Create vector store file batch

POST/vector_stores/{vector_store_id}/file_batches

Create a vector store file batch.

Path ParametersExpand Collapse

vector_store_id: string

Body ParametersJSONExpand Collapse

attributes: optional map[string or number or boolean] or 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.

One of the following:

string

number

boolean

chunking_strategy: optional FileChunkingStrategyParam

The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

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.

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. If attributes or chunking_strategy are provided, they will be applied to all files in the batch. The maximum batch size is 2000 files. This endpoint is recommended for multi-file ingestion and helps reduce per-vector-store write request pressure. Mutually exclusive with files.

files: optional array of object { file_id, attributes, chunking_strategy }

A list of objects that each include a file_id plus optional attributes or chunking_strategy. Use this when you need to override metadata for specific files. The global attributes or chunking_strategy will be ignored and must be specified for each file. The maximum batch size is 2000 files. This endpoint is recommended for multi-file ingestion and helps reduce per-vector-store write request pressure. Mutually exclusive with file_ids.

file_id: string

A File ID that the vector store should use. Useful for tools like file_search that can access files. For multi-file ingestion, we recommend file_batches to minimize per-vector-store write requests.

attributes: optional map[string or number or boolean] or null

One of the following:

string

number

boolean

chunking_strategy: optional FileChunkingStrategyParam

The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

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.

ReturnsExpand Collapse

VectorStoreFileBatch object { id, created_at, file_counts, 3 more }

A batch of files attached to a vector store.

id: string

The identifier, which can be referenced in API endpoints.

created_at: number

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

formatunixtime

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

cancelled: number

The number of files that where cancelled.

completed: number

The number of files that have been 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.

object: "vector_store.files_batch"

The object type, which is always vector_store.file_batch.

status: "in_progress" or "completed" or "cancelled" or "failed"

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

One of the following:

"in_progress"

"completed"

"cancelled"

"failed"

vector_store_id: string

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