Skip to main content

Endpoint

method
string
default:"POST"
POST
endpoint
string
/v1/evaluator/query

Authentication

This endpoint requires API key authentication. Include your API key in the request headers:
Authorization: Bearer YOUR_API_KEY

Request Body

No specific parameters required. Send an empty object.

Response

data
array
Array of evaluator objects
id
string
Unique identifier for the evaluator
name
string
Evaluator name
scoring_type
string
Type of scoring: “LLM-BOOLEAN”, “LLM-CHOICE”, “LLM-RANGE”, “PYTHON”, or “LASTMILE”
llm_template
object
LLM configuration for LLM-based evaluators
code_template
object
Python code for code-based evaluators
last_mile_config
object
Configuration for LastMile evaluators
organization_id
string
Organization that owns this evaluator
created_at
string
Creation timestamp
updated_at
string
Last update timestamp
error
string | null
Error message if the request failed, null otherwise

Example Request

curl -X POST https://api.helicone.ai/v1/evaluator/query \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

Example Response

{
  "data": [
    {
      "id": "eval_abc123",
      "name": "Hallucination Detector",
      "scoring_type": "LLM-BOOLEAN",
      "llm_template": {
        "model": "gpt-4",
        "prompt": "Does this response contain hallucinations?"
      },
      "code_template": null,
      "last_mile_config": null,
      "organization_id": "org_xyz789",
      "created_at": "2024-01-10T09:00:00Z",
      "updated_at": "2024-01-15T14:30:00Z"
    },
    {
      "id": "eval_def456",
      "name": "Relevance Score",
      "scoring_type": "LLM-RANGE",
      "llm_template": {
        "model": "gpt-4",
        "prompt": "Rate the relevance from 1-10",
        "min": 1,
        "max": 10
      },
      "code_template": null,
      "last_mile_config": null,
      "organization_id": "org_xyz789",
      "created_at": "2024-01-12T11:00:00Z",
      "updated_at": "2024-01-12T11:00:00Z"
    }
  ],
  "error": null
}

Evaluator Types

LLM-BOOLEAN

Uses an LLM to return a true/false score

LLM-CHOICE

Uses an LLM to select from predefined choices

LLM-RANGE

Uses an LLM to score within a numeric range

PYTHON

Executes custom Python code for evaluation

LASTMILE

Integration with LastMile evaluation framework

Build docs developers (and LLMs) love