Response containing a specific version of an Agent Observability prompt.
Expand All
항목
유형
설명
data [required]
object
Data object for a specific version of an Agent Observability prompt.
attributes [required]
object
Attributes of a specific version of an Agent Observability prompt. For a composed version, authoring_template contains its pinned include-bearing source; ordinary versions omit that attribute. Empty config is omitted when configuration authoring is disabled for the organization. Non-empty saved configuration is always returned.
author
string
UUID of the user who authored this version.
authoring_template
<oneOf>
A text template, a list of chat messages and named message placeholders, or an authored chat object. Text can include an exact prompt version with {{>prompt-id version=N}}; other text, including {{>...}} sequences without a version, remains literal. Use an authored chat object when including prompts as chat messages.
Preview: Prompt composition is available in Preview. To request access, contact Datadog Support or your Customer Success Manager.
Without access, inline references remain literal text and structured includes are unsupported. Previously compiled prompt versions remain available for execution.
Preview: Message placeholders are available in Preview. To request access, contact Datadog Support or your Customer Success Manager.
Object 1
string
A text prompt template.
Object 2
[ <oneOf>]
A chat prompt template containing messages and optional named message placeholders.
Preview: Message placeholders are available in Preview. To request access, contact Datadog Support or your Customer Success Manager.
Object 1
object
A single chat message in a prompt template.
content [required]
string
Content of the message.
role [required]
string
Role of the message (for example system, user, or assistant).
<type=placeholder>
object
A named placeholder that inserts a list of messages when a compatible SDK formats the prompt.
Preview: Message placeholders are available in Preview. To request access, contact Datadog Support or your Customer Success Manager.
name [required]
string
Name used to supply the message list when formatting the prompt.
type [required]
enum
Type of chat-template item.
Allowed enum values: placeholder
Object 3
object
A chat prompt whose authored items are stored under messages.
messages [required]
[ <oneOf>]
A chat prompt containing messages, references to specific versions of other prompts, or both.
Object 1
object
A single chat message in a prompt template.
content [required]
string
Content of the message.
role [required]
string
Role of the message (for example system, user, or assistant).
Object 2
object
Includes all or selected messages from a specific version of another prompt.
include [required]
object
Includes messages from a specific version of another prompt. Omitting items includes every message from that version in its original order. When items is present, messages are included in the specified order, including repetitions.
items
[integer]
Zero-based indexes of messages from the included prompt. For example, [2, 0, 0] includes the third message, followed by the first message twice. Omit this field to include all messages in their original order.
prompt_id [required]
string
Customer-provided identifier of the included prompt.
version [required]
int64
Positive sequential version number of the included prompt.
config
object
Versioned prompt configuration is in Preview. To request access, contact Datadog Support or your Customer Success Manager. Customer-owned configuration delivered with a prompt version. Datadog stores and returns the object without interpolating it, validating provider-specific keys, or applying it to model calls. Do not include secrets.
created_at
date-time
Timestamp stored on this prompt version.
datasets
[object]
Datasets observed in runs associated with this prompt version.
id [required]
string
Unique identifier of the dataset.
name
string
Name of the dataset.
description
string
Description of this version.
labels
[string]
DEPRECATED: Labels attached to this version (for example development, staging, production).
last_seen_at
date-time
Timestamp of the most recent observed run of this prompt version.
ml_app
string
The ML application this prompt is associated with.
ml_apps
[string]
ML applications observed running this prompt version.
prompt_id [required]
string
Customer-provided identifier of the parent prompt.
prompt_uuid [required]
string
Unique identifier of the parent prompt.
tags
[string]
Tags observed on runs of this prompt version.
template [required]
<oneOf>
A text template, a list of chat messages and named message placeholders, or an authored chat object. Text can include an exact prompt version with {{>prompt-id version=N}}; other text, including {{>...}} sequences without a version, remains literal. Use an authored chat object when including prompts as chat messages.
Preview: Prompt composition is available in Preview. To request access, contact Datadog Support or your Customer Success Manager.
Without access, inline references remain literal text and structured includes are unsupported. Previously compiled prompt versions remain available for execution.
Preview: Message placeholders are available in Preview. To request access, contact Datadog Support or your Customer Success Manager.
Object 1
string
A text prompt template.
Object 2
[ <oneOf>]
A chat prompt template containing messages and optional named message placeholders.
Preview: Message placeholders are available in Preview. To request access, contact Datadog Support or your Customer Success Manager.
Object 1
object
A single chat message in a prompt template.
content [required]
string
Content of the message.
role [required]
string
Role of the message (for example system, user, or assistant).
<type=placeholder>
object
A named placeholder that inserts a list of messages when a compatible SDK formats the prompt.
Preview: Message placeholders are available in Preview. To request access, contact Datadog Support or your Customer Success Manager.
name [required]
string
Name used to supply the message list when formatting the prompt.
type [required]
enum
Type of chat-template item.
Allowed enum values: placeholder
Object 3
object
A chat prompt whose authored items are stored under messages.
messages [required]
[ <oneOf>]
A chat prompt containing messages, references to specific versions of other prompts, or both.
Object 1
object
A single chat message in a prompt template.
content [required]
string
Content of the message.
role [required]
string
Role of the message (for example system, user, or assistant).
Object 2
object
Includes all or selected messages from a specific version of another prompt.
include [required]
object
Includes messages from a specific version of another prompt. Omitting items includes every message from that version in its original order. When items is present, messages are included in the specified order, including repetitions.
items
[integer]
Zero-based indexes of messages from the included prompt. For example, [2, 0, 0] includes the third message, followed by the first message twice. Omit this field to include all messages in their original order.
prompt_id [required]
string
Customer-provided identifier of the included prompt.
version [required]
int64
Positive sequential version number of the included prompt.
user_version
string
User-supplied identifier for this version.
version [required]
int64
Sequential version number.
version_created_at
date-time
Timestamp when this version was created.
id [required]
string
Unique identifier of the prompt version.
type [required]
enum
Resource type of an Agent Observability prompt version.
Allowed enum values: prompt-template-versions
{"data":{"attributes":{"author":"3b12f1df-14fd-4e12-bd6f-4a2f5c8b3d1e","config":{},"created_at":"2025-02-01T14:30:00Z","description":"Give concise answers and cite relevant help-center articles.","prompt_id":"customer-support-assistant","prompt_uuid":"4a1a28ff-8a25-5f0f-946f-f48264d772eb","template":[{"content":"You are a helpful customer support assistant for {{company_name}}.","role":"system"},{"content":"Help {{customer_name}} with this question: {{question}}","role":"user"}],"version":2,"version_created_at":"2025-02-01T14:30:00Z"},"id":"d83ab666-61cc-5545-a83b-2424bb85467b","type":"prompt-template-versions"}}
# Path parameters exportprompt_id="customer-support-assistant" exportversion="1" # Use a Personal Access Token or Service Access Token exportDD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"
"""
Get a specific Agent Observability prompt version returns "OK" response
"""fromosimportenvironfromdatadog_api_clientimportApiClient,Configurationfromdatadog_api_client.v2.api.agent_observability_apiimportAgentObservabilityApiconfiguration=Configuration()configuration.access_token=environ["DD_BEARER_TOKEN"]configuration.unstable_operations["get_llm_obs_prompt_version"]=TruewithApiClient(configuration)asapi_client:api_instance=AgentObservabilityApi(api_client)response=api_instance.get_llm_obs_prompt_version(prompt_id="prompt_id",version=9223372036854775807,)print(response)
DD_SITE="datadoghq.comus3.datadoghq.comus5.datadoghq.comdatadoghq.euap1.datadoghq.comap2.datadoghq.comuk1.datadoghq.comddog-gov.comus2.ddog-gov.com"DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"python3"example.py"
# Get a specific Agent Observability prompt version returns "OK" responserequire"datadog_api_client"DatadogAPIClient.configuredo|config|config.access_token=ENV["DD_BEARER_TOKEN"]config.unstable_operations["v2.get_llm_obs_prompt_version".to_sym]=trueendapi_instance=DatadogAPIClient::V2::AgentObservabilityAPI.newpapi_instance.get_llm_obs_prompt_version("prompt_id",9223372036854775807)
DD_SITE="datadoghq.comus3.datadoghq.comus5.datadoghq.comdatadoghq.euap1.datadoghq.comap2.datadoghq.comuk1.datadoghq.comddog-gov.comus2.ddog-gov.com"DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"rb"example.rb"
// Get a specific Agent Observability prompt version returns "OK" responsepackagemainimport("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")funcmain(){ctx:=datadog.NewDefaultContext(context.Background())ctx=context.WithValue(ctx,datadog.ContextAccessToken,os.Getenv("DD_BEARER_TOKEN"))configuration:=datadog.NewConfiguration()configuration.SetUnstableOperationEnabled("v2.GetLLMObsPromptVersion",true)apiClient:=datadog.NewAPIClient(configuration)api:=datadogV2.NewAgentObservabilityApi(apiClient)resp,r,err:=api.GetLLMObsPromptVersion(ctx,"prompt_id",9223372036854775807)iferr!=nil{fmt.Fprintf(os.Stderr,"Error when calling `AgentObservabilityApi.GetLLMObsPromptVersion`: %v\n",err)fmt.Fprintf(os.Stderr,"Full HTTP response: %v\n",r)}responseContent,_:=json.MarshalIndent(resp,""," ")fmt.Fprintf(os.Stdout,"Response from `AgentObservabilityApi.GetLLMObsPromptVersion`:\n%s\n",responseContent)}
DD_SITE="datadoghq.comus3.datadoghq.comus5.datadoghq.comdatadoghq.euap1.datadoghq.comap2.datadoghq.comuk1.datadoghq.comddog-gov.comus2.ddog-gov.com"DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"go run"main.go"
// Get a specific Agent Observability prompt version returns "OK" responseimportcom.datadog.api.client.ApiClient;importcom.datadog.api.client.ApiException;importcom.datadog.api.client.v2.api.AgentObservabilityApi;importcom.datadog.api.client.v2.model.LLMObsPromptVersionResponse;publicclassExample{publicstaticvoidmain(String[]args){ApiClientdefaultClient=ApiClient.getDefaultApiClient();defaultClient.setAccessToken(System.getenv("DD_BEARER_TOKEN"));defaultClient.setUnstableOperationEnabled("v2.getLLMObsPromptVersion",true);AgentObservabilityApiapiInstance=newAgentObservabilityApi(defaultClient);try{LLMObsPromptVersionResponseresult=apiInstance.getLLMObsPromptVersion("customer-support-assistant",1L);System.out.println(result);}catch(ApiExceptione){System.err.println("Exception when calling AgentObservabilityApi#getLLMObsPromptVersion");System.err.println("Status code: "+e.getCode());System.err.println("Reason: "+e.getResponseBody());System.err.println("Response headers: "+e.getResponseHeaders());e.printStackTrace();}}}
DD_SITE="datadoghq.comus3.datadoghq.comus5.datadoghq.comdatadoghq.euap1.datadoghq.comap2.datadoghq.comuk1.datadoghq.comddog-gov.comus2.ddog-gov.com"DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"java"Example.java"
// Get a specific Agent Observability prompt version returns "OK" response
usedatadog_api_client::datadog;usedatadog_api_client::datadogV2::api_agent_observability::AgentObservabilityAPI;#[tokio::main]asyncfnmain(){letmutconfiguration=datadog::Configuration::new();configuration.set_unstable_operation_enabled("v2.GetLLMObsPromptVersion",true);letapi=AgentObservabilityAPI::with_config(configuration);letresp=api.get_llm_obs_prompt_version("prompt_id".to_string(),9223372036854775807).await;ifletOk(value)=resp{println!("{:#?}",value);}else{println!("{:#?}",resp.unwrap_err());}}
DD_SITE="datadoghq.comus3.datadoghq.comus5.datadoghq.comdatadoghq.euap1.datadoghq.comap2.datadoghq.comuk1.datadoghq.comddog-gov.comus2.ddog-gov.com"DD_API_KEY="<DD_API_KEY>"DD_APP_KEY="<DD_APP_KEY>"cargo run
/**
* Get a specific Agent Observability prompt version returns "OK" response
*/import{client,v2}from"@datadog/datadog-api-client";constconfiguration=client.createConfiguration({authMethods:{AuthZ:{accessToken: process.env.DD_BEARER_TOKENasstring,},},});configuration.unstableOperations["v2.getLLMObsPromptVersion"]=true;constapiInstance=newv2.AgentObservabilityApi(configuration);constparams: v2.AgentObservabilityApiGetLLMObsPromptVersionRequest={promptId:"prompt_id",version: 9223372036854775807,};apiInstance.getLLMObsPromptVersion(params).then((data: v2.LLMObsPromptVersionResponse)=>{console.log("API called successfully. Returned data: "+JSON.stringify(data));}).catch((error: any)=>console.error(error));
DD_SITE="datadoghq.comus3.datadoghq.comus5.datadoghq.comdatadoghq.euap1.datadoghq.comap2.datadoghq.comuk1.datadoghq.comddog-gov.comus2.ddog-gov.com"DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"tsc"example.ts"
맞춤형 데모 요청
Datadog 시작하기
Ask AI
AI-generated responses may be inaccurate. Verify important info.