Skip to content
POST/api/v1/experiments/rag-automl

Run a RAG AutoML combinatorial search

Enumerates a RAG config search space, scores submitted candidate rankings via IR metrics (nDCG/MAP/MRR), and persists a reproducible org-scoped leaderboard. role=editor, audited.

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",
  "searchSpace": {},
  "qrels": {},
  "runs": {},
  "objective": "ndcg",
  "objectiveK": 0,
  "ks": [
    0
  ],
  "maxConfigs": 0
}
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
        },
        "searchSpace": {
          "type": "object",
          "additionalProperties": {
            "minItems": 1,
            "maxItems": 64,
            "type": "array",
            "items": {
              "anyOf": [
                {
                  "type": "number"
                },
                {
                  "type": "string",
                  "maxLength": 200
                },
                {
                  "type": "boolean"
                }
              ]
            }
          }
        },
        "qrels": {
          "type": "object",
          "additionalProperties": {
            "type": "object",
            "additionalProperties": {
              "type": "number",
              "minimum": 0,
              "maximum": 10
            }
          }
        },
        "runs": {
          "type": "object",
          "additionalProperties": {
            "type": "object",
            "additionalProperties": {
              "maxItems": 1000,
              "type": "array",
              "items": {
                "type": "string",
                "minLength": 1,
                "maxLength": 200
              }
            }
          }
        },
        "objective": {
          "type": "string",
          "enum": [
            "ndcg",
            "map",
            "mrr",
            "precision",
            "recall",
            "hitRate"
          ]
        },
        "objectiveK": {
          "type": "integer",
          "minimum": 0,
          "exclusiveMinimum": true,
          "maximum": 1000
        },
        "ks": {
          "minItems": 1,
          "maxItems": 10,
          "type": "array",
          "items": {
            "type": "integer",
            "minimum": 0,
            "exclusiveMinimum": true,
            "maximum": 1000
          }
        },
        "maxConfigs": {
          "type": "integer",
          "minimum": 0,
          "exclusiveMinimum": true,
          "maximum": 256
        }
      },
      "required": [
        "projectId",
        "name",
        "searchSpace",
        "qrels",
        "runs"
      ],
      "additionalProperties": false
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Ranked leaderboard.
201Created.
400(no description)
401(no description)
403Forbidden — insufficient role for this operation.
409Conflict — CONFLICT.
429(no description)
500Internal Server Error — DB_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/experiments/rag-automl \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "projectId": "00000000-0000-0000-0000-000000000000", "name": "string", "searchSpace": {}, "qrels": {}, "runs": {}, "objective": "ndcg", "objectiveK": 0, "ks": [ 0 ], "maxConfigs": 0 }'

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/experiments/rag-automl", {
  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",
    "searchSpace": {},
    "qrels": {},
    "runs": {},
    "objective": "ndcg",
    "objectiveK": 0,
    "ks": [
      0
    ],
    "maxConfigs": 0
  }),
});
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/experiments/rag-automl",
    headers=headers,
    json={
    "projectId": "00000000-0000-0000-0000-000000000000",
    "name": "string",
    "searchSpace": {},
    "qrels": {},
    "runs": {},
    "objective": "ndcg",
    "objectiveK": 0,
    "ks": [
        0
    ],
    "maxConfigs": 0
},
)
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","searchSpace":{},"qrels":{},"runs":{},"objective":"ndcg","objectiveK":0,"ks":[0],"maxConfigs":0}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/experiments/rag-automl", 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