API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Vector Stores

Create vector store

vector_stores.create(**kwargs) -> VectorStore { id, created_at, file_counts, 8 more }

POST/vector_stores

Delete vector store

vector_stores.delete(vector_store_id) -> VectorStoreDeleted { id, deleted, object }

DELETE/vector_stores/{vector_store_id}

List vector stores

vector_stores.list(**kwargs) -> CursorPage<VectorStore { id, created_at, file_counts, 8 more } >

GET/vector_stores

Retrieve vector store

vector_stores.retrieve(vector_store_id) -> VectorStore { id, created_at, file_counts, 8 more }

GET/vector_stores/{vector_store_id}

Search vector store

vector_stores.search(vector_store_id, **kwargs) -> Page<VectorStoreSearchResponse { attributes, content, file_id, 2 more } >

POST/vector_stores/{vector_store_id}/search

Modify vector store

vector_stores.update(vector_store_id, **kwargs) -> VectorStore { id, created_at, file_counts, 8 more }

POST/vector_stores/{vector_store_id}

ModelsExpand Collapse

class AutoFileChunkingStrategyParam { type }

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

FileChunkingStrategy = StaticFileChunkingStrategyObject { static, type } | OtherFileChunkingStrategyObject { type }

The strategy used to chunk the file.

FileChunkingStrategyParam = AutoFileChunkingStrategyParam { type } | 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.

class OtherFileChunkingStrategyObject { type }

This is returned when the chunking strategy is unknown. Typically, this is because the file was indexed before the chunking_strategy concept was introduced in the API.

class StaticFileChunkingStrategy { chunk_overlap_tokens, max_chunk_size_tokens }

class StaticFileChunkingStrategyObject { static, type }

class StaticFileChunkingStrategyObjectParam { static, type }

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

class VectorStore { id, created_at, file_counts, 8 more }

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

class VectorStoreDeleted { id, deleted, object }

class VectorStoreSearchResponse { attributes, content, file_id, 2 more }

Vector StoresFile Batches

Cancel vector store file batch

vector_stores.file_batches.cancel(batch_id, **kwargs) -> VectorStoreFileBatch { id, created_at, file_counts, 3 more }

POST/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel

Create vector store file batch

vector_stores.file_batches.create(vector_store_id, **kwargs) -> VectorStoreFileBatch { id, created_at, file_counts, 3 more }

POST/vector_stores/{vector_store_id}/file_batches

List vector store files in a batch

vector_stores.file_batches.list_files(batch_id, **kwargs) -> CursorPage<VectorStoreFile { id, created_at, last_error, 6 more } >

GET/vector_stores/{vector_store_id}/file_batches/{batch_id}/files

Retrieve vector store file batch

vector_stores.file_batches.retrieve(batch_id, **kwargs) -> VectorStoreFileBatch { id, created_at, file_counts, 3 more }

GET/vector_stores/{vector_store_id}/file_batches/{batch_id}

ModelsExpand Collapse

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

A batch of files attached to a vector store.

Vector StoresFiles

Retrieve vector store file content

vector_stores.files.content(file_id, **kwargs) -> Page<FileContentResponse { text, type } >

GET/vector_stores/{vector_store_id}/files/{file_id}/content

Create vector store file

vector_stores.files.create(vector_store_id, **kwargs) -> VectorStoreFile { id, created_at, last_error, 6 more }

POST/vector_stores/{vector_store_id}/files

Delete vector store file

vector_stores.files.delete(file_id, **kwargs) -> VectorStoreFileDeleted { id, deleted, object }

DELETE/vector_stores/{vector_store_id}/files/{file_id}

List vector store files

vector_stores.files.list(vector_store_id, **kwargs) -> CursorPage<VectorStoreFile { id, created_at, last_error, 6 more } >

GET/vector_stores/{vector_store_id}/files

Retrieve vector store file

vector_stores.files.retrieve(file_id, **kwargs) -> VectorStoreFile { id, created_at, last_error, 6 more }

GET/vector_stores/{vector_store_id}/files/{file_id}

Update vector store file attributes

vector_stores.files.update(file_id, **kwargs) -> VectorStoreFile { id, created_at, last_error, 6 more }

POST/vector_stores/{vector_store_id}/files/{file_id}

ModelsExpand Collapse

class FileContentResponse { text, type }

class VectorStoreFile { id, created_at, last_error, 6 more }

A list of files attached to a vector store.

class VectorStoreFileDeleted { id, deleted, object }