For AI agents: A markdown version of this page is available at https://dnd37xeb23o8n.cloudfront.net/jen.gilbert/astro-base/ko/api/latest/agent-observability/upload-records-to-an-agent-observability-dataset.md. A documentation index is available at /llms.txt.
homeHomedocs문서apiAPI
Language
Datadog site

Agent Observability 데이터 세트에 레코드 업로드하기

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/v2/{project_id}/datasets/{dataset_id}/records/uploadhttps://api.us3.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/uploadhttps://api.us5.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/uploadhttps://api.datadoghq.eu/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/uploadhttps://api.ap1.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/uploadhttps://api.ap2.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/uploadhttps://api.uk1.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/uploadhttps://api.ddog-gov.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/uploadhttps://api.us2.ddog-gov.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload

개요

파일에서 데이터 세트로 레코드를 업로드합니다. 이 요청은 단일 file 파트를 포함하는 multipart/form-data 업로드입니다. 현재는 CSV만 지원됩니다. CSV에는 input 열이 포함되어야 합니다. 선택적 열은 id, expected_output, metadata 및 tags입니다.

응답은 레코드가 처리되는 동안 진행 상황 업데이트를 내보내는 Server-Sent Events 스트림(text/event-stream)입니다. 스트림은 다음과 같은 명명된 이벤트를 내보냅니다.

  • progress: 지금까지 작성된 증분 레코드 수입니다.
  • completed: records_created를 포함하는 JSON 본문이 있는 터미널 이벤트입니다.
  • error: 오류 message를 포함하는 JSON 본문이 있는 터미널 이벤트입니다.

인수

경로 파라미터

이름
유형
설명
project_id [required]
string

The ID of the Agent Observability project.

dataset_id [required]
string

The ID of the Agent Observability dataset.

쿼리 문자열

이름
유형
설명
deduplicate
boolean

Whether to skip records whose input already exists in the dataset. Defaults to false.

Default: false
overwrite
boolean

Whether to overwrite existing records that share the same user-provided id. Defaults to true.

Default: true
tags
array

Tags to apply to every uploaded record, in addition to any tags defined on individual rows. Can be repeated, e.g. tags=env:prod&tags=team:ai.

include[user_data]
boolean

Whether to enrich the response with user metadata.

요청

Body Data (required)

레코드 파일이 포함된 멀티파트 업로드 페이로드입니다.

항목
유형
설명
file
binary

파일에서 데이터 세트 레코드를 업로드하기 위한 멀티파트 페이로드입니다.

응답

OK

코드 예시

Agent Observability 데이터 세트에 레코드 업로드하기
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string
# Path parameters
export project_id="a33671aa-24fd-4dcd-9b33-a8ec7dde7751"
export dataset_id="9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"

# 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.${DD_SITE}/api/v2/llm-obs/v2/${project_id}/datasets/${dataset_id}/records/upload" \
-H "Accept: application/json" \
-H "Content-Type: multipart/form-data" \
-H "Authorization: Bearer ${DD_BEARER_TOKEN}" \
-F file=@string