Skip to content
POST/api/v1/evaluators

Create an evaluator version (content-hash deduped)

Creates a new version of a named evaluator (projectId + name + definition required; definition.kind ∈ llm-judge|code|heuristic|composite). The definition is content-hashed: if it is identical to the latest version the existing row is returned with `deduped: true` and HTTP 200 (a changed `numberValence` is patched onto that row in place rather than forcing a new version). Otherwise a new version is inserted at latest+1 (with one retry on the UNIQUE race) and returned with 201. `activate` DEFAULTS TO TRUE — the new version becomes active and every other version of that name is demoted; pass `activate: false` to create it inactive. Editor role, evals:create.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Request body required

Example

{
  "projectId": "00000000-0000-0000-0000-000000000000",
  "name": "string",
  "definition": {
    "kind": "llm-judge",
    "config": {},
    "threshold": 0
  },
  "notes": "string",
  "activate": false,
  "numberValence": "positive"
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "projectId": {
          "type": "string",
          "format": "uuid",
          "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
        },
        "name": {
          "type": "string",
          "minLength": 1,
          "maxLength": 200
        },
        "definition": {
          "type": "object",
          "properties": {
            "kind": {
              "type": "string",
              "enum": [
                "llm-judge",
                "code",
                "heuristic",
                "composite"
              ]
            },
            "config": {
              "default": {},
              "type": "object",
              "additionalProperties": {}
            },
            "threshold": {
              "type": "number",
              "minimum": 0,
              "maximum": 1
            }
          },
          "required": [
            "kind",
            "config"
          ],
          "additionalProperties": false
        },
        "notes": {
          "type": "string",
          "maxLength": 2000
        },
        "activate": {
          "type": "boolean"
        },
        "numberValence": {
          "type": "string",
          "enum": [
            "positive",
            "negative",
            "neutral"
          ]
        }
      },
      "required": [
        "projectId",
        "name",
        "definition"
      ],
      "additionalProperties": false
    }
  }
}

Response

All status codes

200Deduped — identical to the latest version
201Created
401Unauthorized — no valid credential was presented (AUTH_REQUIRED).
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
429Too Many Requests — the per-key or per-organization rate limit was exceeded. Honour the Retry-After header.
500Internal Server Error — DB_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/evaluators \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "projectId": "00000000-0000-0000-0000-000000000000", "name": "string", "definition": { "kind": "llm-judge", "config": {}, "threshold": 0 }, "notes": "string", "activate": false, "numberValence": "positive" }'

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/evaluators", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "projectId": "00000000-0000-0000-0000-000000000000",
    "name": "string",
    "definition": {
      "kind": "llm-judge",
      "config": {},
      "threshold": 0
    },
    "notes": "string",
    "activate": false,
    "numberValence": "positive"
  }),
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}
headers["Content-Type"] = "application/json"

response = requests.request(
    "POST",
    "https://evalguard.ai/api/v1/evaluators",
    headers=headers,
    json={
    "projectId": "00000000-0000-0000-0000-000000000000",
    "name": "string",
    "definition": {
        "kind": "llm-judge",
        "config": {},
        "threshold": 0
    },
    "notes": "string",
    "activate": False,
    "numberValence": "positive"
},
)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"projectId":"00000000-0000-0000-0000-000000000000","name":"string","definition":{"kind":"llm-judge","config":{},"threshold":0},"notes":"string","activate":false,"numberValence":"positive"}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/evaluators", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

401403429500

Other Evaluators endpoints