새로운 Agent Observability 프롬프트 버전 생성 - Agent Observability

경고Note: This endpoint is in preview and is subject to change. If you have any feedback, contact Datadog support.

POSThttps://api.datadoghq.com/api/v2/llm-obs/v1/prompts/{prompt_id}/versionshttps://api.us3.datadoghq.com/api/v2/llm-obs/v1/prompts/{prompt_id}/versionshttps://api.us5.datadoghq.com/api/v2/llm-obs/v1/prompts/{prompt_id}/versionshttps://api.datadoghq.eu/api/v2/llm-obs/v1/prompts/{prompt_id}/versionshttps://api.ap1.datadoghq.com/api/v2/llm-obs/v1/prompts/{prompt_id}/versionshttps://api.ap2.datadoghq.com/api/v2/llm-obs/v1/prompts/{prompt_id}/versionshttps://api.uk1.datadoghq.com/api/v2/llm-obs/v1/prompts/{prompt_id}/versionshttps://api.ddog-gov.com/api/v2/llm-obs/v1/prompts/{prompt_id}/versionshttps://api.us2.ddog-gov.com/api/v2/llm-obs/v1/prompts/{prompt_id}/versions

개요

기존 Agent Observability 프롬프트의 새 버전을 생성합니다.

This endpoint requires all of the following permissions:

llm_observability_read
llm_observability_write
feature_flag_config_read
feature_flag_config_write
feature_flag_environment_config_read

인수

경로 파라미터

이름

유형

설명

prompt_id [required]

string

The customer-provided identifier of the Agent Observability prompt.

요청

Body Data (required)

프롬프트 버전 페이로드를 생성합니다.

항목

유형

설명

data [required]

object

Agent Observability 프롬프트의 새 버전을 생성하도록 요청합니다.

attributes [required]

object

Attributes for creating a new version of an Agent Observability prompt. template is required; all other attributes are optional. If config is omitted, the latest version's configuration is carried forward. An explicit empty object clears it. Configuration authoring must be enabled for your organization to supply config. Otherwise, supplying it, including an empty object, returns HTTP 403. Omitting config still carries forward the latest configuration.

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.

description

string

Optional description of this version.

env_ids

[string]

Optional feature-flag environment UUIDs the service attempts to enable and configure to use this version as their default after creation.

labels

[string]

DEPRECATED Optional labels to attach to this version. Do not use this attribute for new integrations.

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.

user_version

string

Optional user-supplied version identifier for this version.

type [required]

enum

Resource type of an Agent Observability prompt version.

Allowed enum values: prompt-template-versions

{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "response_format": {
          "type": "json_object"
        },
        "temperature": 0.2
      },
      "description": "string",
      "env_ids": [],
      "labels": [],
      "template": {
        "description": "You are a helpful assistant for {{audience}}.",
        "minLength": "You are a helpful assistant for {{audience}}.",
        "pattern": "You are a helpful assistant for {{audience}}.",
        "type": "You are a helpful assistant for {{audience}}."
      },
      "user_version": "string"
    },
    "type": "prompt-template-versions"
  }
}

응답

Response containing a specific version of an Agent Observability prompt.

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>

config

object

created_at

date-time

Timestamp stored on this prompt version.

datasets

[object]

Datasets observed in runs associated with this prompt version.

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>

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"
  }
}

Bad Request

API error response.

항목

유형

설명

errors [required]

[object]

A list of errors.

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

Unauthorized

API error response.

항목

유형

설명

errors [required]

[object]

A list of errors.

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

Forbidden

API error response.

항목

유형

설명

errors [required]

[object]

A list of errors.

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

Not Found

API error response.

항목

유형

설명

errors [required]

[object]

A list of errors.

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

Too many requests

API error response.

항목

유형

설명

errors [required]

[string]

A list of errors.

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

코드 예시

새로운 Agent Observability 프롬프트 버전 생성

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us3.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us3.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us3.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us5.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us5.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us5.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="datadoghq.eu"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="datadoghq.eu"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="datadoghq.eu"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ap1.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ap1.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ap1.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ap2.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ap2.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ap2.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="uk1.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="uk1.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="uk1.datadoghq.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ddog-gov.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ddog-gov.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="ddog-gov.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes all or selected messages from other prompts

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us2.ddog-gov.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "template": {
        "messages": [
          {
            "include": {
              "prompt_id": "assistant-introduction",
              "version": 2
            }
          },
          {
            "include": {
              "items": [
                2,
                0,
                0
              ],
              "prompt_id": "response-examples",
              "version": 4
            }
          },
          {
            "content": "Answer {{question}}.",
            "role": "user"
          }
        ]
      }
    },
    "type": "prompt-template-versions"
  }
}
EOF

## Create a version that includes text from another prompt

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us2.ddog-gov.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "description": "Reuse the exact response policy.",
      "template": "{{>response-policy version=3}}\n\nAnswer {{question}}."
    },
    "type": "prompt-template-versions"
  }
}
EOF

## default

# Path parameters
export prompt_id="customer-support-assistant"

# Set your Datadog site and credentials
export DD_SITE="us2.ddog-gov.com"
# Use a Personal Access Token or Service Access Token
export DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>"

curl -X POST "https://api.${DD_SITE}/api/v2/llm-obs/v1/prompts/${prompt_id}/versions" \
-H "Accept: application/json" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-d @- << EOF
{
  "data": {
    "attributes": {
      "config": {
        "model": "provider-model",
        "temperature": 0.4
      },
      "description": "Give concise answers and cite relevant help-center articles.",
      "template": [
        {
          "content": "You are a helpful customer support assistant for {{company_name}}.",
          "role": "system"
        },
        {
          "content": "Help {{customer_name}} with this question: {{question}}",
          "role": "user"
        }
      ]
    },
    "type": "prompt-template-versions"
  }
}
EOF

새로운 Agent Observability 프롬프트 버전 생성

// Create a new Agent Observability prompt version 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.LLMObsCreatePromptVersionRequest{
		Data: datadogV2.LLMObsCreatePromptVersionData{
			Attributes: datadogV2.LLMObsCreatePromptVersionDataAttributes{
				Config: map[string]interface{}{
					"model":           "provider-model",
					"response_format": "{'type': 'json_object'}",
					"temperature":     0.2,
				},
				EnvIds: []string{},
				Labels: []datadogV2.LLMObsPromptVersionLabel{
					datadogV2.LLMOBSPROMPTVERSIONLABEL_PRODUCTION,
				},
				Template: datadogV2.LLMObsPromptTemplate{
					LLMObsPromptTextTemplate: datadog.PtrString("You are a helpful assistant for .")},
			},
			Type: datadogV2.LLMOBSPROMPTVERSIONTYPE_PROMPT_TEMPLATE_VERSIONS,
		},
	}
	ctx := datadog.NewDefaultContext(context.Background())
	ctx = context.WithValue(ctx, datadog.ContextAccessToken, os.Getenv("DD_BEARER_TOKEN"))
	configuration := datadog.NewConfiguration()
	configuration.SetUnstableOperationEnabled("v2.CreateLLMObsPromptVersion", true)
	apiClient := datadog.NewAPIClient(configuration)
	api := datadogV2.NewAgentObservabilityApi(apiClient)
	resp, r, err := api.CreateLLMObsPromptVersion(ctx, "prompt_id", body)

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

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

Instructions

First install the library and its dependencies and then save the example to main.go and run following commands:

DD_SITE="datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

DD_SITE="us3.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

DD_SITE="us5.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

DD_SITE="datadoghq.eu" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

DD_SITE="ap1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

DD_SITE="ap2.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

DD_SITE="uk1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

DD_SITE="ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

DD_SITE="us2.ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" go run "main.go"

새로운 Agent Observability 프롬프트 버전 생성

// Create a new Agent Observability prompt version returns "OK" 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.LLMObsCreatePromptVersionData;
import com.datadog.api.client.v2.model.LLMObsCreatePromptVersionDataAttributes;
import com.datadog.api.client.v2.model.LLMObsCreatePromptVersionRequest;
import com.datadog.api.client.v2.model.LLMObsPromptTemplate;
import com.datadog.api.client.v2.model.LLMObsPromptVersionLabel;
import com.datadog.api.client.v2.model.LLMObsPromptVersionResponse;
import com.datadog.api.client.v2.model.LLMObsPromptVersionType;
import java.util.Collections;
import java.util.Map;

public class Example {
  public static void main(String[] args) {
    ApiClient defaultClient = ApiClient.getDefaultApiClient();
    defaultClient.setAccessToken(System.getenv("DD_BEARER_TOKEN"));
    defaultClient.setUnstableOperationEnabled("v2.createLLMObsPromptVersion", true);
    AgentObservabilityApi apiInstance = new AgentObservabilityApi(defaultClient);

    LLMObsCreatePromptVersionRequest body =
        new LLMObsCreatePromptVersionRequest()
            .data(
                new LLMObsCreatePromptVersionData()
                    .attributes(
                        new LLMObsCreatePromptVersionDataAttributes()
                            .config(
                                Map.ofEntries(
                                    Map.entry("model", "provider-model"),
                                    Map.entry("response_format", "{'type': 'json_object'}"),
                                    Map.entry("temperature", "0.2")))
                            .labels(Collections.singletonList(LLMObsPromptVersionLabel.PRODUCTION))
                            .template(
                                new LLMObsPromptTemplate("You are a helpful assistant for .")))
                    .type(LLMObsPromptVersionType.PROMPT_TEMPLATE_VERSIONS));

    try {
      LLMObsPromptVersionResponse result =
          apiInstance.createLLMObsPromptVersion("customer-support-assistant", body);
      System.out.println(result);
    } catch (ApiException e) {
      System.err.println("Exception when calling AgentObservabilityApi#createLLMObsPromptVersion");
      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 and then save the example to Example.java and run following commands:

DD_SITE="datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

DD_SITE="us3.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

DD_SITE="us5.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

DD_SITE="datadoghq.eu" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

DD_SITE="ap1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

DD_SITE="ap2.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

DD_SITE="uk1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

DD_SITE="ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

DD_SITE="us2.ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" java "Example.java"

새로운 Agent Observability 프롬프트 버전 생성

"""
Create a new Agent Observability prompt version returns "OK" 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_create_prompt_version_data import LLMObsCreatePromptVersionData
from datadog_api_client.v2.model.llm_obs_create_prompt_version_data_attributes import (
    LLMObsCreatePromptVersionDataAttributes,
)
from datadog_api_client.v2.model.llm_obs_create_prompt_version_request import LLMObsCreatePromptVersionRequest
from datadog_api_client.v2.model.llm_obs_prompt_config import LLMObsPromptConfig
from datadog_api_client.v2.model.llm_obs_prompt_version_label import LLMObsPromptVersionLabel
from datadog_api_client.v2.model.llm_obs_prompt_version_type import LLMObsPromptVersionType

body = LLMObsCreatePromptVersionRequest(
    data=LLMObsCreatePromptVersionData(
        attributes=LLMObsCreatePromptVersionDataAttributes(
            config=LLMObsPromptConfig(
                [("model", "provider-model"), ("response_format", "{'type': 'json_object'}"), ("temperature", "0.2")]
            ),
            env_ids=[],
            labels=[
                LLMObsPromptVersionLabel.PRODUCTION,
            ],
            template="You are a helpful assistant for .",
        ),
        type=LLMObsPromptVersionType.PROMPT_TEMPLATE_VERSIONS,
    ),
)

configuration = Configuration()
configuration.access_token = environ["DD_BEARER_TOKEN"]
configuration.unstable_operations["create_llm_obs_prompt_version"] = True
with ApiClient(configuration) as api_client:
    api_instance = AgentObservabilityApi(api_client)
    response = api_instance.create_llm_obs_prompt_version(prompt_id="prompt_id", body=body)

    print(response)

Instructions

First install the library and its dependencies and then save the example to example.py and run following commands:

DD_SITE="datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

DD_SITE="us3.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

DD_SITE="us5.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

DD_SITE="datadoghq.eu" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

DD_SITE="ap1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

DD_SITE="ap2.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

DD_SITE="uk1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

DD_SITE="ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

DD_SITE="us2.ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" python3 "example.py"

새로운 Agent Observability 프롬프트 버전 생성

# Create a new Agent Observability prompt version returns "OK" response

require "datadog_api_client"
DatadogAPIClient.configure do |config|
  config.access_token = ENV["DD_BEARER_TOKEN"]
  config.unstable_operations["v2.create_llm_obs_prompt_version".to_sym] = true
end
api_instance = DatadogAPIClient::V2::AgentObservabilityAPI.new

body = DatadogAPIClient::V2::LLMObsCreatePromptVersionRequest.new({
  data: DatadogAPIClient::V2::LLMObsCreatePromptVersionData.new({
    attributes: DatadogAPIClient::V2::LLMObsCreatePromptVersionDataAttributes.new({
      config: DatadogAPIClient::V2::LLMObsPromptConfig.new({}),
      env_ids: [],
      labels: [
        DatadogAPIClient::V2::LLMObsPromptVersionLabel::PRODUCTION,
      ],
      template: "You are a helpful assistant for .",
    }),
    type: DatadogAPIClient::V2::LLMObsPromptVersionType::PROMPT_TEMPLATE_VERSIONS,
  }),
})
p api_instance.create_llm_obs_prompt_version("prompt_id", body)

Instructions

First install the library and its dependencies and then save the example to example.rb and run following commands:

DD_SITE="datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

DD_SITE="us3.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

DD_SITE="us5.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

DD_SITE="datadoghq.eu" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

DD_SITE="ap1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

DD_SITE="ap2.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

DD_SITE="uk1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

DD_SITE="ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

DD_SITE="us2.ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" rb "example.rb"

새로운 Agent Observability 프롬프트 버전 생성

// Create a new Agent Observability prompt version returns "OK" response
use datadog_api_client::datadog;
use datadog_api_client::datadogV2::api_agent_observability::AgentObservabilityAPI;
use datadog_api_client::datadogV2::model::LLMObsCreatePromptVersionData;
use datadog_api_client::datadogV2::model::LLMObsCreatePromptVersionDataAttributes;
use datadog_api_client::datadogV2::model::LLMObsCreatePromptVersionRequest;
use datadog_api_client::datadogV2::model::LLMObsPromptTemplate;
use datadog_api_client::datadogV2::model::LLMObsPromptVersionLabel;
use datadog_api_client::datadogV2::model::LLMObsPromptVersionType;
use serde_json::Value;
use std::collections::BTreeMap;

#[tokio::main]
async fn main() {
    let body = LLMObsCreatePromptVersionRequest::new(LLMObsCreatePromptVersionData::new(
        LLMObsCreatePromptVersionDataAttributes::new(
            LLMObsPromptTemplate::LLMObsPromptTextTemplate(
                "You are a helpful assistant for .".to_string(),
            ),
        )
        .config(BTreeMap::from([
            ("model".to_string(), Value::from("provider-model")),
            ("temperature".to_string(), Value::from(0.2)),
        ]))
        .env_ids(vec![])
        .labels(vec![LLMObsPromptVersionLabel::PRODUCTION]),
        LLMObsPromptVersionType::PROMPT_TEMPLATE_VERSIONS,
    ));
    let mut configuration = datadog::Configuration::new();
    configuration.set_unstable_operation_enabled("v2.create_llm_obs_prompt_version", true);
    let api = AgentObservabilityAPI::with_config(configuration);
    let resp = api
        .create_llm_obs_prompt_version("prompt_id".to_string(), body)
        .await;
    if let Ok(value) = resp {
        println!("{:#?}", value);
    } else {
        println!("{:#?}", resp.unwrap_err());
    }
}

Instructions

First install the library and its dependencies 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

DD_SITE="us3.datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run

DD_SITE="us5.datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run

DD_SITE="datadoghq.eu" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run

DD_SITE="ap1.datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run

DD_SITE="ap2.datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run

DD_SITE="uk1.datadoghq.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run

DD_SITE="ddog-gov.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run

DD_SITE="us2.ddog-gov.com" DD_API_KEY="<DD_API_KEY>" DD_APP_KEY="<DD_APP_KEY>" cargo run

새로운 Agent Observability 프롬프트 버전 생성

/**
 * Create a new Agent Observability prompt version returns "OK" 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.createLLMObsPromptVersion"] = true;
const apiInstance = new v2.AgentObservabilityApi(configuration);

const params: v2.AgentObservabilityApiCreateLLMObsPromptVersionRequest = {
  body: {
    data: {
      attributes: {
        config: {
          model: "provider-model",
          response_format: "{'type': 'json_object'}",
          temperature: "0.2",
        },
        envIds: [],
        labels: ["production"],
        template: "You are a helpful assistant for .",
      },
      type: "prompt-template-versions",
    },
  },
  promptId: "prompt_id",
};

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

Instructions

First install the library and its dependencies and then save the example to example.ts and run following commands:

DD_SITE="datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"

DD_SITE="us3.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"

DD_SITE="us5.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"

DD_SITE="datadoghq.eu" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"

DD_SITE="ap1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"

DD_SITE="ap2.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"

DD_SITE="uk1.datadoghq.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"

DD_SITE="ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"

DD_SITE="us2.ddog-gov.com" DD_BEARER_TOKEN="<PERSONAL_ACCESS_TOKEN OR SERVICE_ACCESS_TOKEN>" tsc "example.ts"