Create experiments experiments

curl --request POST \
  --url https://evalgate.com/api/experiments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "evaluationId": 123,
  "idempotencyKey": "<string>",
  "baselineVariantKey": "<string>",
  "variants": [
    {
      "name": "<string>",
      "key": "<string>",
      "provider": "<string>",
      "model": "<string>",
      "systemPrompt": "<string>",
      "tools": {},
      "promptVersionId": "<string>",
      "messages": [
        {
          "id": "<string>",
          "role": "user",
          "content": "<string>",
          "name": "<string>"
        }
      ],
      "routingProfileId": "<string>",
      "parameters": {},
      "policies": {},
      "expectedPromptContentHash": "<string>",
      "routingStrategy": {},
      "scorerConfigIds": [
        123
      ],
      "calibrationMappingIds": [
        "<string>"
      ]
    }
  ],
  "description": "<string>",
  "environment": "dev",
  "datasetVersionId": "<string>",
  "seed": 123,
  "winnerPolicy": {
    "confidenceLevel": 123,
    "minimumPassRateDelta": 123,
    "maximumCostIncreasePercent": 123,
    "maximumP95LatencyIncreasePercent": 123,
    "allowIncomparableJudges": false,
    "allowRegressions": false,
    "minimumSampleSize": 123,
    "requireConfidenceInterval": true
  },
  "expectedDatasetContentHash": "<string>",
  "runnerVersion": "<string>",
  "codeVersion": "<string>",
  "policies": {}
}
'

import requests

url = "https://evalgate.com/api/experiments"

payload = {
    "name": "<string>",
    "evaluationId": 123,
    "idempotencyKey": "<string>",
    "baselineVariantKey": "<string>",
    "variants": [
        {
            "name": "<string>",
            "key": "<string>",
            "provider": "<string>",
            "model": "<string>",
            "systemPrompt": "<string>",
            "tools": {},
            "promptVersionId": "<string>",
            "messages": [
                {
                    "id": "<string>",
                    "role": "user",
                    "content": "<string>",
                    "name": "<string>"
                }
            ],
            "routingProfileId": "<string>",
            "parameters": {},
            "policies": {},
            "expectedPromptContentHash": "<string>",
            "routingStrategy": {},
            "scorerConfigIds": [123],
            "calibrationMappingIds": ["<string>"]
        }
    ],
    "description": "<string>",
    "environment": "dev",
    "datasetVersionId": "<string>",
    "seed": 123,
    "winnerPolicy": {
        "confidenceLevel": 123,
        "minimumPassRateDelta": 123,
        "maximumCostIncreasePercent": 123,
        "maximumP95LatencyIncreasePercent": 123,
        "allowIncomparableJudges": False,
        "allowRegressions": False,
        "minimumSampleSize": 123,
        "requireConfidenceInterval": True
    },
    "expectedDatasetContentHash": "<string>",
    "runnerVersion": "<string>",
    "codeVersion": "<string>",
    "policies": {}
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    evaluationId: 123,
    idempotencyKey: '<string>',
    baselineVariantKey: '<string>',
    variants: [
      {
        name: '<string>',
        key: '<string>',
        provider: '<string>',
        model: '<string>',
        systemPrompt: '<string>',
        tools: {},
        promptVersionId: '<string>',
        messages: [{id: '<string>', role: 'user', content: '<string>', name: '<string>'}],
        routingProfileId: '<string>',
        parameters: {},
        policies: {},
        expectedPromptContentHash: '<string>',
        routingStrategy: {},
        scorerConfigIds: [123],
        calibrationMappingIds: ['<string>']
      }
    ],
    description: '<string>',
    environment: 'dev',
    datasetVersionId: '<string>',
    seed: 123,
    winnerPolicy: {
      confidenceLevel: 123,
      minimumPassRateDelta: 123,
      maximumCostIncreasePercent: 123,
      maximumP95LatencyIncreasePercent: 123,
      allowIncomparableJudges: false,
      allowRegressions: false,
      minimumSampleSize: 123,
      requireConfidenceInterval: true
    },
    expectedDatasetContentHash: '<string>',
    runnerVersion: '<string>',
    codeVersion: '<string>',
    policies: {}
  })
};

fetch('https://evalgate.com/api/experiments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://evalgate.com/api/experiments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'evaluationId' => 123,
    'idempotencyKey' => '<string>',
    'baselineVariantKey' => '<string>',
    'variants' => [
        [
                'name' => '<string>',
                'key' => '<string>',
                'provider' => '<string>',
                'model' => '<string>',
                'systemPrompt' => '<string>',
                'tools' => [
                                
                ],
                'promptVersionId' => '<string>',
                'messages' => [
                                [
                                                                'id' => '<string>',
                                                                'role' => 'user',
                                                                'content' => '<string>',
                                                                'name' => '<string>'
                                ]
                ],
                'routingProfileId' => '<string>',
                'parameters' => [
                                
                ],
                'policies' => [
                                
                ],
                'expectedPromptContentHash' => '<string>',
                'routingStrategy' => [
                                
                ],
                'scorerConfigIds' => [
                                123
                ],
                'calibrationMappingIds' => [
                                '<string>'
                ]
        ]
    ],
    'description' => '<string>',
    'environment' => 'dev',
    'datasetVersionId' => '<string>',
    'seed' => 123,
    'winnerPolicy' => [
        'confidenceLevel' => 123,
        'minimumPassRateDelta' => 123,
        'maximumCostIncreasePercent' => 123,
        'maximumP95LatencyIncreasePercent' => 123,
        'allowIncomparableJudges' => false,
        'allowRegressions' => false,
        'minimumSampleSize' => 123,
        'requireConfidenceInterval' => true
    ],
    'expectedDatasetContentHash' => '<string>',
    'runnerVersion' => '<string>',
    'codeVersion' => '<string>',
    'policies' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://evalgate.com/api/experiments"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"evaluationId\": 123,\n  \"idempotencyKey\": \"<string>\",\n  \"baselineVariantKey\": \"<string>\",\n  \"variants\": [\n    {\n      \"name\": \"<string>\",\n      \"key\": \"<string>\",\n      \"provider\": \"<string>\",\n      \"model\": \"<string>\",\n      \"systemPrompt\": \"<string>\",\n      \"tools\": {},\n      \"promptVersionId\": \"<string>\",\n      \"messages\": [\n        {\n          \"id\": \"<string>\",\n          \"role\": \"user\",\n          \"content\": \"<string>\",\n          \"name\": \"<string>\"\n        }\n      ],\n      \"routingProfileId\": \"<string>\",\n      \"parameters\": {},\n      \"policies\": {},\n      \"expectedPromptContentHash\": \"<string>\",\n      \"routingStrategy\": {},\n      \"scorerConfigIds\": [\n        123\n      ],\n      \"calibrationMappingIds\": [\n        \"<string>\"\n      ]\n    }\n  ],\n  \"description\": \"<string>\",\n  \"environment\": \"dev\",\n  \"datasetVersionId\": \"<string>\",\n  \"seed\": 123,\n  \"winnerPolicy\": {\n    \"confidenceLevel\": 123,\n    \"minimumPassRateDelta\": 123,\n    \"maximumCostIncreasePercent\": 123,\n    \"maximumP95LatencyIncreasePercent\": 123,\n    \"allowIncomparableJudges\": false,\n    \"allowRegressions\": false,\n    \"minimumSampleSize\": 123,\n    \"requireConfidenceInterval\": true\n  },\n  \"expectedDatasetContentHash\": \"<string>\",\n  \"runnerVersion\": \"<string>\",\n  \"codeVersion\": \"<string>\",\n  \"policies\": {}\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://evalgate.com/api/experiments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"evaluationId\": 123,\n  \"idempotencyKey\": \"<string>\",\n  \"baselineVariantKey\": \"<string>\",\n  \"variants\": [\n    {\n      \"name\": \"<string>\",\n      \"key\": \"<string>\",\n      \"provider\": \"<string>\",\n      \"model\": \"<string>\",\n      \"systemPrompt\": \"<string>\",\n      \"tools\": {},\n      \"promptVersionId\": \"<string>\",\n      \"messages\": [\n        {\n          \"id\": \"<string>\",\n          \"role\": \"user\",\n          \"content\": \"<string>\",\n          \"name\": \"<string>\"\n        }\n      ],\n      \"routingProfileId\": \"<string>\",\n      \"parameters\": {},\n      \"policies\": {},\n      \"expectedPromptContentHash\": \"<string>\",\n      \"routingStrategy\": {},\n      \"scorerConfigIds\": [\n        123\n      ],\n      \"calibrationMappingIds\": [\n        \"<string>\"\n      ]\n    }\n  ],\n  \"description\": \"<string>\",\n  \"environment\": \"dev\",\n  \"datasetVersionId\": \"<string>\",\n  \"seed\": 123,\n  \"winnerPolicy\": {\n    \"confidenceLevel\": 123,\n    \"minimumPassRateDelta\": 123,\n    \"maximumCostIncreasePercent\": 123,\n    \"maximumP95LatencyIncreasePercent\": 123,\n    \"allowIncomparableJudges\": false,\n    \"allowRegressions\": false,\n    \"minimumSampleSize\": 123,\n    \"requireConfidenceInterval\": true\n  },\n  \"expectedDatasetContentHash\": \"<string>\",\n  \"runnerVersion\": \"<string>\",\n  \"codeVersion\": \"<string>\",\n  \"policies\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://evalgate.com/api/experiments")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"evaluationId\": 123,\n  \"idempotencyKey\": \"<string>\",\n  \"baselineVariantKey\": \"<string>\",\n  \"variants\": [\n    {\n      \"name\": \"<string>\",\n      \"key\": \"<string>\",\n      \"provider\": \"<string>\",\n      \"model\": \"<string>\",\n      \"systemPrompt\": \"<string>\",\n      \"tools\": {},\n      \"promptVersionId\": \"<string>\",\n      \"messages\": [\n        {\n          \"id\": \"<string>\",\n          \"role\": \"user\",\n          \"content\": \"<string>\",\n          \"name\": \"<string>\"\n        }\n      ],\n      \"routingProfileId\": \"<string>\",\n      \"parameters\": {},\n      \"policies\": {},\n      \"expectedPromptContentHash\": \"<string>\",\n      \"routingStrategy\": {},\n      \"scorerConfigIds\": [\n        123\n      ],\n      \"calibrationMappingIds\": [\n        \"<string>\"\n      ]\n    }\n  ],\n  \"description\": \"<string>\",\n  \"environment\": \"dev\",\n  \"datasetVersionId\": \"<string>\",\n  \"seed\": 123,\n  \"winnerPolicy\": {\n    \"confidenceLevel\": 123,\n    \"minimumPassRateDelta\": 123,\n    \"maximumCostIncreasePercent\": 123,\n    \"maximumP95LatencyIncreasePercent\": 123,\n    \"allowIncomparableJudges\": false,\n    \"allowRegressions\": false,\n    \"minimumSampleSize\": 123,\n    \"requireConfidenceInterval\": true\n  },\n  \"expectedDatasetContentHash\": \"<string>\",\n  \"runnerVersion\": \"<string>\",\n  \"codeVersion\": \"<string>\",\n  \"policies\": {}\n}"

response = http.request(request)
puts response.read_body

{
  "idempotentReplay": true,
  "id": "<string>",
  "organizationId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "evaluationId": 123,
  "name": "<string>",
  "description": "<string>",
  "status": "<string>",
  "baselineVariantKey": "<string>",
  "datasetVersionId": "<string>",
  "snapshotHash": "<string>",
  "snapshotJson": {
    "schemaVersion": 1,
    "snapshotHashVersion": "sha256-canonical-v1",
    "name": "<string>",
    "description": "<string>",
    "evaluationId": 123,
    "environment": "dev",
    "seed": 123,
    "code": {
      "runnerVersion": "<string>",
      "codeVersion": "<string>",
      "schemaVersion": "<string>"
    },
    "evaluation": {
      "type": "<string>",
      "executionSettings": {},
      "modelSettings": {},
      "customMetrics": {},
      "executorType": "<string>",
      "executorConfig": {}
    },
    "dataset": {
      "id": "<string>",
      "versionId": "<string>",
      "contentHash": "<string>",
      "schema": {},
      "rows": [
        {
          "id": 123,
          "name": "<string>",
          "input": "<string>",
          "expectedOutput": "<string>",
          "metadata": true,
          "lifecycleState": "<string>",
          "originType": "<string>",
          "datasetId": "<string>",
          "datasetVersionId": "<string>",
          "datasetRowId": "<string>",
          "datasetRowContentHash": "<string>",
          "inputHash": "<string>",
          "lastLifecycleTransitionAt": "<string>",
          "archivedAt": "<string>",
          "supersededById": 123,
          "supersededAt": "<string>",
          "supersessionReason": "<string>",
          "createdAt": "<string>"
        }
      ],
      "datasetHubRows": [
        {
          "id": "<string>",
          "ordinal": 123,
          "contentHash": "<string>",
          "payload": {}
        }
      ]
    },
    "baselineVariantKey": "<string>",
    "variants": [
      {
        "key": "<string>",
        "ordinal": 123,
        "name": "<string>",
        "prompt": {
          "versionId": "<string>",
          "artifactId": 123,
          "contentHash": "<string>",
          "payload": {},
          "messages": [
            {
              "id": "<string>",
              "role": "user",
              "content": "<string>",
              "name": "<string>"
            }
          ],
          "systemPrompt": "<string>"
        },
        "routing": {
          "profileId": "<string>",
          "provider": "<string>",
          "model": "<string>",
          "strategy": {}
        },
        "parameters": {},
        "tools": {},
        "scorers": [
          {
            "id": 123,
            "name": "<string>",
            "model": "<string>",
            "promptTemplate": "<string>",
            "promptTemplateHash": "<string>",
            "criteria": true,
            "settings": true,
            "criteriaList": true
          }
        ],
        "calibrationMappings": [
          {
            "mappingId": "<string>",
            "calibrationRunId": "<string>",
            "method": "percentile",
            "scoreScaleVersion": "<string>",
            "mapping": {},
            "calibratedJudgeConfigHash": "<string>",
            "calibrationSetId": "<string>",
            "mappingVersionId": "<string>",
            "calibrationSetVersionId": "<string>"
          }
        ],
        "policies": {},
        "configurationHash": "<string>"
      }
    ],
    "policies": {},
    "createdFrom": {
      "surface": "playground",
      "playgroundId": 123
    },
    "decisionPolicy": {
      "schemaVersion": "evalgate.experiment-winner-policy.v2",
      "minimumPassRateDelta": 123,
      "maximumCostIncreasePercent": 123,
      "maximumP95LatencyIncreasePercent": 123,
      "allowIncomparableJudges": false,
      "allowRegressions": true,
      "minimumSampleSize": 123,
      "confidenceLevel": 123,
      "requireConfidenceInterval": true,
      "statisticalMethod": "paired-bonferroni-wilson-v1"
    }
  },
  "createRequestHash": "<string>",
  "winnerPolicy": {
    "minimumPassRateDelta": 123,
    "maximumCostIncreasePercent": 123,
    "maximumP95LatencyIncreasePercent": 123,
    "allowIncomparableJudges": false,
    "allowRegressions": false,
    "minimumSampleSize": 123,
    "confidenceLevel": 123,
    "requireConfidenceInterval": false
  },
  "createIdempotencyKey": "<string>",
  "createdBy": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "completedAt": "2023-11-07T05:31:56Z"
}

{
  "idempotentReplay": true,
  "id": "<string>",
  "organizationId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "evaluationId": 123,
  "name": "<string>",
  "description": "<string>",
  "status": "<string>",
  "baselineVariantKey": "<string>",
  "datasetVersionId": "<string>",
  "snapshotHash": "<string>",
  "snapshotJson": {
    "schemaVersion": 1,
    "snapshotHashVersion": "sha256-canonical-v1",
    "name": "<string>",
    "description": "<string>",
    "evaluationId": 123,
    "environment": "dev",
    "seed": 123,
    "code": {
      "runnerVersion": "<string>",
      "codeVersion": "<string>",
      "schemaVersion": "<string>"
    },
    "evaluation": {
      "type": "<string>",
      "executionSettings": {},
      "modelSettings": {},
      "customMetrics": {},
      "executorType": "<string>",
      "executorConfig": {}
    },
    "dataset": {
      "id": "<string>",
      "versionId": "<string>",
      "contentHash": "<string>",
      "schema": {},
      "rows": [
        {
          "id": 123,
          "name": "<string>",
          "input": "<string>",
          "expectedOutput": "<string>",
          "metadata": true,
          "lifecycleState": "<string>",
          "originType": "<string>",
          "datasetId": "<string>",
          "datasetVersionId": "<string>",
          "datasetRowId": "<string>",
          "datasetRowContentHash": "<string>",
          "inputHash": "<string>",
          "lastLifecycleTransitionAt": "<string>",
          "archivedAt": "<string>",
          "supersededById": 123,
          "supersededAt": "<string>",
          "supersessionReason": "<string>",
          "createdAt": "<string>"
        }
      ],
      "datasetHubRows": [
        {
          "id": "<string>",
          "ordinal": 123,
          "contentHash": "<string>",
          "payload": {}
        }
      ]
    },
    "baselineVariantKey": "<string>",
    "variants": [
      {
        "key": "<string>",
        "ordinal": 123,
        "name": "<string>",
        "prompt": {
          "versionId": "<string>",
          "artifactId": 123,
          "contentHash": "<string>",
          "payload": {},
          "messages": [
            {
              "id": "<string>",
              "role": "user",
              "content": "<string>",
              "name": "<string>"
            }
          ],
          "systemPrompt": "<string>"
        },
        "routing": {
          "profileId": "<string>",
          "provider": "<string>",
          "model": "<string>",
          "strategy": {}
        },
        "parameters": {},
        "tools": {},
        "scorers": [
          {
            "id": 123,
            "name": "<string>",
            "model": "<string>",
            "promptTemplate": "<string>",
            "promptTemplateHash": "<string>",
            "criteria": true,
            "settings": true,
            "criteriaList": true
          }
        ],
        "calibrationMappings": [
          {
            "mappingId": "<string>",
            "calibrationRunId": "<string>",
            "method": "percentile",
            "scoreScaleVersion": "<string>",
            "mapping": {},
            "calibratedJudgeConfigHash": "<string>",
            "calibrationSetId": "<string>",
            "mappingVersionId": "<string>",
            "calibrationSetVersionId": "<string>"
          }
        ],
        "policies": {},
        "configurationHash": "<string>"
      }
    ],
    "policies": {},
    "createdFrom": {
      "surface": "playground",
      "playgroundId": 123
    },
    "decisionPolicy": {
      "schemaVersion": "evalgate.experiment-winner-policy.v2",
      "minimumPassRateDelta": 123,
      "maximumCostIncreasePercent": 123,
      "maximumP95LatencyIncreasePercent": 123,
      "allowIncomparableJudges": false,
      "allowRegressions": true,
      "minimumSampleSize": 123,
      "confidenceLevel": 123,
      "requireConfidenceInterval": true,
      "statisticalMethod": "paired-bonferroni-wilson-v1"
    }
  },
  "createRequestHash": "<string>",
  "winnerPolicy": {
    "minimumPassRateDelta": 123,
    "maximumCostIncreasePercent": 123,
    "maximumP95LatencyIncreasePercent": 123,
    "allowIncomparableJudges": false,
    "allowRegressions": false,
    "minimumSampleSize": 123,
    "confidenceLevel": 123,
    "requireConfidenceInterval": false
  },
  "createIdempotencyKey": "<string>",
  "createdBy": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "completedAt": "2023-11-07T05:31:56Z"
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}

{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "<string>",
    "details": "<unknown>",
    "requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "redaction": {
      "applied": true,
      "fieldCount": 1,
      "secretCount": 1
    }
  }
}