Run Pipeline
Execute the full knowledge pipeline for a knowledge base. Supports both streaming and blocking response modes.
<string>{
"status": 400,
"code": "invalid_param",
"message": "Pipeline not found"
}{
"status": 403,
"code": "forbidden",
"message": "Dataset api access is not enabled."
}{
"status": 404,
"code": "not_found",
"message": "Dataset not found."
}{
"status": 500,
"code": "pipeline_run_error",
"message": "Pipeline execution failed: connection timeout"
}Authorizations
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. Requests with a missing or invalid API key fail with HTTP 401 and error code unauthorized.
Path Parameters
Knowledge base ID.
Body
Key-value pairs for pipeline input variables defined in the workflow. Pass {} if the pipeline has no input variables.
Type of the datasource. Determines which fields are expected in datasource_info_list items.
local_file, online_document, website_crawl, online_drive List of datasource objects to process. The expected item structure depends on datasource_type.
- Local File
- Online Document
- Website Crawl
- Online Drive
Show child attributes
Show child attributes
ID of the node to start pipeline execution from.
Whether to run the published or draft version of the pipeline. true runs the latest published version; false runs the current draft (useful for testing unpublished changes).
Response mode for the pipeline execution. streaming returns a Server-Sent Events stream, blocking waits and returns the complete result.
streaming, blocking Response
Pipeline execution result. Format depends on response_mode: streaming returns a text/event-stream, blocking returns a JSON object.
Server-Sent Events stream. Returned when response_mode is streaming.
Each line is data: {JSON}\n\n. Key events: workflow_started (execution began), node_started / node_finished (per-node progress with node_id, node_type, status, inputs, outputs), workflow_finished (final result with status, outputs, total_tokens, elapsed_time), ping (keepalive).
Was this page helpful?
<string>{
"status": 400,
"code": "invalid_param",
"message": "Pipeline not found"
}{
"status": 403,
"code": "forbidden",
"message": "Dataset api access is not enabled."
}{
"status": 404,
"code": "not_found",
"message": "Dataset not found."
}{
"status": 500,
"code": "pipeline_run_error",
"message": "Pipeline execution failed: connection timeout"
}