Skip to content
POST/api/v1/scorers/local-model

Create or update a local-model scorer config

Upserts a local-model-backed scorer for an org. Provide id to update an existing config; omit it to create. requiredRole: member.

Authentication

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

Request body required

Example

{
  "orgId": "00000000-0000-0000-0000-000000000000",
  "id": "00000000-0000-0000-0000-000000000000",
  "name": "string",
  "endpointUrl": "https://example.com",
  "modelName": "string",
  "format": "openai",
  "promptTemplate": "string",
  "parseResponse": "json-score",
  "passThreshold": 0.7,
  "timeoutMs": 30000,
  "maxRetries": 2,
  "headers": {}
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "required": [
        "orgId",
        "name",
        "endpointUrl",
        "modelName",
        "format",
        "promptTemplate",
        "parseResponse"
      ],
      "properties": {
        "orgId": {
          "type": "string",
          "format": "uuid"
        },
        "id": {
          "type": "string",
          "format": "uuid",
          "description": "Present = update existing config; absent = create."
        },
        "name": {
          "type": "string",
          "maxLength": 100
        },
        "endpointUrl": {
          "type": "string",
          "format": "uri"
        },
        "modelName": {
          "type": "string"
        },
        "format": {
          "type": "string",
          "enum": [
            "openai",
            "ollama",
            "vllm",
            "tgi"
          ]
        },
        "promptTemplate": {
          "type": "string"
        },
        "parseResponse": {
          "type": "string",
          "enum": [
            "json-score",
            "text-binary",
            "logprobs"
          ]
        },
        "passThreshold": {
          "type": "number",
          "minimum": 0,
          "maximum": 1,
          "default": 0.7
        },
        "timeoutMs": {
          "type": "integer",
          "minimum": 1000,
          "maximum": 300000,
          "default": 30000
        },
        "maxRetries": {
          "type": "integer",
          "minimum": 0,
          "maximum": 10,
          "default": 2
        },
        "headers": {
          "type": "object",
          "additionalProperties": {
            "type": "string"
          }
        }
      }
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Updated existing config.
201Created new config.
400(no description)
401(no description)
403Forbidden — member role required.
409Conflict — CONFLICT.
429(no description)
500Internal Server Error — DB_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/scorers/local-model \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "orgId": "00000000-0000-0000-0000-000000000000", "id": "00000000-0000-0000-0000-000000000000", "name": "string", "endpointUrl": "https://example.com", "modelName": "string", "format": "openai", "promptTemplate": "string", "parseResponse": "json-score", "passThreshold": 0.7, "timeoutMs": 30000, "maxRetries": 2, "headers": {} }'

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/scorers/local-model", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "orgId": "00000000-0000-0000-0000-000000000000",
    "id": "00000000-0000-0000-0000-000000000000",
    "name": "string",
    "endpointUrl": "https://example.com",
    "modelName": "string",
    "format": "openai",
    "promptTemplate": "string",
    "parseResponse": "json-score",
    "passThreshold": 0.7,
    "timeoutMs": 30000,
    "maxRetries": 2,
    "headers": {}
  }),
});
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/scorers/local-model",
    headers=headers,
    json={
    "orgId": "00000000-0000-0000-0000-000000000000",
    "id": "00000000-0000-0000-0000-000000000000",
    "name": "string",
    "endpointUrl": "https://example.com",
    "modelName": "string",
    "format": "openai",
    "promptTemplate": "string",
    "parseResponse": "json-score",
    "passThreshold": 0.7,
    "timeoutMs": 30000,
    "maxRetries": 2,
    "headers": {}
},
)
print(response.status_code, response.json())

Go

package main

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

func main() {
	body := strings.NewReader(`{"orgId":"00000000-0000-0000-0000-000000000000","id":"00000000-0000-0000-0000-000000000000","name":"string","endpointUrl":"https://example.com","modelName":"string","format":"openai","promptTemplate":"string","parseResponse":"json-score","passThreshold":0.7,"timeoutMs":30000,"maxRetries":2,"headers":{}}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/scorers/local-model", 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

400401403409429500

Other Evals endpoints