Evals

Update Eval

Update an existing eval's fields and prompts.

Args: eval_uuid (str): UUID of the eval to update. update_request (EvalUpdateRequest): Update data including fields and prompt modifications. workspace_uuid (str, optional): Optional workspace UUID for filtering.

Returns: Eval: The updated eval data.

Raises: AymaraAPIError: If the eval is not found or update is invalid.

Example: PUT /api/evals/{eval_uuid} { "name": "Updated Eval Name", "ai_description": "Updated description", "prompt_updates": [ {"prompt_uuid": "...", "content": "New content", "action": "update"}, {"prompt_uuid": "...", "action": "delete"} ], "prompt_creates": [ {"content": "New prompt", "category": "test"} ] }

put/v2/evals/{eval_uuid}

Path parameters

eval_uuidstring required

Query parameters

workspace_uuidstring

Request body

namestring nullable

New name for the evaluation.

ai_descriptionstring nullable

New description of the AI under evaluation.

eval_instructionsstring nullable

New additional instructions for the eval.

Response

OK

eval_uuidstring nullable

Unique identifier for the evaluation.

namestring nullable

Name of the evaluation.

created_bystring nullable

Name of the user who created the evaluation.

ai_descriptionstring required

Description of the AI under evaluation.

eval_typestring required

Type of the eval (safety, accuracy, etc.)

eval_instructionsstring nullable

Additional instructions for the eval, if any.

languagestring nullable

Language code for the eval (default: "en").

modality'text' | 'image' | 'video'

Content type for AI interactions.

num_promptsinteger nullable

Number of prompts/questions in the eval (default: 50).

is_jailbreakboolean

Indicates if the eval is a jailbreak test.

is_sandboxboolean

Indicates if the eval results are sandboxed.

workspace_uuidstring nullable

UUID of the associated workspace, if any.

status'created' | 'processing' | 'finished' | 'failed'

Resource status.

created_atstring date-time nullable

Timestamp when the eval was created.

updated_atstring date-time nullable

Timestamp when the eval was last updated.

Changes

Changed in 8 of the 25 revisions of this API.6219

  • 0cb64ef11adf22See the full diff
    • removed the required property ai_instructions/anyOf[subschema #2: AgentInstructions]/tools/oneOf[subschema #1: ToolArray]/value/items/id from the response with the 200 status

      response-required-property-removed

    • removed the required property ai_instructions/anyOf[subschema #3: WorkflowInstructions]/instructions/items/tools/oneOf[subschema #1: ToolArray]/value/items/id from the response with the 200 status

      response-required-property-removed

    • removed the request property ai_instructions/anyOf[subschema #2: AgentInstructions]/tools/oneOf[subschema #1: ToolArray]/value/items/id

      request-property-removed

    • removed the request property ai_instructions/anyOf[subschema #3: WorkflowInstructions]/instructions/items/tools/oneOf[subschema #1: ToolArray]/value/items/id

      request-property-removed

    • added subschema #1 subschema #4 to the ai_instructions response property anyOf list for the response status 200

      response-property-any-of-added

    • removed subschema #1 subschema #4 from the ai_instructions response property anyOf list for the response status 200

      response-property-any-of-removed

    • added the new optional request property ai_instructions/anyOf[subschema #2: AgentInstructions]/agent_name

      new-optional-request-property

    • added WorkflowInstructions to the ai_instructions request property anyOf list

      request-property-any-of-added

    • added the optional property ai_instructions/anyOf[subschema #2: AgentInstructions]/agent_name to the response with the 200 status

      response-optional-property-added

    • added WorkflowInstructions to the ai_instructions response property anyOf list for the response status 200

      response-property-any-of-added

  • 1af31c95d91a24See the full diff
    • removed ToolsList ToolDict ToolsString from the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools request property anyOf list

      request-property-any-of-removed

    • added ToolArray ToolDict ToolString to the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools response property oneOf list for the response status 200

      response-property-one-of-added

    • added discriminator to ai_instructions/anyOf[subschema #2: AgentInstructions]/tools request property

      request-property-discriminator-added

    • added ToolArray ToolDict ToolString to the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools request property oneOf list

      request-property-one-of-added

    • removed ToolsList ToolDict ToolsString from the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools response property anyOf list for the response status 200

      response-property-any-of-removed

    • added discriminator to ai_instructions/anyOf[subschema #2: AgentInstructions]/tools response property for the response status 200

      response-property-discriminator-added

    This revision also has 2 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • d950d722e23013See the full diff
    • removed subschema #1 subschema #3 from the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools request property anyOf list

      request-property-any-of-removed

    • added subschema #1 subschema #3 to the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools request property anyOf list

      request-property-any-of-added

    • added subschema #1 subschema #3 to the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools response property anyOf list for the response status 200

      response-property-any-of-added

    • removed subschema #1 subschema #3 from the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools response property anyOf list for the response status 200

      response-property-any-of-removed

    • removed subschema #2 from the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools request property anyOf list

      request-property-any-of-removed

    • added subschema #1 to the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools request property anyOf list

      request-property-any-of-added

    • added subschema #1 to the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools response property anyOf list for the response status 200

      response-property-any-of-added

    • removed subschema #2 from the ai_instructions/anyOf[subschema #2: AgentInstructions]/tools response property anyOf list for the response status 200

      response-property-any-of-removed

    • added AgentInstructions to the ai_instructions request property anyOf list

      request-property-any-of-added

    • added AgentInstructions to the ai_instructions response property anyOf list for the response status 200

      response-property-any-of-added

    • endpoint added

      endpoint-added