--- title: Agent Observability 주석 대기열 생성 description: 주석 대기열을 생성합니다. name 및 project_id 필드는 필수입니다. 대기열에 대한 레이블을 정의하기 위해 선택적 annotation_schema를 제공할 수 있습니다. 선택적 액세스 제어 필드를 사용하여 검토자 또는 담당자로 주석 액세스를 제한할 수 있습니다.… breadcrumbs: 문서 > API > Agent Observability 주석 대기열 생성 --- > For the complete documentation index, see [llms.txt](https://dnd37xeb23o8n.cloudfront.net/stefon.simmons/docs-astro-web-10435/llms.txt). # Agent Observability 주석 대기열 생성 ## v2 (latest) {% alert level="warning" %} **Note**: This endpoint is in preview and is subject to change. If you have any feedback, contact [Datadog support](https://docs.datadoghq.com/help.md). {% /alert %} | Datadog site | API endpoint | | ----------------- | ---------------------------------------------------------------------- | | app.datadoghq.com | POST https://api.datadoghq.com/api/v2/llm-obs/v1/annotation-queues | | us3.datadoghq.com | POST https://api.us3.datadoghq.com/api/v2/llm-obs/v1/annotation-queues | | us5.datadoghq.com | POST https://api.us5.datadoghq.com/api/v2/llm-obs/v1/annotation-queues | | app.datadoghq.eu | POST https://api.datadoghq.eu/api/v2/llm-obs/v1/annotation-queues | | ap1.datadoghq.com | POST https://api.ap1.datadoghq.com/api/v2/llm-obs/v1/annotation-queues | | ap2.datadoghq.com | POST https://api.ap2.datadoghq.com/api/v2/llm-obs/v1/annotation-queues | | uk1.datadoghq.com | POST https://api.uk1.datadoghq.com/api/v2/llm-obs/v1/annotation-queues | | app.ddog-gov.com | POST https://api.ddog-gov.com/api/v2/llm-obs/v1/annotation-queues | | us2.ddog-gov.com | POST https://api.us2.ddog-gov.com/api/v2/llm-obs/v1/annotation-queues | ### Overview 주석 대기열을 생성합니다. `name` 및 `project_id` 필드는 필수입니다. 대기열에 대한 레이블을 정의하기 위해 선택적 `annotation_schema`를 제공할 수 있습니다. 선택적 액세스 제어 필드를 사용하여 검토자 또는 담당자로 주석 액세스를 제한할 수 있습니다. `created_by`, `owned_by`, `created_at`, `modified_by`, `modified_at`와 같은 필드는 백엔드에서 추론됩니다. ### Request #### Body Data (required) 주석 대기열 생성 페이로드입니다. {% tabs %} {% tab label="Model" %} | Parent field | Field | Type | Description | | ----------------- | -------------------------- | -------- | -------------------------------------------------------------------------------------------------------------------- | | | data [*required*] | object | Agent Observability 주석 대기열을 생성하도록 요청합니다. | | data | attributes [*required*] | object | Attributes for creating an Agent Observability annotation queue. | | attributes | annotation_schema | object | Schema defining the labels for an annotation queue. | | annotation_schema | label_schemas [*required*] | [object] | List of label schema definitions. | | label_schemas | description | string | Description of the label. | | label_schemas | has_assessment | boolean | Whether this label includes an assessment field. | | label_schemas | has_reasoning | boolean | Whether this label includes a reasoning field. | | label_schemas | id | string | Unique identifier of the label schema. Assigned by the server if not provided. | | label_schemas | is_assessment | boolean | Whether the boolean label represents an assessment. Requires `has_assessment` to be true. | | label_schemas | is_integer | boolean | Whether score values must be integers. Applicable to score-type labels. | | label_schemas | is_required | boolean | Whether this label is required for an annotation. | | label_schemas | max | double | Maximum value for score-type labels. | | label_schemas | min | double | Minimum value for score-type labels. | | label_schemas | name [*required*] | string | Name of the label. Must match the pattern `^[a-zA-Z0-9_-]+$` and be unique within the queue. | | label_schemas | type [*required*] | enum | Type of a label in an annotation queue label schema. Allowed enum values: `score`, `categorical`, `boolean`, `text`. | | label_schemas | values | [string] | Allowed values for categorical-type labels. Must contain at least one non-empty, unique value. | | attributes | description | string | Description of the annotation queue. | | attributes | name [*required*] | string | Name of the annotation queue. | | attributes | project_id [*required*] | string | Identifier of the project this queue belongs to. | | attributes | restrict_to_assignees | boolean | Whether annotation access is restricted to assigned users. | | attributes | restrict_to_reviewers | boolean | Whether annotation access is restricted to queue reviewers. | | attributes | reviewer_emails | [string] | Email addresses of reviewers who can access the annotation queue. | | data | type [*required*] | enum | Resource type of an Agent Observability annotation queue. Allowed enum values: `queues`. | {% /tab %} {% tab label="Example" %} ```json { "data": { "attributes": { "annotation_schema": { "label_schemas": [ { "description": "Rating of the response quality.", "has_assessment": false, "has_reasoning": false, "id": "abc-123", "is_assessment": false, "is_integer": false, "is_required": true, "max": 5, "min": 0, "name": "quality", "type": "score", "values": [ "good", "bad", "neutral" ] } ] }, "description": "Queue for annotating customer support traces", "name": "My annotation queue", "project_id": "00000000-0000-0000-0000-000000000002", "restrict_to_assignees": false, "restrict_to_reviewers": true, "reviewer_emails": [ "reviewer@example.com" ] }, "type": "queues" } } ``` {% /tab %} {% /tabs %} ### Response {% tabs %} {% tab label="201" %} Created {% tabs %} {% tab label="Model" %} Response containing a single Agent Observability annotation queue. | Parent field | Field | Type | Description | | ----------------- | ---------------------------------- | --------- | -------------------------------------------------------------------------------------------------------------------- | | | data [*required*] | object | Data object for an Agent Observability annotation queue. | | data | attributes [*required*] | object | Attributes of an Agent Observability annotation queue. | | attributes | annotation_schema | object | Schema defining the labels for an annotation queue. | | annotation_schema | label_schemas [*required*] | [object] | List of label schema definitions. | | label_schemas | description | string | Description of the label. | | label_schemas | has_assessment | boolean | Whether this label includes an assessment field. | | label_schemas | has_reasoning | boolean | Whether this label includes a reasoning field. | | label_schemas | id | string | Unique identifier of the label schema. Assigned by the server if not provided. | | label_schemas | is_assessment | boolean | Whether the boolean label represents an assessment. Requires `has_assessment` to be true. | | label_schemas | is_integer | boolean | Whether score values must be integers. Applicable to score-type labels. | | label_schemas | is_required | boolean | Whether this label is required for an annotation. | | label_schemas | max | double | Maximum value for score-type labels. | | label_schemas | min | double | Minimum value for score-type labels. | | label_schemas | name [*required*] | string | Name of the label. Must match the pattern `^[a-zA-Z0-9_-]+$` and be unique within the queue. | | label_schemas | type [*required*] | enum | Type of a label in an annotation queue label schema. Allowed enum values: `score`, `categorical`, `boolean`, `text`. | | label_schemas | values | [string] | Allowed values for categorical-type labels. Must contain at least one non-empty, unique value. | | attributes | can_manage_access [*required*] | boolean | Whether the current caller can manage access for the annotation queue. Read-only. | | attributes | created_at [*required*] | date-time | Timestamp when the queue was created. | | attributes | created_by [*required*] | string | Identifier of the user who created the queue. | | attributes | description [*required*] | string | Description of the annotation queue. | | attributes | modified_at [*required*] | date-time | Timestamp when the queue was last modified. | | attributes | modified_by [*required*] | string | Identifier of the user who last modified the queue. | | attributes | name [*required*] | string | Name of the annotation queue. | | attributes | owned_by [*required*] | string | Identifier of the user who owns the queue. | | attributes | project_id [*required*] | string | Identifier of the project this queue belongs to. | | attributes | restrict_to_assignees [*required*] | boolean | Whether annotation access is restricted to assigned users. | | attributes | restrict_to_reviewers [*required*] | boolean | Whether annotation access is restricted to queue reviewers. | | attributes | reviewer_emails | [string] | Email addresses of reviewers for the annotation queue. Returned only when the caller can manage queue access. | | data | id [*required*] | string | Unique identifier of the annotation queue. | | data | type [*required*] | enum | Resource type of an Agent Observability annotation queue. Allowed enum values: `queues`. | {% /tab %} {% tab label="Example" %} ```json { "data": { "attributes": { "annotation_schema": { "label_schemas": [ { "description": "Rating of the response quality.", "has_assessment": false, "has_reasoning": false, "id": "abc-123", "is_assessment": false, "is_integer": false, "is_required": true, "max": 5, "min": 0, "name": "quality", "type": "score", "values": [ "good", "bad", "neutral" ] } ] }, "can_manage_access": true, "created_at": "2024-01-15T10:30:00Z", "created_by": "00000000-0000-0000-0000-000000000002", "description": "Queue for annotating customer support traces", "modified_at": "2024-01-15T10:30:00Z", "modified_by": "00000000-0000-0000-0000-000000000002", "name": "My annotation queue", "owned_by": "00000000-0000-0000-0000-000000000002", "project_id": "00000000-0000-0000-0000-000000000002", "restrict_to_assignees": false, "restrict_to_reviewers": true, "reviewer_emails": [ "reviewer@example.com" ] }, "id": "00000000-0000-0000-0000-000000000001", "type": "queues" } } ``` {% /tab %} {% /tabs %} {% /tab %} {% tab label="400" %} Bad Request {% tabs %} {% tab label="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 label="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 %} {% /tabs %} {% /tab %} {% tab label="401" %} Unauthorized {% tabs %} {% tab label="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 label="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 %} {% /tabs %} {% /tab %} {% tab label="403" %} Forbidden {% tabs %} {% tab label="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 label="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 %} {% /tabs %} {% /tab %} {% tab label="429" %} Too many requests {% tabs %} {% tab label="Model" %} API error response. | Field | Type | Description | | ------------------- | -------- | ----------------- | | errors [*required*] | [string] | A list of errors. | {% /tab %} {% tab label="Example" %} ```json { "errors": [ "Bad Request" ] } ``` {% /tab %} {% /tabs %} {% /tab %} {% /tabs %} ### Code Example {% tabs %} {% tab label="Curl" %} ```bash ## default # Set your Datadog site and credentials export DD_SITE="datadoghq.com" # Or us3.datadoghq.com, us5.datadoghq.com, datadoghq.eu, ap1.datadoghq.com, ap2.datadoghq.com, uk1.datadoghq.com, ddog-gov.com, us2.ddog-gov.com # Use a Personal Access Token or Service Access Token export DD_BEARER_TOKEN="" curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/annotation-queues" \ -H "Accept: application/json" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer ${DD_BEARER_TOKEN}" \ -d @- << EOF { "data": { "attributes": { "description": "Queue for annotating customer support traces", "name": "My annotation queue", "project_id": "00000000-0000-0000-0000-000000000002" }, "type": "queues" } } EOF ## Create queue with access controls # Set your Datadog site and credentials export DD_SITE="datadoghq.com" # Or us3.datadoghq.com, us5.datadoghq.com, datadoghq.eu, ap1.datadoghq.com, ap2.datadoghq.com, uk1.datadoghq.com, ddog-gov.com, us2.ddog-gov.com # Use a Personal Access Token or Service Access Token export DD_BEARER_TOKEN="" curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/annotation-queues" \ -H "Accept: application/json" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer ${DD_BEARER_TOKEN}" \ -d @- << EOF { "data": { "attributes": { "description": "Queue for annotating customer support traces", "name": "Restricted annotation queue", "project_id": "00000000-0000-0000-0000-000000000002", "restrict_to_assignees": false, "restrict_to_reviewers": true, "reviewer_emails": [ "reviewer@example.com" ] }, "type": "queues" } } EOF ## Create queue with annotation schema # Set your Datadog site and credentials export DD_SITE="datadoghq.com" # Or us3.datadoghq.com, us5.datadoghq.com, datadoghq.eu, ap1.datadoghq.com, ap2.datadoghq.com, uk1.datadoghq.com, ddog-gov.com, us2.ddog-gov.com # Use a Personal Access Token or Service Access Token export DD_BEARER_TOKEN="" curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/annotation-queues" \ -H "Accept: application/json" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer ${DD_BEARER_TOKEN}" \ -d @- << EOF { "data": { "attributes": { "annotation_schema": { "label_schemas": [ { "is_required": true, "max": 5, "min": 0, "name": "quality", "type": "score" }, { "name": "sentiment", "type": "categorical", "values": [ "positive", "negative", "neutral" ] } ] }, "description": "Queue for annotating customer support traces", "name": "My annotation queue", "project_id": "00000000-0000-0000-0000-000000000002" }, "type": "queues" } } EOF ``` {% /tab %} {% tab label="Go" %} ```go // Create an Agent Observability annotation queue returns "Created" 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.LLMObsAnnotationQueueRequest{ Data: datadogV2.LLMObsAnnotationQueueDataRequest{ Attributes: datadogV2.LLMObsAnnotationQueueDataAttributesRequest{ AnnotationSchema: &datadogV2.LLMObsAnnotationSchema{ LabelSchemas: []datadogV2.LLMObsLabelSchema{ { Description: datadog.PtrString("Rating of the response quality."), HasAssessment: datadog.PtrBool(false), HasReasoning: datadog.PtrBool(false), Id: datadog.PtrString("abc-123"), IsAssessment: datadog.PtrBool(false), IsInteger: datadog.PtrBool(false), IsRequired: datadog.PtrBool(true), Max: datadog.PtrFloat64(5.0), Min: datadog.PtrFloat64(0.0), Name: "quality", Type: datadogV2.LLMOBSLABELSCHEMATYPE_SCORE, Values: []string{ "good", "bad", "neutral", }, }, }, }, Description: datadog.PtrString("Queue for annotating customer support traces"), Name: "My annotation queue", ProjectId: "00000000-0000-0000-0000-000000000002", RestrictToAssignees: datadog.PtrBool(false), RestrictToReviewers: datadog.PtrBool(true), ReviewerEmails: []string{ "reviewer@example.com", }, }, Type: datadogV2.LLMOBSANNOTATIONQUEUETYPE_QUEUES, }, } ctx := datadog.NewDefaultContext(context.Background()) ctx = context.WithValue(ctx, datadog.ContextAccessToken, os.Getenv("DD_BEARER_TOKEN")) configuration := datadog.NewConfiguration() configuration.SetUnstableOperationEnabled("v2.CreateLLMObsAnnotationQueue", true) apiClient := datadog.NewAPIClient(configuration) api := datadogV2.NewAgentObservabilityApi(apiClient) resp, r, err := api.CreateLLMObsAnnotationQueue(ctx, body) if err != nil { fmt.Fprintf(os.Stderr, "Error when calling `AgentObservabilityApi.CreateLLMObsAnnotationQueue`: %v\n", err) fmt.Fprintf(os.Stderr, "Full HTTP response: %v\n", r) } responseContent, _ := json.MarshalIndent(resp, "", " ") fmt.Fprintf(os.Stdout, "Response from `AgentObservabilityApi.CreateLLMObsAnnotationQueue`:\n%s\n", responseContent) } ``` #### Instructions First [install the library and its dependencies](https://dnd37xeb23o8n.cloudfront.net/api/latest.md?code-lang=go) and then save the example to `main.go` and run following commands: ```bash DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" go run "main.go" ``` {% /tab %} {% tab label="Java" %} ```java // Create an Agent Observability annotation queue returns "Created" response import com.datadog.api.client.ApiClient; import com.datadog.api.client.ApiException; import com.datadog.api.client.v2.api.AgentObservabilityApi; import com.datadog.api.client.v2.model.LLMObsAnnotationQueueDataAttributesRequest; import com.datadog.api.client.v2.model.LLMObsAnnotationQueueDataRequest; import com.datadog.api.client.v2.model.LLMObsAnnotationQueueRequest; import com.datadog.api.client.v2.model.LLMObsAnnotationQueueResponse; import com.datadog.api.client.v2.model.LLMObsAnnotationQueueType; import com.datadog.api.client.v2.model.LLMObsAnnotationSchema; import com.datadog.api.client.v2.model.LLMObsLabelSchema; import com.datadog.api.client.v2.model.LLMObsLabelSchemaType; import java.util.Arrays; import java.util.Collections; public class Example { public static void main(String[] args) { ApiClient defaultClient = ApiClient.getDefaultApiClient(); defaultClient.setAccessToken(System.getenv("DD_BEARER_TOKEN")); defaultClient.setUnstableOperationEnabled("v2.createLLMObsAnnotationQueue", true); AgentObservabilityApi apiInstance = new AgentObservabilityApi(defaultClient); LLMObsAnnotationQueueRequest body = new LLMObsAnnotationQueueRequest() .data( new LLMObsAnnotationQueueDataRequest() .attributes( new LLMObsAnnotationQueueDataAttributesRequest() .annotationSchema( new LLMObsAnnotationSchema() .labelSchemas( Collections.singletonList( new LLMObsLabelSchema() .description("Rating of the response quality.") .hasAssessment(false) .hasReasoning(false) .id("abc-123") .isAssessment(false) .isInteger(false) .isRequired(true) .max(5.0) .name("quality") .type(LLMObsLabelSchemaType.SCORE) .values(Arrays.asList("good", "bad", "neutral"))))) .description("Queue for annotating customer support traces") .name("My annotation queue") .projectId("00000000-0000-0000-0000-000000000002") .restrictToAssignees(false) .restrictToReviewers(true) .reviewerEmails(Collections.singletonList("reviewer@example.com"))) .type(LLMObsAnnotationQueueType.QUEUES)); try { LLMObsAnnotationQueueResponse result = apiInstance.createLLMObsAnnotationQueue(body); System.out.println(result); } catch (ApiException e) { System.err.println( "Exception when calling AgentObservabilityApi#createLLMObsAnnotationQueue"); 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://dnd37xeb23o8n.cloudfront.net/api/latest.md?code-lang=java) and then save the example to `Example.java` and run following commands: ```bash DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" java "Example.java" ``` {% /tab %} {% tab label="Python" %} ```python """ Create an Agent Observability annotation queue returns "Created" response """ from os import environ from datadog_api_client import ApiClient, Configuration from datadog_api_client.v2.api.agent_observability_api import AgentObservabilityApi from datadog_api_client.v2.model.llm_obs_annotation_queue_data_attributes_request import ( LLMObsAnnotationQueueDataAttributesRequest, ) from datadog_api_client.v2.model.llm_obs_annotation_queue_data_request import LLMObsAnnotationQueueDataRequest from datadog_api_client.v2.model.llm_obs_annotation_queue_request import LLMObsAnnotationQueueRequest from datadog_api_client.v2.model.llm_obs_annotation_queue_type import LLMObsAnnotationQueueType from datadog_api_client.v2.model.llm_obs_annotation_schema import LLMObsAnnotationSchema from datadog_api_client.v2.model.llm_obs_label_schema import LLMObsLabelSchema from datadog_api_client.v2.model.llm_obs_label_schema_type import LLMObsLabelSchemaType body = LLMObsAnnotationQueueRequest( data=LLMObsAnnotationQueueDataRequest( attributes=LLMObsAnnotationQueueDataAttributesRequest( annotation_schema=LLMObsAnnotationSchema( label_schemas=[ LLMObsLabelSchema( description="Rating of the response quality.", has_assessment=False, has_reasoning=False, id="abc-123", is_assessment=False, is_integer=False, is_required=True, max=5.0, min=0.0, name="quality", type=LLMObsLabelSchemaType.SCORE, values=[ "good", "bad", "neutral", ], ), ], ), description="Queue for annotating customer support traces", name="My annotation queue", project_id="00000000-0000-0000-0000-000000000002", restrict_to_assignees=False, restrict_to_reviewers=True, reviewer_emails=[ "reviewer@example.com", ], ), type=LLMObsAnnotationQueueType.QUEUES, ), ) configuration = Configuration() configuration.access_token = environ["DD_BEARER_TOKEN"] configuration.unstable_operations["create_llm_obs_annotation_queue"] = True with ApiClient(configuration) as api_client: api_instance = AgentObservabilityApi(api_client) response = api_instance.create_llm_obs_annotation_queue(body=body) print(response) ``` #### Instructions First [install the library and its dependencies](https://dnd37xeb23o8n.cloudfront.net/api/latest.md?code-lang=python) and then save the example to `example.py` and run following commands: ```bash DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" python3 "example.py" ``` {% /tab %} {% tab label="Ruby" %} ```ruby # Create an Agent Observability annotation queue returns "Created" response require "datadog_api_client" DatadogAPIClient.configure do |config| config.access_token = ENV["DD_BEARER_TOKEN"] config.unstable_operations["v2.create_llm_obs_annotation_queue".to_sym] = true end api_instance = DatadogAPIClient::V2::AgentObservabilityAPI.new body = DatadogAPIClient::V2::LLMObsAnnotationQueueRequest.new({ data: DatadogAPIClient::V2::LLMObsAnnotationQueueDataRequest.new({ attributes: DatadogAPIClient::V2::LLMObsAnnotationQueueDataAttributesRequest.new({ annotation_schema: DatadogAPIClient::V2::LLMObsAnnotationSchema.new({ label_schemas: [ DatadogAPIClient::V2::LLMObsLabelSchema.new({ description: "Rating of the response quality.", has_assessment: false, has_reasoning: false, id: "abc-123", is_assessment: false, is_integer: false, is_required: true, max: 5.0, min: 0.0, name: "quality", type: DatadogAPIClient::V2::LLMObsLabelSchemaType::SCORE, values: [ "good", "bad", "neutral", ], }), ], }), description: "Queue for annotating customer support traces", name: "My annotation queue", project_id: "00000000-0000-0000-0000-000000000002", restrict_to_assignees: false, restrict_to_reviewers: true, reviewer_emails: [ "reviewer@example.com", ], }), type: DatadogAPIClient::V2::LLMObsAnnotationQueueType::QUEUES, }), }) p api_instance.create_llm_obs_annotation_queue(body) ``` #### Instructions First [install the library and its dependencies](https://dnd37xeb23o8n.cloudfront.net/api/latest.md?code-lang=ruby) and then save the example to `example.rb` and run following commands: ```bash DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" rb "example.rb" ``` {% /tab %} {% tab label="Rust" %} ```rust // Create an Agent Observability annotation queue returns "Created" response use datadog_api_client::datadog; use datadog_api_client::datadogV2::api_agent_observability::AgentObservabilityAPI; use datadog_api_client::datadogV2::model::LLMObsAnnotationQueueDataAttributesRequest; use datadog_api_client::datadogV2::model::LLMObsAnnotationQueueDataRequest; use datadog_api_client::datadogV2::model::LLMObsAnnotationQueueRequest; use datadog_api_client::datadogV2::model::LLMObsAnnotationQueueType; use datadog_api_client::datadogV2::model::LLMObsAnnotationSchema; use datadog_api_client::datadogV2::model::LLMObsLabelSchema; use datadog_api_client::datadogV2::model::LLMObsLabelSchemaType; #[tokio::main] async fn main() { let body = LLMObsAnnotationQueueRequest::new(LLMObsAnnotationQueueDataRequest::new( LLMObsAnnotationQueueDataAttributesRequest::new( "My annotation queue".to_string(), "00000000-0000-0000-0000-000000000002".to_string(), ) .annotation_schema(LLMObsAnnotationSchema::new(vec![LLMObsLabelSchema::new( "quality".to_string(), LLMObsLabelSchemaType::SCORE, ) .description("Rating of the response quality.".to_string()) .has_assessment(false) .has_reasoning(false) .id("abc-123".to_string()) .is_assessment(false) .is_integer(false) .is_required(true) .max(5.0 as f64) .min(0.0 as f64) .values(vec![ "good".to_string(), "bad".to_string(), "neutral".to_string(), ])])) .description("Queue for annotating customer support traces".to_string()) .restrict_to_assignees(false) .restrict_to_reviewers(true) .reviewer_emails(vec!["reviewer@example.com".to_string()]), LLMObsAnnotationQueueType::QUEUES, )); let mut configuration = datadog::Configuration::new(); configuration.set_unstable_operation_enabled("v2.create_llm_obs_annotation_queue", true); let api = AgentObservabilityAPI::with_config(configuration); let resp = api.create_llm_obs_annotation_queue(body).await; if let Ok(value) = resp { println!("{:#?}", value); } else { println!("{:#?}", resp.unwrap_err()); } } ``` #### Instructions First [install the library and its dependencies](https://dnd37xeb23o8n.cloudfront.net/api/latest.md?code-lang=rust) and then save the example to `src/main.rs` and run following commands: ```bash DD_SITE="datadoghq.com" DD_API_KEY="" DD_APP_KEY="" cargo run ``` {% /tab %} {% tab label="TypeScript" %} ```typescript /** * Create an Agent Observability annotation queue returns "Created" response */ import { client, v2 } from "@datadog/datadog-api-client"; const configuration = client.createConfiguration({ authMethods: { AuthZ: { accessToken: process.env.DD_BEARER_TOKEN as string, }, }, }); configuration.unstableOperations["v2.createLLMObsAnnotationQueue"] = true; const apiInstance = new v2.AgentObservabilityApi(configuration); const params: v2.AgentObservabilityApiCreateLLMObsAnnotationQueueRequest = { body: { data: { attributes: { annotationSchema: { labelSchemas: [ { description: "Rating of the response quality.", hasAssessment: false, hasReasoning: false, id: "abc-123", isAssessment: false, isInteger: false, isRequired: true, max: 5.0, min: 0.0, name: "quality", type: "score", values: ["good", "bad", "neutral"], }, ], }, description: "Queue for annotating customer support traces", name: "My annotation queue", projectId: "00000000-0000-0000-0000-000000000002", restrictToAssignees: false, restrictToReviewers: true, reviewerEmails: ["reviewer@example.com"], }, type: "queues", }, }, }; apiInstance .createLLMObsAnnotationQueue(params) .then((data: v2.LLMObsAnnotationQueueResponse) => { 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://dnd37xeb23o8n.cloudfront.net/api/latest.md?code-lang=typescript) and then save the example to `example.ts` and run following commands: ```bash DD_SITE="datadoghq.com" DD_BEARER_TOKEN="" tsc "example.ts" ``` {% /tab %} {% /tabs %}