--- title: Agent Observability 데이터 세트에 레코드 업로드하기 description: 파일에서 데이터 세트로 레코드를 업로드합니다. 이 요청은 단일 file 파트를 포함하는 multipart/form-data 업로드입니다. 현재는 CSV만 지원됩니다. breadcrumbs: 문서 > API > Agent Observability 데이터 세트에 레코드 업로드하기 --- > For the complete documentation index, see [llms.txt](https://dnd37xeb23o8n.cloudfront.net/jen.gilbert/astro-base/llms.txt). # Agent Observability 데이터 세트에 레코드 업로드하기 ## 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/v2/{project_id}/datasets/{dataset_id}/records/upload | | us3.datadoghq.com | POST https://api.us3.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload | | us5.datadoghq.com | POST https://api.us5.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload | | app.datadoghq.eu | POST https://api.datadoghq.eu/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload | | ap1.datadoghq.com | POST https://api.ap1.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload | | ap2.datadoghq.com | POST https://api.ap2.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload | | uk1.datadoghq.com | POST https://api.uk1.datadoghq.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload | | app.ddog-gov.com | POST https://api.ddog-gov.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload | | us2.ddog-gov.com | POST https://api.us2.ddog-gov.com/api/v2/llm-obs/v2/{project_id}/datasets/{dataset_id}/records/upload | ### Overview 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 `tags`입니다. 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_created`를 포함하는 JSON 본문이 있는 터미널 이벤트입니다. - `error`: 오류 `message`를 포함하는 JSON 본문이 있는 터미널 이벤트입니다. ### Arguments #### Path Parameters | Field | Type | Description | | ----------------------- | ------ | ------------------------------------------ | | project_id [*required*] | string | The ID of the Agent Observability project. | | dataset_id [*required*] | string | The ID of the Agent Observability dataset. | #### Query Strings | Field | Type | Description | | ------------------ | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | | 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. | ### Request #### Body Data (required) 레코드 파일이 포함된 멀티파트 업로드 페이로드입니다. {% tabs %} {% tab label="Model" %} | Field | Type | Description | | ----- | ------ | --------------------------------------- | | file | binary | 파일에서 데이터 세트 레코드를 업로드하기 위한 멀티파트 페이로드입니다. | {% /tab %} {% tab label="Example" %} ```bash -F 'file=@records.csv' ``` {% /tab %} {% /tabs %} ### Response {% tabs %} {% tab label="200" %} OK {% /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="404" %} Not Found {% 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 %} {% tab label="500" %} Internal Server Error {% 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 %} {% /tabs %} ### Code Example {% tabs %} {% tab label="Curl" %} ```bash # 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" # 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.${DD_SITE}/api/v2/llm-obs/v2/${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 ``` {% /tab %} {% tab label="Go" %} ```go // Upload records to an Agent Observability dataset returns "OK" response package main import ( "context" "fmt" "os" "github.com/DataDog/datadog-api-client-go/v2/api/datadog" "github.com/DataDog/datadog-api-client-go/v2/api/datadogV2" ) func main() { ctx := datadog.NewDefaultContext(context.Background()) ctx = context.WithValue(ctx, datadog.ContextAccessToken, os.Getenv("DD_BEARER_TOKEN")) configuration := datadog.NewConfiguration() configuration.SetUnstableOperationEnabled("v2.UploadLLMObsDatasetRecordsFile", true) apiClient := datadog.NewAPIClient(configuration) api := datadogV2.NewAgentObservabilityApi(apiClient) r, err := api.UploadLLMObsDatasetRecordsFile(ctx, "project_id", "dataset_id", *datadogV2.NewUploadLLMObsDatasetRecordsFileOptionalParameters()) if err != nil { fmt.Fprintf(os.Stderr, "Error when calling `AgentObservabilityApi.UploadLLMObsDatasetRecordsFile`: %v\n", err) fmt.Fprintf(os.Stderr, "Full HTTP response: %v\n", r) } } ``` #### 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 // Upload records to an Agent Observability dataset returns "OK" response import com.datadog.api.client.ApiClient; import com.datadog.api.client.ApiException; import com.datadog.api.client.v2.api.AgentObservabilityApi; public class Example { public static void main(String[] args) { ApiClient defaultClient = ApiClient.getDefaultApiClient(); defaultClient.setAccessToken(System.getenv("DD_BEARER_TOKEN")); defaultClient.setUnstableOperationEnabled("v2.uploadLLMObsDatasetRecordsFile", true); AgentObservabilityApi apiInstance = new AgentObservabilityApi(defaultClient); try { apiInstance.uploadLLMObsDatasetRecordsFile( "a33671aa-24fd-4dcd-9b33-a8ec7dde7751", "9f64e5c7-dc5a-45c8-a17c-1b85f0bec97d"); } catch (ApiException e) { System.err.println( "Exception when calling AgentObservabilityApi#uploadLLMObsDatasetRecordsFile"); 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 """ Upload records to an Agent Observability dataset 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 configuration = Configuration() configuration.access_token = environ["DD_BEARER_TOKEN"] configuration.unstable_operations["upload_llm_obs_dataset_records_file"] = True with ApiClient(configuration) as api_client: api_instance = AgentObservabilityApi(api_client) api_instance.upload_llm_obs_dataset_records_file( project_id="project_id", dataset_id="dataset_id", ) ``` #### 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 # Upload records to an Agent Observability dataset returns "OK" response require "datadog_api_client" DatadogAPIClient.configure do |config| config.access_token = ENV["DD_BEARER_TOKEN"] config.unstable_operations["v2.upload_llm_obs_dataset_records_file".to_sym] = true end api_instance = DatadogAPIClient::V2::AgentObservabilityAPI.new p api_instance.upload_llm_obs_dataset_records_file("project_id", "dataset_id") ``` #### 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 // Upload records to an Agent Observability dataset returns "OK" response use datadog_api_client::datadog; use datadog_api_client::datadogV2::api_agent_observability::AgentObservabilityAPI; use datadog_api_client::datadogV2::api_agent_observability::UploadLLMObsDatasetRecordsFileOptionalParams; #[tokio::main] async fn main() { let mut configuration = datadog::Configuration::new(); configuration.set_unstable_operation_enabled("v2.upload_llm_obs_dataset_records_file", true); let api = AgentObservabilityAPI::with_config(configuration); let resp = api .upload_llm_obs_dataset_records_file( "project_id".to_string(), "dataset_id".to_string(), UploadLLMObsDatasetRecordsFileOptionalParams::default(), ) .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 /** * Upload records to an Agent Observability dataset 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.uploadLLMObsDatasetRecordsFile"] = true; const apiInstance = new v2.AgentObservabilityApi(configuration); const params: v2.AgentObservabilityApiUploadLLMObsDatasetRecordsFileRequest = { projectId: "project_id", datasetId: "dataset_id", }; apiInstance .uploadLLMObsDatasetRecordsFile(params) .then((data: any) => { 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 %}