Tracing

Trace Ingestion

Creates a new trace on Confident AI.

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Request

uuidstringRequired
This is the unique identifier of the trace.
startTimestringRequiredformat: "date-time"
This is the time the trace started.
endTimestringRequiredformat: "date-time"
This is the time the trace ended.
namestringOptional
This is the name of the trace.
inputstringOptional
This is the input to the trace.
outputstringOptional
This is the output of the trace.
environmentenumOptional
This is the environment where your trace was posted, which helps with separating and debugging traces from different environments on the Confident AI platform.
Allowed values:
metadatamap from strings to anyOptional
This is any additional metadata associated with the trace.
tagslist of stringsOptional
This is any tags associated with the trace, which helps with grouping traces and filtering them on the Confident AI platform.
baseSpanslist of objectsOptional
This is the list of base spans associated with the trace.
llmSpanslist of objectsOptional
This is the list of LLM spans associated with the trace.
retrieverSpanslist of objectsOptional
This is the list of retriever spans associated with the trace.
toolSpanslist of objectsOptional
This is the list of tool spans associated with the trace.
agentSpanslist of objectsOptional
This is the list of agent spans associated with the trace.
threadIdstringOptional
This is the unique identifier of the thread associated with the trace.
userIdstringOptional
This is the unique identifier for your end user for the trace.
metricCollectionstringOptional
This is the metric collection you wish to use to evaluate the trace.
retrievalContextlist of stringsOptional
This is the retrieval context of your trace, which is to be used for evaluation.
contextlist of stringsOptional
This is the ideal retrieval context of your trace, which is to be used for evaluation.
expectedOutputstringOptional
This is the expected output of your trace, which is the ideal actual output and to be used for evaluation.
toolsCalledlist of objectsOptional
This is the tools called by your trace, which is to be used for evaluation.
expectedToolslist of objectsOptional
This is the expected tools to be called by the trace, which is to be used for evaluation.

Response

successboolean
A boolean indicating the success or failure of the API call
dataobject
This maps to the trace id.
deprecatedboolean
This is true if this endpoint is deprecated.