Eval Results Query

Read grouped evaluation result rows for one or more evaluations.

POST /v2/{entity}/{project}/eval_results/query

Eval Results Query

cURL

curl --request POST \
  --url https://api.example.com/v2/{entity}/{project}/eval_results/query \
  --header 'Content-Type: application/json' \
  --data '
{
  "evaluation_call_ids": [
    "<string>"
  ],
  "evaluation_run_ids": [
    "<string>"
  ],
  "require_intersection": false,
  "include_raw_data_rows": false,
  "resolve_row_refs": false,
  "include_rows": true,
  "include_summary": false,
  "summary_require_intersection": true,
  "include_predict_and_score_children": true,
  "sort_by": [
    {
      "field": "<string>",
      "evaluation_call_id": "<string>",
      "mode": "value"
    }
  ],
  "filters": [
    {
      "query": {
        "$expr": {
          "$and": [
            {
              "$literal": "<string>"
            }
          ]
        }
      },
      "evaluation_call_id": "<string>"
    }
  ],
  "filter_logic_operator": "or",
  "limit": 123,
  "offset": 0
}
'

import requests

url = "https://api.example.com/v2/{entity}/{project}/eval_results/query"

payload = {
    "evaluation_call_ids": ["<string>"],
    "evaluation_run_ids": ["<string>"],
    "require_intersection": False,
    "include_raw_data_rows": False,
    "resolve_row_refs": False,
    "include_rows": True,
    "include_summary": False,
    "summary_require_intersection": True,
    "include_predict_and_score_children": True,
    "sort_by": [
        {
            "field": "<string>",
            "evaluation_call_id": "<string>",
            "mode": "value"
        }
    ],
    "filters": [
        {
            "query": { "$expr": { "$and": [{ "$literal": "<string>" }] } },
            "evaluation_call_id": "<string>"
        }
    ],
    "filter_logic_operator": "or",
    "limit": 123,
    "offset": 0
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    evaluation_call_ids: ['<string>'],
    evaluation_run_ids: ['<string>'],
    require_intersection: false,
    include_raw_data_rows: false,
    resolve_row_refs: false,
    include_rows: true,
    include_summary: false,
    summary_require_intersection: true,
    include_predict_and_score_children: true,
    sort_by: [{field: '<string>', evaluation_call_id: '<string>', mode: 'value'}],
    filters: [
      {
        query: {$expr: {$and: [{$literal: '<string>'}]}},
        evaluation_call_id: '<string>'
      }
    ],
    filter_logic_operator: 'or',
    limit: 123,
    offset: 0
  })
};

fetch('https://api.example.com/v2/{entity}/{project}/eval_results/query', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/v2/{entity}/{project}/eval_results/query",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'evaluation_call_ids' => [
        '<string>'
    ],
    'evaluation_run_ids' => [
        '<string>'
    ],
    'require_intersection' => false,
    'include_raw_data_rows' => false,
    'resolve_row_refs' => false,
    'include_rows' => true,
    'include_summary' => false,
    'summary_require_intersection' => true,
    'include_predict_and_score_children' => true,
    'sort_by' => [
        [
                'field' => '<string>',
                'evaluation_call_id' => '<string>',
                'mode' => 'value'
        ]
    ],
    'filters' => [
        [
                'query' => [
                                '$expr' => [
                                                                '$and' => [
                                                                                                                                [
                                                                                                                                                                                                                                                                '$literal' => '<string>'
                                                                                                                                ]
                                                                ]
                                ]
                ],
                'evaluation_call_id' => '<string>'
        ]
    ],
    'filter_logic_operator' => 'or',
    'limit' => 123,
    'offset' => 0
  ]),
  CURLOPT_HTTPHEADER => [
    "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://api.example.com/v2/{entity}/{project}/eval_results/query"

	payload := strings.NewReader("{\n  \"evaluation_call_ids\": [\n    \"<string>\"\n  ],\n  \"evaluation_run_ids\": [\n    \"<string>\"\n  ],\n  \"require_intersection\": false,\n  \"include_raw_data_rows\": false,\n  \"resolve_row_refs\": false,\n  \"include_rows\": true,\n  \"include_summary\": false,\n  \"summary_require_intersection\": true,\n  \"include_predict_and_score_children\": true,\n  \"sort_by\": [\n    {\n      \"field\": \"<string>\",\n      \"evaluation_call_id\": \"<string>\",\n      \"mode\": \"value\"\n    }\n  ],\n  \"filters\": [\n    {\n      \"query\": {\n        \"$expr\": {\n          \"$and\": [\n            {\n              \"$literal\": \"<string>\"\n            }\n          ]\n        }\n      },\n      \"evaluation_call_id\": \"<string>\"\n    }\n  ],\n  \"filter_logic_operator\": \"or\",\n  \"limit\": 123,\n  \"offset\": 0\n}")

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

	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.example.com/v2/{entity}/{project}/eval_results/query")
  .header("Content-Type", "application/json")
  .body("{\n  \"evaluation_call_ids\": [\n    \"<string>\"\n  ],\n  \"evaluation_run_ids\": [\n    \"<string>\"\n  ],\n  \"require_intersection\": false,\n  \"include_raw_data_rows\": false,\n  \"resolve_row_refs\": false,\n  \"include_rows\": true,\n  \"include_summary\": false,\n  \"summary_require_intersection\": true,\n  \"include_predict_and_score_children\": true,\n  \"sort_by\": [\n    {\n      \"field\": \"<string>\",\n      \"evaluation_call_id\": \"<string>\",\n      \"mode\": \"value\"\n    }\n  ],\n  \"filters\": [\n    {\n      \"query\": {\n        \"$expr\": {\n          \"$and\": [\n            {\n              \"$literal\": \"<string>\"\n            }\n          ]\n        }\n      },\n      \"evaluation_call_id\": \"<string>\"\n    }\n  ],\n  \"filter_logic_operator\": \"or\",\n  \"limit\": 123,\n  \"offset\": 0\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v2/{entity}/{project}/eval_results/query")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"evaluation_call_ids\": [\n    \"<string>\"\n  ],\n  \"evaluation_run_ids\": [\n    \"<string>\"\n  ],\n  \"require_intersection\": false,\n  \"include_raw_data_rows\": false,\n  \"resolve_row_refs\": false,\n  \"include_rows\": true,\n  \"include_summary\": false,\n  \"summary_require_intersection\": true,\n  \"include_predict_and_score_children\": true,\n  \"sort_by\": [\n    {\n      \"field\": \"<string>\",\n      \"evaluation_call_id\": \"<string>\",\n      \"mode\": \"value\"\n    }\n  ],\n  \"filters\": [\n    {\n      \"query\": {\n        \"$expr\": {\n          \"$and\": [\n            {\n              \"$literal\": \"<string>\"\n            }\n          ]\n        }\n      },\n      \"evaluation_call_id\": \"<string>\"\n    }\n  ],\n  \"filter_logic_operator\": \"or\",\n  \"limit\": 123,\n  \"offset\": 0\n}"

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

200

{
  "rows": [
    {
      "row_digest": "<string>",
      "raw_data_row": null,
      "evaluations": [
        {
          "evaluation_call_id": "<string>",
          "trials": [
            {
              "predict_and_score_call_id": "<string>",
              "predict_call_id": "<string>",
              "model_output": null,
              "scores": {},
              "model_latency_seconds": 123,
              "total_tokens": 123,
              "scorer_call_ids": {},
              "genai_span_ref": [
                {
                  "trace_id": "<string>",
                  "span_id": "<string>"
                }
              ]
            }
          ]
        }
      ]
    }
  ],
  "total_rows": 123,
  "summary": {
    "row_count": 0,
    "evaluations": [
      {
        "evaluation_call_id": "<string>",
        "trial_count": 0,
        "scorer_stats": [
          {
            "scorer_key": "<string>",
            "path": "<string>",
            "trial_count": 0,
            "numeric_count": 0,
            "numeric_mean": 123,
            "pass_true_count": 0,
            "pass_known_count": 0,
            "pass_rate": 123,
            "pass_signal_coverage": 123
          }
        ],
        "predict_total_tokens": 123,
        "evaluation_ref": "<string>",
        "model_ref": "<string>",
        "display_name": "<string>",
        "trace_id": "<string>",
        "started_at": "<string>"
      }
    ]
  },
  "warnings": [
    "<string>"
  ]
}

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

Path Parameters

entity · string · required

project · string · required

Body

application/json

evaluation_call_ids · string[] | null

Evaluation root call IDs to include.

evaluation_run_ids · string[] | null

Alias for evaluation call IDs from the Evaluation Runs API.

require_intersection · boolean · default: false

When true, only include rows present in all requested evaluations.

include_raw_data_rows · boolean · default: false

When true, populate raw_data_row on each result row. Inline rows are returned as their dict value; dataset-referenced rows are returned as the ref string unless resolve_row_refs is also true.

resolve_row_refs · boolean · default: false

When true (requires include_raw_data_rows=True), resolve dataset-row reference strings to actual row data via a table lookup. When false, dataset-row refs are returned as-is.

include_rows · boolean · default: true

When true, include grouped row/trial data in rows and compute total_rows for the requested row-level view.

include_summary · boolean · default: false

When true, include aggregated scorer/evaluation summary data in summary.

summary_require_intersection · boolean | null

Optional intersection behavior for the summary section. When null, the value of require_intersection is used.

include_predict_and_score_children · boolean · default: true

When true (default), fetch child calls (predict/score) of each predict_and_score call to populate predict_call_id, scorer_call_ids, and more precise latency/token data. When false, these fields are derived from the predict_and_score call itself (predict_call_id and scorer_call_ids will be null/empty).

sort_by · EvalResultsSortBy · object[] | null

Sort specification for result rows. Supported field prefixes: scores., inputs., outputs.. When null, rows are sorted by row_digest ASC.

Show child attributes

filters · EvalResultsFilter · object[] | null

Filters applied to grouped rows. Multiple filters are AND'd together.

Show child attributes

filter_logic_operator · enum<string> · default: or

How to combine filters across evaluations: 'and' (Match All - row must match in ALL evals) or 'or' (Match Any - row must match in ANY eval). Defaults to 'or' (Match Any).

Available options: and, or

limit · integer | null

Optional row-level page size applied after grouping and intersection.

offset · integer · default: 0

Optional row-level page offset applied after grouping and intersection.

Response

200

application/json

Successful Response

rows · EvalResultsRow · object[] · required

Show child attributes

total_rows · integer · required

summary · EvalResultsSummaryRes · object | null

Show child attributes

warnings · string[]

Non-fatal warnings (e.g. failed to resolve dataset row refs).