Skip to main content
POST
/
vector_stores
/
{vector_store_id}
/
file_batches
Create a vector store file batch.
curl --request POST \
  --url https://api.openai.com/v1/vector_stores/{vector_store_id}/file_batches \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "file_ids": [
    "<string>"
  ],
  "chunking_strategy": {
    "type": "auto"
  },
  "attributes": {}
}'
{
  "id": "<string>",
  "object": "vector_store.files_batch",
  "created_at": 123,
  "vector_store_id": "<string>",
  "status": "in_progress",
  "file_counts": {
    "in_progress": 123,
    "completed": 123,
    "failed": 123,
    "cancelled": 123,
    "total": 123
  }
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

​
vector_store_id
string
required

The ID of the vector store for which to create a File Batch.

Example:

"vs_abc123"

Body

application/json
​
file_ids
string[]
required

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

Required array length: 1 - 500 elements
​
chunking_strategy
object

The chunking strategy used to chunk the file(s). If not set, will use the auto strategy. The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.

  • Auto Chunking Strategy
  • Static Chunking Strategy
​
attributes
object | null

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, booleans, or numbers.

Response

200 - application/json

OK

A batch of files attached to a vector store.

​
id
string
required

The identifier, which can be referenced in API endpoints.

​
object
enum<string>
required

The object type, which is always vector_store.file_batch.

Available options:
vector_store.files_batch
​
created_at
integer
required

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

​
vector_store_id
string
required

The ID of the vector store that the File is attached to.

​
status
enum<string>
required

The status of the vector store files batch, which can be either in_progress, completed, cancelled or failed.

Available options:
in_progress,
completed,
cancelled,
failed
​
file_counts
object
required