---
title: Aggregate LLM Observability experimentation
description: Datadog, the leading service for cloud-scale monitoring.
breadcrumbs: Docs > API Reference > LLM Observability
---

# Aggregate LLM Observability experimentation{% #aggregate-llm-observability-experimentation %}
Copy pageCopied
{% tab title="v2" %}
**Note**: This endpoint is in preview and is subject to change. If you have any feedback, contact [Datadog support](https://docs.datadoghq.com/help/).
| Datadog site      | API endpoint                                                                   |
| ----------------- | ------------------------------------------------------------------------------ |
| ap1.datadoghq.com | POST https://api.ap1.datadoghq.com/api/v2/llm-obs/v1/experimentation/analytics |
| ap2.datadoghq.com | POST https://api.ap2.datadoghq.com/api/v2/llm-obs/v1/experimentation/analytics |
| app.datadoghq.eu  | POST https://api.datadoghq.eu/api/v2/llm-obs/v1/experimentation/analytics      |
| app.ddog-gov.com  | POST https://api.ddog-gov.com/api/v2/llm-obs/v1/experimentation/analytics      |
| us2.ddog-gov.com  | POST https://api.us2.ddog-gov.com/api/v2/llm-obs/v1/experimentation/analytics  |
| app.datadoghq.com | POST https://api.datadoghq.com/api/v2/llm-obs/v1/experimentation/analytics     |
| us3.datadoghq.com | POST https://api.us3.datadoghq.com/api/v2/llm-obs/v1/experimentation/analytics |
| us5.datadoghq.com | POST https://api.us5.datadoghq.com/api/v2/llm-obs/v1/experimentation/analytics |

### Overview



Execute an analytics aggregation over LLM Observability experimentation data. Use this endpoint to compute metrics (for example average eval scores) grouped by fields such as `span_id` or `experiment_id`.

At least one `compute` definition and one `index` must be provided.



### Request

#### Body Data (required)

Analytics payload.

{% tab title="Model" %}

| Parent field | Field                        | Type     | Description                                                                                               |
| ------------ | ---------------------------- | -------- | --------------------------------------------------------------------------------------------------------- |
|              | data [*required*]       | object   | Data object for an analytics request.                                                                     |
| data         | attributes [*required*] | object   | Attributes for an analytics request.                                                                      |
| attributes   | aggregate [*required*]  | object   | Analytics aggregation parameters.                                                                         |
| aggregate    | compute [*required*]    | [object] | List of metric computations to perform.                                                                   |
| compute      | metric [*required*]     | string   | Name of the metric to compute.                                                                            |
| compute      | name                         | string   | Optional alias for this computation in the response.                                                      |
| aggregate    | dataset_version              | int64    | Filter to a specific dataset version.                                                                     |
| aggregate    | group_by                     | [object] | Fields to group results by.                                                                               |
| group_by     | field [*required*]      | string   | Field name to group by.                                                                                   |
| aggregate    | indexes [*required*]    | [string] | Data indexes to query. At least one is required.                                                          |
| aggregate    | limit                        | int32    | Maximum number of results to return.                                                                      |
| aggregate    | search [*required*]     | object   | Search query for filtering analytics data.                                                                |
| search       | query [*required*]      | string   | Filter expression.                                                                                        |
| aggregate    | time                         | object   | Unix-millisecond time range for filtering analytics data.                                                 |
| time         | from [*required*]       | int64    | Start of the time range in milliseconds since Unix epoch.                                                 |
| time         | to [*required*]         | int64    | End of the time range in milliseconds since Unix epoch.                                                   |
| data         | type [*required*]       | enum     | Resource type for experimentation search and analytics operations. Allowed enum values: `experimentation` |

{% /tab %}

{% tab title="Example" %}

```json
{
  "data": {
    "attributes": {
      "aggregate": {
        "compute": [
          {
            "metric": "score_value",
            "name": "avg_faithfulness"
          }
        ],
        "dataset_version": "integer",
        "group_by": [
          {
            "field": "span_id"
          }
        ],
        "indexes": [
          "experiment-evals"
        ],
        "limit": 1000,
        "search": {
          "query": "@experiment_id:3fd6b5e0-8910-4b1c-a7d0-5b84de329012"
        },
        "time": {
          "from": 1705312200000,
          "to": 1705315800000
        }
      }
    },
    "type": "experimentation"
  }
}
```

{% /tab %}

### Response

{% tab title="200" %}
OK
{% tab title="Model" %}
Response to an analytics query.

| Parent field | Field                        | Type     | Description                                                                                               |
| ------------ | ---------------------------- | -------- | --------------------------------------------------------------------------------------------------------- |
|              | data [*required*]       | object   | JSON:API data object for an analytics response.                                                           |
| data         | attributes [*required*] | object   | Attributes of an analytics response.                                                                      |
| attributes   | hit_count [*required*]  | int64    | Total number of events matched by the query before grouping.                                              |
| attributes   | result [*required*]     | object   | Analytics query result containing all buckets.                                                            |
| result       | values [*required*]     | [object] | List of result buckets.                                                                                   |
| values       | by                           | object   | The group-by field values for this bucket.                                                                |
| values       | metrics [*required*]    | object   | Computed metric values for this bucket.                                                                   |
| data         | id [*required*]         | string   | Server-generated identifier for this analytics result.                                                    |
| data         | type [*required*]       | enum     | Resource type for experimentation search and analytics operations. Allowed enum values: `experimentation` |

{% /tab %}

{% tab title="Example" %}

```json
{
  "data": {
    "attributes": {
      "hit_count": 1500,
      "result": {
        "values": [
          {
            "by": {
              "span_id": "span-7a1b2c3d"
            },
            "metrics": {
              "score_value": 0.85
            }
          }
        ]
      }
    },
    "id": "00000000-0000-0000-0000-000000000001",
    "type": "experimentation"
  }
}
```

{% /tab %}

{% /tab %}

{% tab title="400" %}
Bad Request
{% tab title="Model" %}
API error response.

| Parent field | Field                    | Type     | Description                                                                     |
| ------------ | ------------------------ | -------- | ------------------------------------------------------------------------------- |
|              | errors [*required*] | [object] | A list of errors.                                                               |
| errors       | detail                   | string   | A human-readable explanation specific to this occurrence of the error.          |
| errors       | meta                     | object   | Non-standard meta-information about the error                                   |
| errors       | source                   | object   | References to the source of the error.                                          |
| source       | header                   | string   | A string indicating the name of a single request header which caused the error. |
| source       | parameter                | string   | A string indicating which URI query parameter caused the error.                 |
| source       | pointer                  | string   | A JSON pointer to the value in the request document that caused the error.      |
| errors       | status                   | string   | Status code of the response.                                                    |
| errors       | title                    | string   | Short human-readable summary of the error.                                      |

{% /tab %}

{% tab title="Example" %}

```json
{
  "errors": [
    {
      "detail": "Missing required attribute in body",
      "meta": {},
      "source": {
        "header": "Authorization",
        "parameter": "limit",
        "pointer": "/data/attributes/title"
      },
      "status": "400",
      "title": "Bad Request"
    }
  ]
}
```

{% /tab %}

{% /tab %}

{% tab title="401" %}
Unauthorized
{% tab title="Model" %}
API error response.

| Parent field | Field                    | Type     | Description                                                                     |
| ------------ | ------------------------ | -------- | ------------------------------------------------------------------------------- |
|              | errors [*required*] | [object] | A list of errors.                                                               |
| errors       | detail                   | string   | A human-readable explanation specific to this occurrence of the error.          |
| errors       | meta                     | object   | Non-standard meta-information about the error                                   |
| errors       | source                   | object   | References to the source of the error.                                          |
| source       | header                   | string   | A string indicating the name of a single request header which caused the error. |
| source       | parameter                | string   | A string indicating which URI query parameter caused the error.                 |
| source       | pointer                  | string   | A JSON pointer to the value in the request document that caused the error.      |
| errors       | status                   | string   | Status code of the response.                                                    |
| errors       | title                    | string   | Short human-readable summary of the error.                                      |

{% /tab %}

{% tab title="Example" %}

```json
{
  "errors": [
    {
      "detail": "Missing required attribute in body",
      "meta": {},
      "source": {
        "header": "Authorization",
        "parameter": "limit",
        "pointer": "/data/attributes/title"
      },
      "status": "400",
      "title": "Bad Request"
    }
  ]
}
```

{% /tab %}

{% /tab %}

{% tab title="403" %}
Forbidden
{% tab title="Model" %}
API error response.

| Parent field | Field                    | Type     | Description                                                                     |
| ------------ | ------------------------ | -------- | ------------------------------------------------------------------------------- |
|              | errors [*required*] | [object] | A list of errors.                                                               |
| errors       | detail                   | string   | A human-readable explanation specific to this occurrence of the error.          |
| errors       | meta                     | object   | Non-standard meta-information about the error                                   |
| errors       | source                   | object   | References to the source of the error.                                          |
| source       | header                   | string   | A string indicating the name of a single request header which caused the error. |
| source       | parameter                | string   | A string indicating which URI query parameter caused the error.                 |
| source       | pointer                  | string   | A JSON pointer to the value in the request document that caused the error.      |
| errors       | status                   | string   | Status code of the response.                                                    |
| errors       | title                    | string   | Short human-readable summary of the error.                                      |

{% /tab %}

{% tab title="Example" %}

```json
{
  "errors": [
    {
      "detail": "Missing required attribute in body",
      "meta": {},
      "source": {
        "header": "Authorization",
        "parameter": "limit",
        "pointer": "/data/attributes/title"
      },
      "status": "400",
      "title": "Bad Request"
    }
  ]
}
```

{% /tab %}

{% /tab %}

{% tab title="429" %}
Too many requests
{% tab title="Model" %}
API error response.

| Field                    | Type     | Description       |
| ------------------------ | -------- | ----------------- |
| errors [*required*] | [string] | A list of errors. |

{% /tab %}

{% tab title="Example" %}

```json
{
  "errors": [
    "Bad Request"
  ]
}
```

{% /tab %}

{% /tab %}

{% tab title="500" %}
Internal Server Error
{% tab title="Model" %}
API error response.

| Parent field | Field                    | Type     | Description                                                                     |
| ------------ | ------------------------ | -------- | ------------------------------------------------------------------------------- |
|              | errors [*required*] | [object] | A list of errors.                                                               |
| errors       | detail                   | string   | A human-readable explanation specific to this occurrence of the error.          |
| errors       | meta                     | object   | Non-standard meta-information about the error                                   |
| errors       | source                   | object   | References to the source of the error.                                          |
| source       | header                   | string   | A string indicating the name of a single request header which caused the error. |
| source       | parameter                | string   | A string indicating which URI query parameter caused the error.                 |
| source       | pointer                  | string   | A JSON pointer to the value in the request document that caused the error.      |
| errors       | status                   | string   | Status code of the response.                                                    |
| errors       | title                    | string   | Short human-readable summary of the error.                                      |

{% /tab %}

{% tab title="Example" %}

```json
{
  "errors": [
    {
      "detail": "Missing required attribute in body",
      "meta": {},
      "source": {
        "header": "Authorization",
        "parameter": "limit",
        "pointer": "/data/attributes/title"
      },
      "status": "400",
      "title": "Bad Request"
    }
  ]
}
```

{% /tab %}

{% /tab %}

### Code Example

##### 
                  \## default
# 
 \# Curl command curl -X POST "https://api.datadoghq.com/api/v2/llm-obs/v1/experimentation/analytics" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "DD-API-KEY: ${DD_API_KEY}" \
-H "DD-APPLICATION-KEY: ${DD_APP_KEY}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "aggregate": {
        "compute": [
          {
            "metric": "score_value",
            "name": "avg_faithfulness"
          }
        ],
        "group_by": [
          {
            "field": "span_id"
          }
        ],
        "indexes": [
          "experiment-evals"
        ],
        "search": {
          "query": "@experiment_id:3fd6b5e0-8910-4b1c-a7d0-5b84de329012 @label:faithfulness"
        }
      }
    },
    "type": "experimentation"
  }
}
EOF 
                
##### 

```python
"""
Aggregate LLM Observability experimentation returns "OK" response
"""

from datadog_api_client import ApiClient, Configuration
from datadog_api_client.v2.api.llm_observability_api import LLMObservabilityApi
from datadog_api_client.v2.model.llm_obs_experimentation_analytics_aggregate import (
    LLMObsExperimentationAnalyticsAggregate,
)
from datadog_api_client.v2.model.llm_obs_experimentation_analytics_compute import LLMObsExperimentationAnalyticsCompute
from datadog_api_client.v2.model.llm_obs_experimentation_analytics_data_attributes_request import (
    LLMObsExperimentationAnalyticsDataAttributesRequest,
)
from datadog_api_client.v2.model.llm_obs_experimentation_analytics_data_request import (
    LLMObsExperimentationAnalyticsDataRequest,
)
from datadog_api_client.v2.model.llm_obs_experimentation_analytics_group_by import LLMObsExperimentationAnalyticsGroupBy
from datadog_api_client.v2.model.llm_obs_experimentation_analytics_request import LLMObsExperimentationAnalyticsRequest
from datadog_api_client.v2.model.llm_obs_experimentation_analytics_search import LLMObsExperimentationAnalyticsSearch
from datadog_api_client.v2.model.llm_obs_experimentation_analytics_time_range import (
    LLMObsExperimentationAnalyticsTimeRange,
)
from datadog_api_client.v2.model.llm_obs_experimentation_type import LLMObsExperimentationType

body = LLMObsExperimentationAnalyticsRequest(
    data=LLMObsExperimentationAnalyticsDataRequest(
        attributes=LLMObsExperimentationAnalyticsDataAttributesRequest(
            aggregate=LLMObsExperimentationAnalyticsAggregate(
                compute=[
                    LLMObsExperimentationAnalyticsCompute(
                        metric="score_value",
                        name="avg_faithfulness",
                    ),
                ],
                dataset_version=None,
                group_by=[
                    LLMObsExperimentationAnalyticsGroupBy(
                        field="span_id",
                    ),
                ],
                indexes=[
                    "experiment-evals",
                ],
                limit=1000,
                search=LLMObsExperimentationAnalyticsSearch(
                    query="@experiment_id:3fd6b5e0-8910-4b1c-a7d0-5b84de329012",
                ),
                time=LLMObsExperimentationAnalyticsTimeRange(
                    _from=1705312200000,
                    to=1705315800000,
                ),
            ),
        ),
        type=LLMObsExperimentationType.EXPERIMENTATION,
    ),
)

configuration = Configuration()
configuration.unstable_operations["aggregate_llm_obs_experimentation"] = True
with ApiClient(configuration) as api_client:
    api_instance = LLMObservabilityApi(api_client)
    response = api_instance.aggregate_llm_obs_experimentation(body=body)

    print(response)
```

#### Instructions

First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=python) and then save the example to `example.py` and run following commands:
    DD_SITE="datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" python3 "example.py"
##### 

```ruby
# Aggregate LLM Observability experimentation returns "OK" response

require "datadog_api_client"
DatadogAPIClient.configure do |config|
  config.unstable_operations["v2.aggregate_llm_obs_experimentation".to_sym] = true
end
api_instance = DatadogAPIClient::V2::LLMObservabilityAPI.new

body = DatadogAPIClient::V2::LLMObsExperimentationAnalyticsRequest.new({
  data: DatadogAPIClient::V2::LLMObsExperimentationAnalyticsDataRequest.new({
    attributes: DatadogAPIClient::V2::LLMObsExperimentationAnalyticsDataAttributesRequest.new({
      aggregate: DatadogAPIClient::V2::LLMObsExperimentationAnalyticsAggregate.new({
        compute: [
          DatadogAPIClient::V2::LLMObsExperimentationAnalyticsCompute.new({
            metric: "score_value",
            name: "avg_faithfulness",
          }),
        ],
        dataset_version: nil,
        group_by: [
          DatadogAPIClient::V2::LLMObsExperimentationAnalyticsGroupBy.new({
            field: "span_id",
          }),
        ],
        indexes: [
          "experiment-evals",
        ],
        limit: 1000,
        search: DatadogAPIClient::V2::LLMObsExperimentationAnalyticsSearch.new({
          query: "@experiment_id:3fd6b5e0-8910-4b1c-a7d0-5b84de329012",
        }),
        time: DatadogAPIClient::V2::LLMObsExperimentationAnalyticsTimeRange.new({
          from: 1705312200000,
          to: 1705315800000,
        }),
      }),
    }),
    type: DatadogAPIClient::V2::LLMObsExperimentationType::EXPERIMENTATION,
  }),
})
p api_instance.aggregate_llm_obs_experimentation(body)
```

#### Instructions

First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=ruby) and then save the example to `example.rb` and run following commands:
    DD_SITE="datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" rb "example.rb"
##### 

```go
// Aggregate LLM Observability experimentation returns "OK" response

package main

import (
	"context"
	"encoding/json"
	"fmt"
	"os"

	"github.com/DataDog/datadog-api-client-go/v2/api/datadog"
	"github.com/DataDog/datadog-api-client-go/v2/api/datadogV2"
)

func main() {
	body := datadogV2.LLMObsExperimentationAnalyticsRequest{
		Data: datadogV2.LLMObsExperimentationAnalyticsDataRequest{
			Attributes: datadogV2.LLMObsExperimentationAnalyticsDataAttributesRequest{
				Aggregate: datadogV2.LLMObsExperimentationAnalyticsAggregate{
					Compute: []datadogV2.LLMObsExperimentationAnalyticsCompute{
						{
							Metric: "score_value",
							Name:   datadog.PtrString("avg_faithfulness"),
						},
					},
					DatasetVersion: *datadog.NewNullableInt64(nil),
					GroupBy: []datadogV2.LLMObsExperimentationAnalyticsGroupBy{
						{
							Field: "span_id",
						},
					},
					Indexes: []string{
						"experiment-evals",
					},
					Limit: *datadog.NewNullableInt32(datadog.PtrInt32(1000)),
					Search: datadogV2.LLMObsExperimentationAnalyticsSearch{
						Query: "@experiment_id:3fd6b5e0-8910-4b1c-a7d0-5b84de329012",
					},
					Time: &datadogV2.LLMObsExperimentationAnalyticsTimeRange{
						From: 1705312200000,
						To:   1705315800000,
					},
				},
			},
			Type: datadogV2.LLMOBSEXPERIMENTATIONTYPE_EXPERIMENTATION,
		},
	}
	ctx := datadog.NewDefaultContext(context.Background())
	configuration := datadog.NewConfiguration()
	configuration.SetUnstableOperationEnabled("v2.AggregateLLMObsExperimentation", true)
	apiClient := datadog.NewAPIClient(configuration)
	api := datadogV2.NewLLMObservabilityApi(apiClient)
	resp, r, err := api.AggregateLLMObsExperimentation(ctx, body)

	if err != nil {
		fmt.Fprintf(os.Stderr, "Error when calling `LLMObservabilityApi.AggregateLLMObsExperimentation`: %v\n", err)
		fmt.Fprintf(os.Stderr, "Full HTTP response: %v\n", r)
	}

	responseContent, _ := json.MarshalIndent(resp, "", "  ")
	fmt.Fprintf(os.Stdout, "Response from `LLMObservabilityApi.AggregateLLMObsExperimentation`:\n%s\n", responseContent)
}
```

#### Instructions

First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=go) and then save the example to `main.go` and run following commands:
    DD_SITE="datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" go run "main.go"
##### 

```java
// Aggregate LLM Observability experimentation returns "OK" response

import com.datadog.api.client.ApiClient;
import com.datadog.api.client.ApiException;
import com.datadog.api.client.v2.api.LlmObservabilityApi;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsAggregate;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsCompute;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsDataAttributesRequest;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsDataRequest;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsGroupBy;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsRequest;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsResponse;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsSearch;
import com.datadog.api.client.v2.model.LLMObsExperimentationAnalyticsTimeRange;
import com.datadog.api.client.v2.model.LLMObsExperimentationType;
import java.util.Collections;

public class Example {
  public static void main(String[] args) {
    ApiClient defaultClient = ApiClient.getDefaultApiClient();
    defaultClient.setUnstableOperationEnabled("v2.aggregateLLMObsExperimentation", true);
    LlmObservabilityApi apiInstance = new LlmObservabilityApi(defaultClient);

    LLMObsExperimentationAnalyticsRequest body =
        new LLMObsExperimentationAnalyticsRequest()
            .data(
                new LLMObsExperimentationAnalyticsDataRequest()
                    .attributes(
                        new LLMObsExperimentationAnalyticsDataAttributesRequest()
                            .aggregate(
                                new LLMObsExperimentationAnalyticsAggregate()
                                    .compute(
                                        Collections.singletonList(
                                            new LLMObsExperimentationAnalyticsCompute()
                                                .metric("score_value")
                                                .name("avg_faithfulness")))
                                    .datasetVersion(null)
                                    .groupBy(
                                        Collections.singletonList(
                                            new LLMObsExperimentationAnalyticsGroupBy()
                                                .field("span_id")))
                                    .indexes(Collections.singletonList("experiment-evals"))
                                    .limit(1000)
                                    .search(
                                        new LLMObsExperimentationAnalyticsSearch()
                                            .query(
                                                "@experiment_id:3fd6b5e0-8910-4b1c-a7d0-5b84de329012"))
                                    .time(
                                        new LLMObsExperimentationAnalyticsTimeRange()
                                            .from(1705312200000L)
                                            .to(1705315800000L))))
                    .type(LLMObsExperimentationType.EXPERIMENTATION));

    try {
      LLMObsExperimentationAnalyticsResponse result =
          apiInstance.aggregateLLMObsExperimentation(body);
      System.out.println(result);
    } catch (ApiException e) {
      System.err.println(
          "Exception when calling LlmObservabilityApi#aggregateLLMObsExperimentation");
      System.err.println("Status code: " + e.getCode());
      System.err.println("Reason: " + e.getResponseBody());
      System.err.println("Response headers: " + e.getResponseHeaders());
      e.printStackTrace();
    }
  }
}
```

#### Instructions

First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=java) and then save the example to `Example.java` and run following commands:
    DD_SITE="datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" java "Example.java"
##### 

```rust
// Aggregate LLM Observability experimentation returns "OK" response
use datadog_api_client::datadog;
use datadog_api_client::datadogV2::api_llm_observability::LLMObservabilityAPI;
use datadog_api_client::datadogV2::model::LLMObsExperimentationAnalyticsAggregate;
use datadog_api_client::datadogV2::model::LLMObsExperimentationAnalyticsCompute;
use datadog_api_client::datadogV2::model::LLMObsExperimentationAnalyticsDataAttributesRequest;
use datadog_api_client::datadogV2::model::LLMObsExperimentationAnalyticsDataRequest;
use datadog_api_client::datadogV2::model::LLMObsExperimentationAnalyticsGroupBy;
use datadog_api_client::datadogV2::model::LLMObsExperimentationAnalyticsRequest;
use datadog_api_client::datadogV2::model::LLMObsExperimentationAnalyticsSearch;
use datadog_api_client::datadogV2::model::LLMObsExperimentationAnalyticsTimeRange;
use datadog_api_client::datadogV2::model::LLMObsExperimentationType;

#[tokio::main]
async fn main() {
    let body =
        LLMObsExperimentationAnalyticsRequest::new(LLMObsExperimentationAnalyticsDataRequest::new(
            LLMObsExperimentationAnalyticsDataAttributesRequest::new(
                LLMObsExperimentationAnalyticsAggregate::new(
                    vec![
                        LLMObsExperimentationAnalyticsCompute::new("score_value".to_string())
                            .name("avg_faithfulness".to_string()),
                    ],
                    vec!["experiment-evals".to_string()],
                    LLMObsExperimentationAnalyticsSearch::new(
                        "@experiment_id:3fd6b5e0-8910-4b1c-a7d0-5b84de329012".to_string(),
                    ),
                )
                .dataset_version(None)
                .group_by(vec![LLMObsExperimentationAnalyticsGroupBy::new(
                    "span_id".to_string(),
                )])
                .limit(Some(1000))
                .time(LLMObsExperimentationAnalyticsTimeRange::new(
                    1705312200000,
                    1705315800000,
                )),
            ),
            LLMObsExperimentationType::EXPERIMENTATION,
        ));
    let mut configuration = datadog::Configuration::new();
    configuration.set_unstable_operation_enabled("v2.AggregateLLMObsExperimentation", true);
    let api = LLMObservabilityAPI::with_config(configuration);
    let resp = api.aggregate_llm_obs_experimentation(body).await;
    if let Ok(value) = resp {
        println!("{:#?}", value);
    } else {
        println!("{:#?}", resp.unwrap_err());
    }
}
```

#### Instructions

First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=rust) and then save the example to `src/main.rs` and run following commands:
    DD_SITE="datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run
##### 

```typescript
/**
 * Aggregate LLM Observability experimentation returns "OK" response
 */

import { client, v2 } from "@datadog/datadog-api-client";

const configuration = client.createConfiguration();
configuration.unstableOperations["v2.aggregateLLMObsExperimentation"] = true;
const apiInstance = new v2.LLMObservabilityApi(configuration);

const params: v2.LLMObservabilityApiAggregateLLMObsExperimentationRequest = {
  body: {
    data: {
      attributes: {
        aggregate: {
          compute: [
            {
              metric: "score_value",
              name: "avg_faithfulness",
            },
          ],
          datasetVersion: undefined,
          groupBy: [
            {
              field: "span_id",
            },
          ],
          indexes: ["experiment-evals"],
          limit: 1000,
          search: {
            query: "@experiment_id:3fd6b5e0-8910-4b1c-a7d0-5b84de329012",
          },
          time: {
            from: 1705312200000,
            to: 1705315800000,
          },
        },
      },
      type: "experimentation",
    },
  },
};

apiInstance
  .aggregateLLMObsExperimentation(params)
  .then((data: v2.LLMObsExperimentationAnalyticsResponse) => {
    console.log(
      "API called successfully. Returned data: " + JSON.stringify(data)
    );
  })
  .catch((error: any) => console.error(error));
```

#### Instructions

First [install the library and its dependencies](https://docs.datadoghq.com/api/latest.md?code-lang=typescript) and then save the example to `example.ts` and run following commands:
    DD_SITE="datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" tsc "example.ts"
{% /tab %}