Opik Manual Evaluation API
Manual evaluation resources for traces, threads, and spans
Manual evaluation resources for traces, threads, and spans
openapi: 3.1.0
info:
title: Opik REST Manual Evaluation API
description: "The Opik REST API is currently in beta and subject to change. If you have any questions or feedback about the APIs, please reach out on GitHub: https://github.com/comet-ml/opik.\n\nAll of the methods listed in this documentation are used by either the SDK or the UI to interact with the Opik server. As a result,\nthe methods have been optimized for these use-cases in mind. If you are looking for a method that is not listed above, please create\nand issue on GitHub or raise a PR!\n\nOpik includes two main deployment options that results in slightly different API usage:\n\n- **Self-hosted Opik instance:** You will simply need to specify the URL as `http://localhost:5173/api/<endpoint_path>` or similar. This is the default option for the docs.\n- **Opik Cloud:** You will need to specify the Opik API Key and Opik Workspace in the header. The format of the header should be:\n\n ```\n {\n \"Comet-Workspace\": \"your-workspace-name\",\n \"authorization\": \"your-api-key\"\n }\n ```\n\n The full payload would therefore look like:\n \n ```\n curl -X GET 'https://www.comet.com/opik/api/v1/private/projects' \\\n -H 'Accept: application/json' \\\n -H 'Comet-Workspace: <your-workspace-name>' \\\n -H 'authorization: <your-api-key>'\n ```\n\n Do take note here that the authorization header value does not include the `Bearer ` prefix. To switch to using the Opik Cloud in the documentation, you can\n click on the edit button displayed when hovering over the `Base URL` displayed on the right hand side of the docs.\n"
contact:
name: Github Repository
url: https://github.com/comet-ml/opik
license:
name: Apache 2.0
url: http://www.apache.org/licenses/LICENSE-2.0.html
version: 1.0.0
servers:
- url: http://localhost:5173/api
description: Local server
- url: https://www.comet.com/opik/api
description: Opik Cloud
tags:
- name: Manual Evaluation
description: Manual evaluation resources for traces, threads, and spans
paths:
/v1/private/manual-evaluation/spans:
post:
tags:
- Manual Evaluation
summary: Manually evaluate spans
description: Manually trigger evaluation rules on selected spans. Bypasses sampling and enqueues all specified spans for evaluation.
operationId: evaluateSpans
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ManualEvaluationRequest'
responses:
'202':
description: Accepted - Evaluation request queued successfully
content:
application/json:
schema:
$ref: '#/components/schemas/ManualEvaluationResponse'
'400':
description: Bad Request - Invalid request or missing automation rules
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorMessage'
'404':
description: Not Found - Project not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorMessage'
/v1/private/manual-evaluation/threads:
post:
tags:
- Manual Evaluation
summary: Manually evaluate threads
description: Manually trigger evaluation rules on selected threads. Bypasses sampling and enqueues all specified threads for evaluation.
operationId: evaluateThreads
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ManualEvaluationRequest'
responses:
'202':
description: Accepted - Evaluation request queued successfully
content:
application/json:
schema:
$ref: '#/components/schemas/ManualEvaluationResponse'
'400':
description: Bad Request - Invalid request or missing automation rules
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorMessage'
'404':
description: Not Found - Project not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorMessage'
/v1/private/manual-evaluation/traces:
post:
tags:
- Manual Evaluation
summary: Manually evaluate traces
description: Manually trigger evaluation rules on selected traces. Bypasses sampling and enqueues all specified traces for evaluation.
operationId: evaluateTraces
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ManualEvaluationRequest'
responses:
'202':
description: Accepted - Evaluation request queued successfully
content:
application/json:
schema:
$ref: '#/components/schemas/ManualEvaluationResponse'
'400':
description: Bad Request - Invalid request or missing automation rules
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorMessage'
'404':
description: Not Found - Project not found
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorMessage'
components:
schemas:
ErrorMessage:
type: object
properties:
code:
type: integer
format: int32
message:
type: string
details:
type: string
ManualEvaluationResponse:
type: object
properties:
entities_queued:
type: integer
description: Number of entities queued for evaluation
format: int32
example: 5
rules_applied:
type: integer
description: Number of rules that will be applied
format: int32
example: 2
ManualEvaluationRequest:
required:
- entity_ids
- entity_type
- project_id
- rule_ids
type: object
properties:
project_id:
type: string
description: Project ID
format: uuid
example: 550e8400-e29b-41d4-a716-446655440000
entity_ids:
minItems: 1
type: array
description: List of entity IDs (trace IDs or thread IDs) to evaluate
example:
- 550e8400-e29b-41d4-a716-446655440000
- 550e8400-e29b-41d4-a716-446655440001
items:
type: string
description: List of entity IDs (trace IDs or thread IDs) to evaluate
format: uuid
rule_ids:
minItems: 1
type: array
description: List of automation rule IDs to apply
example:
- 660e8400-e29b-41d4-a716-446655440000
items:
type: string
description: List of automation rule IDs to apply
format: uuid
entity_type:
type: string
description: Type of entity to evaluate (trace or thread)
example: trace
enum:
- trace
- thread
- span