Validate Llm Scorer Log Record

POST /v2/scorers/llm/validate/log_record

Validate Llm Scorer Log Record

cURL

curl --request POST \
  --url https://api.galileo.ai/v2/scorers/llm/validate/log_record \
  --header 'Content-Type: application/json' \
  --header 'Galileo-API-Key: <api-key>' \
  --data '
{
  "query": "<string>",
  "response": "<string>",
  "chain_poll_template": {
    "template": "<string>",
    "metric_system_prompt": "<string>",
    "metric_description": "<string>",
    "value_field_name": "rating",
    "explanation_field_name": "explanation",
    "metric_few_shot_examples": [
      {
        "generation_prompt_and_response": "<string>",
        "evaluating_response": "<string>"
      }
    ],
    "response_schema": {}
  },
  "scorer_configuration": {
    "model_alias": "gpt-4.1-mini",
    "num_judges": 3,
    "output_type": "boolean",
    "scoreable_node_types": [
      "<string>"
    ],
    "cot_enabled": false,
    "ground_truth": false,
    "multimodal_capabilities": []
  },
  "user_prompt": "<string>",
  "starting_token": 0,
  "limit": 100,
  "previous_last_row_id": "<string>",
  "log_stream_id": "<string>",
  "experiment_id": "<string>",
  "metrics_testing_id": "<string>",
  "filters": [
    {
      "column_id": "<string>",
      "value": "<string>",
      "operator": "eq",
      "type": "id"
    }
  ],
  "filter_tree": {
    "filter": {
      "column_id": "<string>",
      "value": "<string>",
      "operator": "eq",
      "type": "id"
    }
  },
  "sort": {
    "column_id": "<string>",
    "ascending": true,
    "sort_type": "column"
  },
  "truncate_fields": false,
  "include_counts": false,
  "include_code_metric_metadata": false,
  "normalized_input": [
    {
      "text": "<string>",
      "type": "text"
    }
  ]
}
'

import requests

url = "https://api.galileo.ai/v2/scorers/llm/validate/log_record"

payload = {
    "query": "<string>",
    "response": "<string>",
    "chain_poll_template": {
        "template": "<string>",
        "metric_system_prompt": "<string>",
        "metric_description": "<string>",
        "value_field_name": "rating",
        "explanation_field_name": "explanation",
        "metric_few_shot_examples": [
            {
                "generation_prompt_and_response": "<string>",
                "evaluating_response": "<string>"
            }
        ],
        "response_schema": {}
    },
    "scorer_configuration": {
        "model_alias": "gpt-4.1-mini",
        "num_judges": 3,
        "output_type": "boolean",
        "scoreable_node_types": ["<string>"],
        "cot_enabled": False,
        "ground_truth": False,
        "multimodal_capabilities": []
    },
    "user_prompt": "<string>",
    "starting_token": 0,
    "limit": 100,
    "previous_last_row_id": "<string>",
    "log_stream_id": "<string>",
    "experiment_id": "<string>",
    "metrics_testing_id": "<string>",
    "filters": [
        {
            "column_id": "<string>",
            "value": "<string>",
            "operator": "eq",
            "type": "id"
        }
    ],
    "filter_tree": { "filter": {
            "column_id": "<string>",
            "value": "<string>",
            "operator": "eq",
            "type": "id"
        } },
    "sort": {
        "column_id": "<string>",
        "ascending": True,
        "sort_type": "column"
    },
    "truncate_fields": False,
    "include_counts": False,
    "include_code_metric_metadata": False,
    "normalized_input": [
        {
            "text": "<string>",
            "type": "text"
        }
    ]
}
headers = {
    "Galileo-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Galileo-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    query: '<string>',
    response: '<string>',
    chain_poll_template: {
      template: '<string>',
      metric_system_prompt: '<string>',
      metric_description: '<string>',
      value_field_name: 'rating',
      explanation_field_name: 'explanation',
      metric_few_shot_examples: [{generation_prompt_and_response: '<string>', evaluating_response: '<string>'}],
      response_schema: {}
    },
    scorer_configuration: {
      model_alias: 'gpt-4.1-mini',
      num_judges: 3,
      output_type: 'boolean',
      scoreable_node_types: ['<string>'],
      cot_enabled: false,
      ground_truth: false,
      multimodal_capabilities: []
    },
    user_prompt: '<string>',
    starting_token: 0,
    limit: 100,
    previous_last_row_id: '<string>',
    log_stream_id: '<string>',
    experiment_id: '<string>',
    metrics_testing_id: '<string>',
    filters: [{column_id: '<string>', value: '<string>', operator: 'eq', type: 'id'}],
    filter_tree: {filter: {column_id: '<string>', value: '<string>', operator: 'eq', type: 'id'}},
    sort: {column_id: '<string>', ascending: true, sort_type: 'column'},
    truncate_fields: false,
    include_counts: false,
    include_code_metric_metadata: false,
    normalized_input: [{text: '<string>', type: 'text'}]
  })
};

fetch('https://api.galileo.ai/v2/scorers/llm/validate/log_record', 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://api.galileo.ai/v2/scorers/llm/validate/log_record",
  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([
    'query' => '<string>',
    'response' => '<string>',
    'chain_poll_template' => [
        'template' => '<string>',
        'metric_system_prompt' => '<string>',
        'metric_description' => '<string>',
        'value_field_name' => 'rating',
        'explanation_field_name' => 'explanation',
        'metric_few_shot_examples' => [
                [
                                'generation_prompt_and_response' => '<string>',
                                'evaluating_response' => '<string>'
                ]
        ],
        'response_schema' => [
                
        ]
    ],
    'scorer_configuration' => [
        'model_alias' => 'gpt-4.1-mini',
        'num_judges' => 3,
        'output_type' => 'boolean',
        'scoreable_node_types' => [
                '<string>'
        ],
        'cot_enabled' => false,
        'ground_truth' => false,
        'multimodal_capabilities' => [
                
        ]
    ],
    'user_prompt' => '<string>',
    'starting_token' => 0,
    'limit' => 100,
    'previous_last_row_id' => '<string>',
    'log_stream_id' => '<string>',
    'experiment_id' => '<string>',
    'metrics_testing_id' => '<string>',
    'filters' => [
        [
                'column_id' => '<string>',
                'value' => '<string>',
                'operator' => 'eq',
                'type' => 'id'
        ]
    ],
    'filter_tree' => [
        'filter' => [
                'column_id' => '<string>',
                'value' => '<string>',
                'operator' => 'eq',
                'type' => 'id'
        ]
    ],
    'sort' => [
        'column_id' => '<string>',
        'ascending' => true,
        'sort_type' => 'column'
    ],
    'truncate_fields' => false,
    'include_counts' => false,
    'include_code_metric_metadata' => false,
    'normalized_input' => [
        [
                'text' => '<string>',
                'type' => 'text'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "Galileo-API-Key: <api-key>"
  ],
]);

$response = curl_exec($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://api.galileo.ai/v2/scorers/llm/validate/log_record"

	payload := strings.NewReader("{\n  \"query\": \"<string>\",\n  \"response\": \"<string>\",\n  \"chain_poll_template\": {\n    \"template\": \"<string>\",\n    \"metric_system_prompt\": \"<string>\",\n    \"metric_description\": \"<string>\",\n    \"value_field_name\": \"rating\",\n    \"explanation_field_name\": \"explanation\",\n    \"metric_few_shot_examples\": [\n      {\n        \"generation_prompt_and_response\": \"<string>\",\n        \"evaluating_response\": \"<string>\"\n      }\n    ],\n    \"response_schema\": {}\n  },\n  \"scorer_configuration\": {\n    \"model_alias\": \"gpt-4.1-mini\",\n    \"num_judges\": 3,\n    \"output_type\": \"boolean\",\n    \"scoreable_node_types\": [\n      \"<string>\"\n    ],\n    \"cot_enabled\": false,\n    \"ground_truth\": false,\n    \"multimodal_capabilities\": []\n  },\n  \"user_prompt\": \"<string>\",\n  \"starting_token\": 0,\n  \"limit\": 100,\n  \"previous_last_row_id\": \"<string>\",\n  \"log_stream_id\": \"<string>\",\n  \"experiment_id\": \"<string>\",\n  \"metrics_testing_id\": \"<string>\",\n  \"filters\": [\n    {\n      \"column_id\": \"<string>\",\n      \"value\": \"<string>\",\n      \"operator\": \"eq\",\n      \"type\": \"id\"\n    }\n  ],\n  \"filter_tree\": {\n    \"filter\": {\n      \"column_id\": \"<string>\",\n      \"value\": \"<string>\",\n      \"operator\": \"eq\",\n      \"type\": \"id\"\n    }\n  },\n  \"sort\": {\n    \"column_id\": \"<string>\",\n    \"ascending\": true,\n    \"sort_type\": \"column\"\n  },\n  \"truncate_fields\": false,\n  \"include_counts\": false,\n  \"include_code_metric_metadata\": false,\n  \"normalized_input\": [\n    {\n      \"text\": \"<string>\",\n      \"type\": \"text\"\n    }\n  ]\n}")

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

	req.Header.Add("Galileo-API-Key", "<api-key>")
	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://api.galileo.ai/v2/scorers/llm/validate/log_record")
  .header("Galileo-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"query\": \"<string>\",\n  \"response\": \"<string>\",\n  \"chain_poll_template\": {\n    \"template\": \"<string>\",\n    \"metric_system_prompt\": \"<string>\",\n    \"metric_description\": \"<string>\",\n    \"value_field_name\": \"rating\",\n    \"explanation_field_name\": \"explanation\",\n    \"metric_few_shot_examples\": [\n      {\n        \"generation_prompt_and_response\": \"<string>\",\n        \"evaluating_response\": \"<string>\"\n      }\n    ],\n    \"response_schema\": {}\n  },\n  \"scorer_configuration\": {\n    \"model_alias\": \"gpt-4.1-mini\",\n    \"num_judges\": 3,\n    \"output_type\": \"boolean\",\n    \"scoreable_node_types\": [\n      \"<string>\"\n    ],\n    \"cot_enabled\": false,\n    \"ground_truth\": false,\n    \"multimodal_capabilities\": []\n  },\n  \"user_prompt\": \"<string>\",\n  \"starting_token\": 0,\n  \"limit\": 100,\n  \"previous_last_row_id\": \"<string>\",\n  \"log_stream_id\": \"<string>\",\n  \"experiment_id\": \"<string>\",\n  \"metrics_testing_id\": \"<string>\",\n  \"filters\": [\n    {\n      \"column_id\": \"<string>\",\n      \"value\": \"<string>\",\n      \"operator\": \"eq\",\n      \"type\": \"id\"\n    }\n  ],\n  \"filter_tree\": {\n    \"filter\": {\n      \"column_id\": \"<string>\",\n      \"value\": \"<string>\",\n      \"operator\": \"eq\",\n      \"type\": \"id\"\n    }\n  },\n  \"sort\": {\n    \"column_id\": \"<string>\",\n    \"ascending\": true,\n    \"sort_type\": \"column\"\n  },\n  \"truncate_fields\": false,\n  \"include_counts\": false,\n  \"include_code_metric_metadata\": false,\n  \"normalized_input\": [\n    {\n      \"text\": \"<string>\",\n      \"type\": \"text\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.galileo.ai/v2/scorers/llm/validate/log_record")

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

request = Net::HTTP::Post.new(url)
request["Galileo-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"query\": \"<string>\",\n  \"response\": \"<string>\",\n  \"chain_poll_template\": {\n    \"template\": \"<string>\",\n    \"metric_system_prompt\": \"<string>\",\n    \"metric_description\": \"<string>\",\n    \"value_field_name\": \"rating\",\n    \"explanation_field_name\": \"explanation\",\n    \"metric_few_shot_examples\": [\n      {\n        \"generation_prompt_and_response\": \"<string>\",\n        \"evaluating_response\": \"<string>\"\n      }\n    ],\n    \"response_schema\": {}\n  },\n  \"scorer_configuration\": {\n    \"model_alias\": \"gpt-4.1-mini\",\n    \"num_judges\": 3,\n    \"output_type\": \"boolean\",\n    \"scoreable_node_types\": [\n      \"<string>\"\n    ],\n    \"cot_enabled\": false,\n    \"ground_truth\": false,\n    \"multimodal_capabilities\": []\n  },\n  \"user_prompt\": \"<string>\",\n  \"starting_token\": 0,\n  \"limit\": 100,\n  \"previous_last_row_id\": \"<string>\",\n  \"log_stream_id\": \"<string>\",\n  \"experiment_id\": \"<string>\",\n  \"metrics_testing_id\": \"<string>\",\n  \"filters\": [\n    {\n      \"column_id\": \"<string>\",\n      \"value\": \"<string>\",\n      \"operator\": \"eq\",\n      \"type\": \"id\"\n    }\n  ],\n  \"filter_tree\": {\n    \"filter\": {\n      \"column_id\": \"<string>\",\n      \"value\": \"<string>\",\n      \"operator\": \"eq\",\n      \"type\": \"id\"\n    }\n  },\n  \"sort\": {\n    \"column_id\": \"<string>\",\n    \"ascending\": true,\n    \"sort_type\": \"column\"\n  },\n  \"truncate_fields\": false,\n  \"include_counts\": false,\n  \"include_code_metric_metadata\": false,\n  \"normalized_input\": [\n    {\n      \"text\": \"<string>\",\n      \"type\": \"text\"\n    }\n  ]\n}"

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

200

{
  "metrics_experiment_id": "<string>",
  "project_id": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

ClassicAPIKeyHeaderAPIKeyHeaderOAuth2PasswordBearerHTTPBasic

Galileo-API-Key · string · header · required

Body

application/json

Request to validate a new LLM scorer based on a log record. This is used to create a new experiment with the copied log records to store the metric testing results.

query · string · required

response · string · required

chain_poll_template · ChainPollTemplate · object · required

Template for a chainpoll metric prompt, containing all the info necessary to send a chainpoll prompt.

Show child attributes

scorer_configuration · GeneratedScorerConfiguration · object · required

Show child attributes

user_prompt · string · required

starting_token · integer · default: 0

limit · integer · default: 100

previous_last_row_id · string<uuid4> | null

log_stream_id · string<uuid4> | null

Log stream id associated with the traces.

experiment_id · string<uuid4> | null

Experiment id associated with the traces.

metrics_testing_id · string<uuid4> | null

Metrics testing id associated with the traces.

filters · (LogRecordsIDFilter · object | LogRecordsDateFilter · object | LogRecordsNumberFilter · object | LogRecordsBooleanFilter · object | LogRecordsCollectionFilter · object | LogRecordsTextFilter · object | LogRecordsFullyAnnotatedFilter · object)[]

LogRecordsIDFilter

LogRecordsDateFilter

LogRecordsNumberFilter

LogRecordsBooleanFilter

LogRecordsCollectionFilter

LogRecordsTextFilter

LogRecordsFullyAnnotatedFilter

Show child attributes

filter_tree · FilterLeaf[Annotated[Union[LogRecordsIDFilter, LogRecordsDateFilter, LogRecordsNumberFilter, LogRecordsBooleanFilter, LogRecordsCollectionFilter, LogRecordsTextFilter, LogRecordsFullyAnnotatedFilter], FieldInfo(annotation=NoneType, required=True, discriminator='type')]] · object

FilterLeaf[Annotated[Union[LogRecordsIDFilter, LogRecordsDateFilter, LogRecordsNumberFilter, LogRecordsBooleanFilter, LogRecordsCollectionFilter, LogRecordsTextFilter, LogRecordsFullyAnnotatedFilter], FieldInfo(annotation=NoneType, required=True, discriminator='type')]]

AndNode[Annotated[Union[LogRecordsIDFilter, LogRecordsDateFilter, LogRecordsNumberFilter, LogRecordsBooleanFilter, LogRecordsCollectionFilter, LogRecordsTextFilter, LogRecordsFullyAnnotatedFilter], FieldInfo(annotation=NoneType, required=True, discriminator='type')]]

OrNode[Annotated[Union[LogRecordsIDFilter, LogRecordsDateFilter, LogRecordsNumberFilter, LogRecordsBooleanFilter, LogRecordsCollectionFilter, LogRecordsTextFilter, LogRecordsFullyAnnotatedFilter], FieldInfo(annotation=NoneType, required=True, discriminator='type')]]

NotNode[Annotated[Union[LogRecordsIDFilter, LogRecordsDateFilter, LogRecordsNumberFilter, LogRecordsBooleanFilter, LogRecordsCollectionFilter, LogRecordsTextFilter, LogRecordsFullyAnnotatedFilter], FieldInfo(annotation=NoneType, required=True, discriminator='type')]]

Show child attributes

sort · LogRecordsSortClause · object | null

Sort for the query. Defaults to native sort (created_at, id descending).

Show child attributes

truncate_fields · boolean · default: false

include_counts · boolean · default: false

If True, include computed child counts (e.g., num_traces for sessions, num_spans for traces).

include_code_metric_metadata · boolean · default: false

If True, include per-row scorer metadata (the dict returned alongside the score by code-based scorers via the (score, metadata) tuple-return contract) on each MetricSuccess in the response. Off by default to keep payloads small for callers that don't need it.

normalized_input · (TextContentPart · object | FileContentPart · object)[] | null

Optional multimodal content parts. When set, replaces the text-only query/response formatting in the validation job so that file content is passed through to the LLM.

A text segment within a message.

TextContentPart

FileContentPart

Show child attributes

Response

200

application/json

Successful Response

metrics_experiment_id · string<uuid4> · required

project_id · string<uuid4> · required