Run Pipeline

Execute the full knowledge pipeline for a knowledge base. Supports both streaming and blocking response modes.

POST /datasets/{dataset_id}/pipeline/run

Error

A valid request URL is required to generate request examples

200

"<string>"

Authorizations

Authorization · string · header · required

API Key authentication. For all API requests, include your API Key in the Authorization HTTP Header, prefixed with Bearer. Example: Authorization: Bearer {API_KEY}. Strongly recommend storing your API Key on the server-side, not shared or stored on the client-side, to avoid possible API-Key leakage that can lead to serious consequences.

Path Parameters

dataset_id · string<uuid> · required

Knowledge base ID.

Body

application/json

inputs · object · required

Input variables for the pipeline.

datasource_type · enum<string> · required

Type of the datasource.

Available options: online_document, local_file, website_crawl, online_drive

datasource_info_list · object[] · required

List of datasource information objects for the pipeline to process.

start_node_id · string · required

ID of the node to start pipeline execution from.

is_published · boolean · required

Whether to run the published or draft version of the pipeline. true runs the published version, false runs the draft.

response_mode · enum<string> · required

Response mode for the pipeline execution. streaming returns a Server-Sent Events stream, blocking waits and returns the complete result.

Available options: streaming, blocking

Response

200

text/event-stream

Pipeline execution result. Format depends on response_mode: streaming returns a text/event-stream, blocking returns a JSON object.

Server-Sent Events stream containing pipeline execution progress and results. Returned when response_mode is streaming.