "cancelled": 0,
    "total": 3
  }
}
Returns Examples
{
  "id": "vs_abc123",
  "object": "vector_store",
  "created_at": 1699061776,
  "name": "Support FAQ",
  "description": "Contains commonly asked questions and answers, organized by topic.",
  "bytes": 139920,
  "file_counts": {
    "in_progress": 0,
    "completed": 3,
    "failed": 0,
    "cancelled": 0,
    "total": 3
  }
}