Skip to main content
POST
/
v1
/
retrievers
/
benchmarks
Create benchmark
curl --request POST \
  --url https://api.mixpeek.com/v1/retrievers/benchmarks \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "benchmark_name": "<string>",
  "baseline_retriever_id": "<string>",
  "candidate_retriever_ids": [
    "<string>"
  ],
  "session_filter": {
    "retriever_ids": [
      "<string>"
    ],
    "taxonomy_node_ids": [
      "<string>"
    ],
    "time_range": {
      "start": "2023-11-07T05:31:56Z",
      "end": "2023-11-07T05:31:56Z"
    },
    "min_interactions": 1,
    "interaction_types": [
      "<string>"
    ],
    "sample_strategy": "random",
    "interaction_weights": {
      "weights": {}
    }
  },
  "session_count": 1000
}
'
import requests

url = "https://api.mixpeek.com/v1/retrievers/benchmarks"

payload = {
    "benchmark_name": "<string>",
    "baseline_retriever_id": "<string>",
    "candidate_retriever_ids": ["<string>"],
    "session_filter": {
        "retriever_ids": ["<string>"],
        "taxonomy_node_ids": ["<string>"],
        "time_range": {
            "start": "2023-11-07T05:31:56Z",
            "end": "2023-11-07T05:31:56Z"
        },
        "min_interactions": 1,
        "interaction_types": ["<string>"],
        "sample_strategy": "random",
        "interaction_weights": { "weights": {} }
    },
    "session_count": 1000
}
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({
    benchmark_name: '<string>',
    baseline_retriever_id: '<string>',
    candidate_retriever_ids: ['<string>'],
    session_filter: {
      retriever_ids: ['<string>'],
      taxonomy_node_ids: ['<string>'],
      time_range: {start: '2023-11-07T05:31:56Z', end: '2023-11-07T05:31:56Z'},
      min_interactions: 1,
      interaction_types: ['<string>'],
      sample_strategy: 'random',
      interaction_weights: {weights: {}}
    },
    session_count: 1000
  })
};

fetch('https://api.mixpeek.com/v1/retrievers/benchmarks', 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.mixpeek.com/v1/retrievers/benchmarks",
  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([
    'benchmark_name' => '<string>',
    'baseline_retriever_id' => '<string>',
    'candidate_retriever_ids' => [
        '<string>'
    ],
    'session_filter' => [
        'retriever_ids' => [
                '<string>'
        ],
        'taxonomy_node_ids' => [
                '<string>'
        ],
        'time_range' => [
                'start' => '2023-11-07T05:31:56Z',
                'end' => '2023-11-07T05:31:56Z'
        ],
        'min_interactions' => 1,
        'interaction_types' => [
                '<string>'
        ],
        'sample_strategy' => 'random',
        'interaction_weights' => [
                'weights' => [
                                
                ]
        ]
    ],
    'session_count' => 1000
  ]),
  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://api.mixpeek.com/v1/retrievers/benchmarks"

	payload := strings.NewReader("{\n  \"benchmark_name\": \"<string>\",\n  \"baseline_retriever_id\": \"<string>\",\n  \"candidate_retriever_ids\": [\n    \"<string>\"\n  ],\n  \"session_filter\": {\n    \"retriever_ids\": [\n      \"<string>\"\n    ],\n    \"taxonomy_node_ids\": [\n      \"<string>\"\n    ],\n    \"time_range\": {\n      \"start\": \"2023-11-07T05:31:56Z\",\n      \"end\": \"2023-11-07T05:31:56Z\"\n    },\n    \"min_interactions\": 1,\n    \"interaction_types\": [\n      \"<string>\"\n    ],\n    \"sample_strategy\": \"random\",\n    \"interaction_weights\": {\n      \"weights\": {}\n    }\n  },\n  \"session_count\": 1000\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://api.mixpeek.com/v1/retrievers/benchmarks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"benchmark_name\": \"<string>\",\n  \"baseline_retriever_id\": \"<string>\",\n  \"candidate_retriever_ids\": [\n    \"<string>\"\n  ],\n  \"session_filter\": {\n    \"retriever_ids\": [\n      \"<string>\"\n    ],\n    \"taxonomy_node_ids\": [\n      \"<string>\"\n    ],\n    \"time_range\": {\n      \"start\": \"2023-11-07T05:31:56Z\",\n      \"end\": \"2023-11-07T05:31:56Z\"\n    },\n    \"min_interactions\": 1,\n    \"interaction_types\": [\n      \"<string>\"\n    ],\n    \"sample_strategy\": \"random\",\n    \"interaction_weights\": {\n      \"weights\": {}\n    }\n  },\n  \"session_count\": 1000\n}")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://api.mixpeek.com/v1/retrievers/benchmarks")

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  \"benchmark_name\": \"<string>\",\n  \"baseline_retriever_id\": \"<string>\",\n  \"candidate_retriever_ids\": [\n    \"<string>\"\n  ],\n  \"session_filter\": {\n    \"retriever_ids\": [\n      \"<string>\"\n    ],\n    \"taxonomy_node_ids\": [\n      \"<string>\"\n    ],\n    \"time_range\": {\n      \"start\": \"2023-11-07T05:31:56Z\",\n      \"end\": \"2023-11-07T05:31:56Z\"\n    },\n    \"min_interactions\": 1,\n    \"interaction_types\": [\n      \"<string>\"\n    ],\n    \"sample_strategy\": \"random\",\n    \"interaction_weights\": {\n      \"weights\": {}\n    }\n  },\n  \"session_count\": 1000\n}"

response = http.request(request)
puts response.read_body
{
  "benchmark_id": "<string>",
  "benchmark_name": "<string>",
  "baseline_retriever_id": "<string>",
  "candidate_retriever_ids": [
    "<string>"
  ],
  "session_count": 123,
  "created_at": "2023-11-07T05:31:56Z",
  "session_filter": {
    "retriever_ids": [
      "<string>"
    ],
    "taxonomy_node_ids": [
      "<string>"
    ],
    "time_range": {
      "start": "2023-11-07T05:31:56Z",
      "end": "2023-11-07T05:31:56Z"
    },
    "min_interactions": 1,
    "interaction_types": [
      "<string>"
    ],
    "sample_strategy": "random",
    "interaction_weights": {
      "weights": {}
    }
  },
  "results": [
    {
      "retriever_id": "<string>",
      "retriever_name": "<string>",
      "pipeline_hash": "<string>",
      "metrics": {
        "ndcg_at_k": {},
        "mean_rank_clicked": 123,
        "recall_at_k": {},
        "avg_position_delta": 123,
        "items_promoted": 1,
        "items_demoted": 1,
        "sessions_improved": 1,
        "sessions_degraded": 1,
        "sessions_neutral": 1,
        "mean_rank_purchased": 123
      },
      "latency": {
        "p50_ms": 1,
        "p90_ms": 1,
        "p99_ms": 1,
        "mean_ms": 1,
        "stage_latencies": {}
      },
      "failed_sessions": 1,
      "taxonomy_deltas": {},
      "error_summary": {}
    }
  ],
  "comparison": {
    "baseline_retriever_id": "<string>",
    "comparisons": [
      {
        "candidate_retriever_id": "<string>",
        "ndcg_delta": {},
        "recall_delta": {},
        "latency_delta_ms": 123,
        "p_value": 123,
        "confidence_interval": {
          "[0]": 123,
          "[1]": 123
        },
        "taxonomy_wins": [
          "<string>"
        ],
        "taxonomy_losses": [
          "<string>"
        ]
      }
    ],
    "recommendation": "<string>"
  },
  "started_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "error_message": "<string>"
}
{
  "status": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>",
    "details": {}
  },
  "success": false
}
{
  "status": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>",
    "details": {}
  },
  "success": false
}
{
  "status": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>",
    "details": {}
  },
  "success": false
}
{
  "status": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>",
    "details": {}
  },
  "success": false
}
{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}
{
  "status": 123,
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>",
    "details": {}
  },
  "success": false
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request to create a new benchmark run.

​
benchmark_name
string
required

Human-readable name for this benchmark.

Required string length: 1 - 255
​
baseline_retriever_id
string
required

ID of the baseline retriever pipeline to compare against.

​
candidate_retriever_ids
string[]
required

IDs of candidate retriever pipelines to evaluate.

Minimum array length: 1
​
session_filter
SessionFilter · object | null

Optional filter criteria for selecting sessions to replay.

​
session_count
integer
default:1000

Number of sessions to include in the benchmark.

Required range: 10 <= x <= 10000

Response

Successful Response

Response containing benchmark details and results.

​
benchmark_id
string
required

Unique benchmark identifier.

​
benchmark_name
string
required

Human-readable name.

​
baseline_retriever_id
string
required

Baseline retriever ID.

​
candidate_retriever_ids
string[]
required

Candidate retriever IDs.

​
session_count
integer
required

Number of sessions in benchmark.

​
status
enum<string>
required

Current benchmark status.

Available options:
pending,
building_sessions,
replaying,
computing_metrics,
completed,
failed
​
created_at
string<date-time>
required

Creation timestamp.

​
session_filter
SessionFilter · object | null

Filter criteria used.

​
results
BenchmarkResult · object[] | null

Results per pipeline (available when completed).

​
comparison
BenchmarkComparison · object | null

Statistical comparison (available when completed).

​
started_at
string<date-time> | null

Execution start time.

​
completed_at
string<date-time> | null

Completion time.

​
error_message
string | null

Error message if failed.