Skip to content
POST/api/v1/annotations/bootstrap

Bootstrap an evaluator from completed annotations

Learns an evaluator (rubric/few-shot/classifier) from a queue's completed annotations and returns it synchronously. queueId, targetDimension, method required; minAnnotations optional (default 10).

Authentication

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

Request body required

Example

{
  "queueId": "00000000-0000-0000-0000-000000000000",
  "targetDimension": "string",
  "method": "rubric-extraction",
  "minAnnotations": 1
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "queueId": {
          "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)$",
          "description": "Annotation queue (maps to project_id in production_logs)."
        },
        "targetDimension": {
          "type": "string",
          "minLength": 1,
          "maxLength": 200
        },
        "method": {
          "type": "string",
          "enum": [
            "rubric-extraction",
            "few-shot",
            "classifier-train"
          ]
        },
        "minAnnotations": {
          "type": "integer",
          "minimum": 1,
          "maximum": 10000
        }
      },
      "required": [
        "queueId",
        "targetDimension",
        "method"
      ],
      "additionalProperties": false
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Bootstrapped evaluator (or prompt_ready inputs for LLM-backed methods).
400(no description)
401(no description)
422Not enough completed annotations.
429(no description)

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/annotations/bootstrap \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "queueId": "00000000-0000-0000-0000-000000000000", "targetDimension": "string", "method": "rubric-extraction", "minAnnotations": 1 }'

TypeScript

import { EvalGuard } from "@evalguard/sdk";

const client = new EvalGuard({ apiKey: process.env.EVALGUARD_API_KEY });

const response = await client.request({
  method: "POST",
  path: "/api/v1/annotations/bootstrap",
  body: {
    "queueId": "00000000-0000-0000-0000-000000000000",
    "targetDimension": "string",
    "method": "rubric-extraction",
    "minAnnotations": 1
  },
});
console.log(response);

Python

from evalguard import EvalGuard
import os

client = EvalGuard(api_key=os.environ["EVALGUARD_API_KEY"])

response = client.request(
    method="POST",
    path="/api/v1/annotations/bootstrap",
    body={
    "queueId": "00000000-0000-0000-0000-000000000000",
    "targetDimension": "string",
    "method": "rubric-extraction",
    "minAnnotations": 1
},
)
print(response)

Go

package main

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

func main() {
	body := strings.NewReader(`{"queueId":"00000000-0000-0000-0000-000000000000","targetDimension":"string","method":"rubric-extraction","minAnnotations":1}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/annotations/bootstrap", 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

400401422429

Other Evals endpoints