Create Golden

POSThttps://api.confident-ai.com/v1/datasets/{alias}/goldens

Creates a single golden in the dataset identified by alias. The dataset's type (single- or multi-turn) determines how the golden is interpreted. Optionally target a specific datasetVersion; omitting it uses the latest version.

POST/v1/datasets/{alias}/goldens

curl -X POST "https://api.confident-ai.com/v1/datasets/{alias}/goldens" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>" \
  -H "Content-Type: application/json" \
  -d '{
  "golden": {
    "input": "What is the capital of France?",
    "expectedOutput": "Paris.",
    "finalized": true
  }
}'

200

{
  "success": true,
  "data": {
    "id": "golden-id"
  },
  "link": "https://app.confident-ai.com/project/<PROJECT-ID>/datasets/<DATASET-ID>",
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Path parameters

aliasstringRequired
The alias of the dataset to add the golden to.

Request body

goldenobject | objectRequired
The golden to create. Provide single-turn or multi-turn fields matching the dataset type.
Show 2 variantsHide 2 variants
- GoldenRequestDataobject
  Show 13 propertiesHide 13 properties
  - inputstringRequired
    The input to your LLM application.
  - actualOutputstring
    The actual output from your LLM application.
  - expectedOutputstring
    The ideal output from your LLM application.
  - retrievalContextlist of strings
    The retrieval context used by your LLM application.
  - contextlist of strings
    The ideal retrieval context for your LLM application.
  - toolsCalledlist of objects
    The tools called by your LLM application.
    Show 5 propertiesHide 5 properties
    namestringRequired
    This is the name of the tool.
    descriptionstringRequired
    This is the description of the tool.
    inputParametersobject
    This is the input parameters that are passed to the tool.
    outputstring
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - expectedToolslist of objects
    The tools expected to be called by your LLM application.
    Show 5 propertiesHide 5 properties
    namestringRequired
    This is the name of the tool.
    descriptionstringRequired
    This is the description of the tool.
    inputParametersobject
    This is the input parameters that are passed to the tool.
    outputstring
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - additionalMetadataobject
    Additional metadata to associate with the golden.
  - commentsstring
    Comments to associate with the golden.
  - sourceFilestring
    The source file associated with the golden.
  - finalizedboolean
    Whether the golden is ready to use in evaluations.
  - customColumnKeyValuesobject
    Custom dataset column values keyed by column name.
  - tagslist of strings
    Tags to associate with the golden.
- OR
- ConversationalGoldenRequestDataobject
  Show 11 propertiesHide 11 properties
  - scenariostringRequired
    A description of the conversation context.
  - userDescriptionstring
    A description of the user in the conversation.
  - expectedOutcomestring
    The ideal outcome or conversation flow.
  - turnslist of objects
    The conversation turns.
    Show 5 propertiesHide 5 properties
    roleenumRequired
    The role of the turn, either user or assistant.
    Show 2 enum valuesHide 2 enum values
    user
    assistant
    contentstringRequired
    The message content of the turn.
    userIdstring
    The user ID associated with the turn.
    retrievalContextlist of strings
    The contexts retrieved to generate the LLM response for this turn.
    toolsCalledlist of objects
    The tools called to generate the LLM response for this turn.
    Show 5 propertiesHide 5 properties
    namestringRequired
    This is the name of the tool.
    descriptionstringRequired
    This is the description of the tool.
    inputParametersobject
    This is the input parameters that are passed to the tool.
    outputstring
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - contextlist of strings
    Context for the conversation.
  - additionalMetadataobject
    Additional metadata to associate with the golden.
  - commentsstring
    Comments to associate with the golden.
  - sourceFilestring
    The source file associated with the golden.
  - finalizedboolean
    Whether the golden is ready to use in evaluations.
  - customColumnKeyValuesobject
    Custom dataset column values keyed by column name.
  - tagslist of strings
    Tags to associate with the golden.
datasetVersionstring
Optional dataset version to add the golden to. Omitting it targets the latest version (or unversioned if the dataset has no versions).

Response

The golden was created successfully.

successboolean
This is true if the golden was successfully created.
dataobject
Show 1 propertyHide 1 property
- idstring
  This is the ID of the created golden.
linkstring
A link to the dataset the golden belongs to.
deprecatedboolean
This is true if this datasets endpoint is deprecated.

Built byConfident AI