> ## Documentation Index
> Fetch the complete documentation index at: https://langwatch.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details.

# Create Evaluate

> Trigger an evaluation run of a workflow's committed version through the evaluations pipeline. Evaluate the workflow's attached dataset, inline data, or a platform dataset id; parameters bind as constant entry inputs on every row. A saved dataset is read at `dataset_version` when given, else its current content is saved as a new version. Returns a run id and a results URL to poll or open in the browser.



## OpenAPI

````yaml POST /api/v1/workflows/{id}/evaluate
openapi: 3.1.0
info:
  title: LangWatch API
  description: LangWatch openapi spec
  version: 1.0.0
servers:
  - url: https://app.langwatch.ai
security:
  - project_api_key: []
paths:
  /api/v1/workflows/{id}/evaluate:
    post:
      description: >-
        Trigger an evaluation run of a workflow's committed version through the
        evaluations pipeline. Evaluate the workflow's attached dataset, inline
        data, or a platform dataset id; parameters bind as constant entry inputs
        on every row. A saved dataset is read at `dataset_version` when given,
        else its current content is saved as a new version. Returns a run id and
        a results URL to poll or open in the browser.
      operationId: postApiWorkflowsByIdEvaluate
      parameters:
        - in: path
          name: id
          schema:
            type: string
            minLength: 1
          required: true
      requestBody:
        required: false
        content:
          application/json:
            schema:
              type: object
              properties:
                version_id:
                  description: Committed version to evaluate; defaults to the latest commit
                  type: string
                data:
                  description: >-
                    Inline rows to evaluate instead of the workflow's attached
                    dataset
                  type: array
                  items:
                    type: object
                    propertyNames:
                      type: string
                    additionalProperties: {}
                dataset_id:
                  description: >-
                    Platform dataset id to evaluate; mutually exclusive with
                    data
                  type: string
                dataset_version:
                  description: >-
                    Version of the saved dataset to evaluate (dataset_id, else
                    the workflow's attached dataset); defaults to its current
                    content
                  type: integer
                  exclusiveMinimum: 0
                  maximum: 9007199254740991
                parameters:
                  description: >-
                    Constant entry inputs applied to every row, e.g. a feature
                    flag or PR number
                  type: object
                  propertyNames:
                    type: string
                  additionalProperties:
                    type:
                      - string
                      - number
                      - boolean
                row_indices:
                  description: Subset of dataset row indices to evaluate
                  type: array
                  items:
                    type: integer
                    minimum: 0
                    maximum: 9007199254740991
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                type: object
                properties:
                  run_id:
                    type: string
                  run_url:
                    type: string
                  workflow_version_id:
                    type: string
                  version:
                    type: string
                required:
                  - run_id
                  - run_url
                  - workflow_version_id
                  - version
                additionalProperties: false
        '400':
          description: >-
            The workflow has no committed version, the run could not start, or
            `dataset_version` was sent with no saved dataset to read it from
          content: {}
        '403':
          description: The API key cannot read the evaluation run it would start
          content: {}
        '404':
          description: >-
            The project holds no such workflow or dataset, or the dataset has no
            version `dataset_version` names (`dataset_version_not_found`)
          content: {}
        '422':
          description: The body failed validation
          content: {}
      security:
        - project_api_key: []
components:
  securitySchemes:
    project_api_key:
      type: apiKey
      in: header
      name: X-Auth-Token
      description: >-
        Project API key for sending traces and accessing project-scoped
        resources. Format: sk-lw-... (no underscore). Obtain one by creating a
        project via the Admin API or the LangWatch UI.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.