API Reference

Pipelines

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Documents

Create Batch Pipeline Documents

client.pipelines.documents.create(stringpipelineID, DocumentCreateParams { body } params, RequestOptionsoptions?): DocumentCreateResponse { id, metadata, text, 4 more }

POST/api/v1/pipelines/{pipeline_id}/documents

Paginated List Pipeline Documents

client.pipelines.documents.list(stringpipelineID, DocumentListParams { file_id, limit, only_api_data_source_documents, 3 more } query?, RequestOptionsoptions?): PaginatedCloudDocuments<CloudDocument { id, metadata, text, 4 more } >

GET/api/v1/pipelines/{pipeline_id}/documents/paginated

Get Pipeline Document

client.pipelines.documents.get(stringdocumentID, DocumentGetParams { pipeline_id } params, RequestOptionsoptions?): CloudDocument { id, metadata, text, 4 more }

GET/api/v1/pipelines/{pipeline_id}/documents/{document_id}

Delete Pipeline Document

client.pipelines.documents.delete(stringdocumentID, DocumentDeleteParams { pipeline_id } params, RequestOptionsoptions?): void

DELETE/api/v1/pipelines/{pipeline_id}/documents/{document_id}

Get Pipeline Document Status

client.pipelines.documents.getStatus(stringdocumentID, DocumentGetStatusParams { pipeline_id } params, RequestOptionsoptions?): ManagedIngestionStatusResponse { status, deployment_date, effective_at, 2 more }

GET/api/v1/pipelines/{pipeline_id}/documents/{document_id}/status

Sync Pipeline Document

client.pipelines.documents.sync(stringdocumentID, DocumentSyncParams { pipeline_id } params, RequestOptionsoptions?): DocumentSyncResponse

POST/api/v1/pipelines/{pipeline_id}/documents/{document_id}/sync

List Pipeline Document Chunks

client.pipelines.documents.getChunks(stringdocumentID, DocumentGetChunksParams { pipeline_id } params, RequestOptionsoptions?): DocumentGetChunksResponse { class_name, embedding, end_char_idx, 11 more }

GET/api/v1/pipelines/{pipeline_id}/documents/{document_id}/chunks

Upsert Batch Pipeline Documents

client.pipelines.documents.upsert(stringpipelineID, DocumentUpsertParams { body } params, RequestOptionsoptions?): DocumentUpsertResponse { id, metadata, text, 4 more }

PUT/api/v1/pipelines/{pipeline_id}/documents

ModelsExpand Collapse

CloudDocument { id, metadata, text, 4 more }

Cloud document stored in S3.

id: string

metadata: Record<string, unknown>

text: string

excluded_embed_metadata_keys?: Array<string>

excluded_llm_metadata_keys?: Array<string>

page_positions?: Array<number> | null

indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1].

status_metadata?: Record<string, unknown> | null

CloudDocumentCreate { metadata, text, id, 3 more }

Create a new cloud document.

metadata: Record<string, unknown>

text: string

id?: string | null

excluded_embed_metadata_keys?: Array<string>

excluded_llm_metadata_keys?: Array<string>

page_positions?: Array<number> | null

indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1].

TextNode { class_name, embedding, end_char_idx, 11 more }

Provided for backward compatibility.

Note: we keep the field with the typo "seperator" to maintain backward compatibility for serialized objects.

class_name?: string

embedding?: Array<number> | null

Embedding of the node.

end_char_idx?: number | null

End char index of the node.

excluded_embed_metadata_keys?: Array<string>

Metadata keys that are excluded from text for the embed model.

excluded_llm_metadata_keys?: Array<string>

Metadata keys that are excluded from text for the LLM.

extra_info?: Record<string, unknown>

A flat dictionary of metadata fields

id_?: string

Unique ID of the node.

metadata_seperator?: string

Separator between metadata fields when converting to string.

metadata_template?: string

Template for how metadata is formatted, with {key} and {value} placeholders.

mimetype?: string

MIME type of the node content.

relationships?: Record<string, RelatedNodeInfo { node_id, class_name, hash, 2 more } | Array<UnionMember1>>

A mapping of relationships to other node information.

Accepts one of the following:

RelatedNodeInfo { node_id, class_name, hash, 2 more }

node_id: string

class_name?: string

hash?: string | null

metadata?: Record<string, unknown>

node_type?: "1" | "2" | "3" | 2 more | (string & {}) | null

Accepts one of the following:

"1" | "2" | "3" | 2 more

"1"

"2"

"3"

"4"

"5"

(string & {})

Array<UnionMember1>

node_id: string

class_name?: string

hash?: string | null

metadata?: Record<string, unknown>

node_type?: "1" | "2" | "3" | 2 more | (string & {}) | null

Accepts one of the following:

"1" | "2" | "3" | 2 more

"1"

"2"

"3"

"4"

"5"

(string & {})

start_char_idx?: number | null

Start char index of the node.

text?: string

Text content of the node.

text_template?: string

Template for how text is formatted, with {content} and {metadata_str} placeholders.