> ## Documentation index > Fetch the complete documentation index at: https://dify-docs.docs7.io/llms.txt > Ask it with GET https://dify-docs.docs7.io/ask?q=. Short keywords rank best. > Use these to discover all available pages before exploring further. # Run Pipeline > Runs the full knowledge pipeline over one or more datasources. `response_mode` selects a streaming or blocking response. `POST /datasets/{dataset_id}/pipeline/run` ## OpenAPI ````yaml en/api-reference/openapi_service.json post /datasets/{dataset_id}/pipeline/run openapi: 3.0.1 info: description: REST API for Dify applications and knowledge bases. Application endpoints authenticate with an app API key; knowledge endpoints authenticate with a dataset API key. title: Dify Service API version: 1.0.0 servers: - description: Base URL of the Dify Service API. For self-hosted deployments, replace it with your own API base URL. url: https://{api_base_url} variables: api_base_url: default: api.dify.ai/v1 description: Host and path of the API base URL, without the `https://` prefix. security: - ApiKeyAuth: [] tags: - description: Operations related to chat messages and interactions. name: Chat Messages - description: File upload and preview operations. name: Files - description: Operations related to end user information. name: End Users - description: User feedback operations. name: Feedback - description: Operations related to managing conversations. name: Conversations - description: Text-to-Speech and Speech-to-Text operations. name: Audio - description: Operations to retrieve application settings and information. name: Applications - description: Operations related to managing annotations for direct replies. name: Annotations - description: Endpoints for resuming paused workflows that require human input. name: Human Input - description: Operations for executing and managing workflows. name: Workflow Runs - description: Operations related to text generation and completion. name: Completion Messages - description: Operations for managing knowledge bases, including creation, configuration, and retrieval. name: Knowledge Bases - description: Operations for creating, updating, and managing documents within a knowledge base. name: Documents - description: Operations for managing document chunks and child chunks. name: Chunks - description: Operations for managing knowledge base metadata fields and document metadata values. name: Metadata - description: Operations for managing knowledge base tags and tag bindings. name: Tags - description: Operations for retrieving available models. name: Models - description: Operations for managing and running knowledge pipelines, including datasource plugins and pipeline execution. name: Knowledge Pipeline paths: /datasets/{dataset_id}/pipeline/run: post: description: Runs the full knowledge pipeline over one or more datasources. `response_mode` selects a streaming or blocking response. operationId: runPipeline parameters: - description: Knowledge base ID, from [List Knowledge Bases](/en/api-reference/knowledge-bases/list-knowledge-bases). For a scoped key, [copy the ID from the Dify URL](/en/api-reference/guides/knowledge#knowledge-base-id). in: path name: dataset_id required: true schema: format: uuid type: string requestBody: content: application/json: examples: local_file: summary: Request Example - Local file value: datasource_info_list: - name: quarterly-report.pdf reference: a1b2c3d4-e5f6-7890-abcd-ef1234567890 datasource_type: local_file inputs: {} is_published: true response_mode: blocking start_node_id: "1719288585006" online_document: summary: Request Example - Online document value: datasource_info_list: - credential_id: cred-789xyz page: page_id: pg-def456 page_name: Product Roadmap type: page workspace_id: ws-abc123 datasource_type: online_document inputs: {} is_published: true response_mode: streaming start_node_id: "1719288585006" online_drive: summary: Request Example - Online drive value: datasource_info_list: - bucket: my-bucket id: file-abc123 name: meeting-notes.docx type: file datasource_type: online_drive inputs: {} is_published: true response_mode: blocking start_node_id: "1719288585006" website_crawl: summary: Request Example - Website crawl value: datasource_info_list: - title: Getting Started Guide url: https://example.com/docs/getting-started datasource_type: website_crawl inputs: {} is_published: true response_mode: blocking start_node_id: "1719288585006" schema: properties: datasource_info_list: description: List of datasource objects to process. The expected item structure depends on `datasource_type`. items: oneOf: - properties: name: description: Document title. Defaults to `"untitled"`. type: string reference: description: Use the `id` returned by the [Upload Pipeline File](/en/api-reference/knowledge-pipeline/upload-pipeline-file) endpoint. `related_id` is accepted as an alias. type: string required: - reference title: Local File type: object - properties: credential_id: description: Credential for authenticating with the external platform. Managed via the Dify console. If omitted, the provider's default credential is used. type: string page: description: Page details. properties: page_id: description: Page identifier. type: string page_name: description: Display name. Defaults to `"untitled"`. type: string type: description: Page type defined by the datasource plugin (e.g., `"page"`, `"database"`). type: string required: - page_id - type type: object workspace_id: description: ID of the workspace or database in the external platform (e.g., a Notion workspace ID). type: string required: - workspace_id - page title: Online Document type: object - properties: title: description: Used as the document name. Defaults to `"untitled"`. type: string url: description: URL to crawl. type: string required: - url title: Website Crawl type: object - properties: bucket: description: Storage bucket name. Required by some drive providers (e.g., S3-compatible stores); omit if the provider does not use buckets. type: string id: description: File or folder ID. type: string name: description: File name. Defaults to `"untitled"`. type: string type: description: Whether this entry is a single file or a folder to expand. enum: - file - folder type: string required: - id - type title: Online Drive type: object type: array datasource_type: description: Type of the datasource. Determines which fields are expected in `datasource_info_list` items. enum: - local_file - online_document - website_crawl - online_drive type: string inputs: additionalProperties: true description: Key-value pairs for pipeline input variables defined in the workflow. Pass `{}` if the pipeline has no input variables. type: object is_published: description: Whether to run the published version of the pipeline instead of the current draft. Run the draft to test unpublished changes. type: boolean response_mode: description: Response mode for the pipeline execution. `streaming` returns a Server-Sent Events stream, `blocking` waits and returns the complete result. enum: - streaming - blocking type: string start_node_id: description: ID of the node to start execution from, from [List Datasource Plugins](/en/api-reference/knowledge-pipeline/list-datasource-plugins). type: string required: - inputs - datasource_type - datasource_info_list - start_node_id - is_published - response_mode type: object required: true responses: "200": content: application/json: examples: success: summary: Blocking Response Example value: data: created_at: 1741267200 finished_at: 1741267210 id: f1e2d3c4-b5a6-7890-abcd-ef0987654321 outputs: {} status: succeeded task_id: a1b2c3d4-e5f6-7890-abcd-ef1234567890 workflow_run_id: f1e2d3c4-b5a6-7890-abcd-ef0987654321 schema: additionalProperties: true description: Complete pipeline execution result. Returned when `response_mode` is `blocking`. type: object text/event-stream: schema: description: >- Server-Sent Events stream. Returned when `response_mode` is `streaming`; see [SSE Streaming](/en/api-reference/guides/streaming) for the wire format. 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 type: string description: "Pipeline execution result. Format depends on `response_mode`: streaming returns a `text/event-stream`, blocking returns a JSON object." "400": content: application/json: examples: invalid_param: summary: invalid_param value: code: invalid_param message: Pipeline not found status: 400 description: "`invalid_param` : The knowledge base has no processing pipeline configured, or the request body failed validation." "403": content: application/json: examples: forbidden_1: summary: forbidden (api access) value: code: forbidden message: Dataset api access is not enabled. status: 403 forbidden_2: summary: forbidden (key scope) value: code: forbidden message: The API key is not authorized to access this knowledge base. status: 403 description: >- - `forbidden` : API access is not enabled for this knowledge base. - `forbidden` : The API key is scoped to specific knowledge bases, and this knowledge base is not one of them. "404": content: application/json: examples: not_found: summary: not_found value: code: not_found message: Dataset not found. status: 404 description: "`not_found` : No knowledge base matches `dataset_id`." "500": content: application/json: examples: pipeline_run_error: summary: pipeline_run_error value: code: pipeline_run_error message: "Pipeline execution failed: connection timeout" status: 500 description: "`pipeline_run_error` : Pipeline execution failed." summary: Run Pipeline tags: - Knowledge Pipeline x-mint: href: /en/api-reference/knowledge-pipeline/run-pipeline metadata: sidebarTitle: Run Pipeline title: Run Pipeline components: securitySchemes: ApiKeyAuth: bearerFormat: API_KEY description: >- Every request authenticates with an API key: `Authorization: Bearer {API_KEY}`. App endpoints take an app API key; knowledge endpoints take a knowledge base API key ([Get Started](/en/api-reference/guides/get-started)). Keep keys server-side; never embed them in client code. Requests with a missing or invalid key fail with HTTP `401` (`unauthorized`). scheme: bearer type: http ````