Create Testrecord
Create a new Testrecord
Authorizations
Path Parameters
The ID of the Run to create the Testrecord in.
123
Body
13
124
The user query that was executed for the testrecord.
"What is the moon made of?"
The context that was used while generating the testrecord.
"After the Apollo missions, we know the moon is made of cheese."
The response generated by the model.
"The moon is made of cheese."
The ideal response.
"The moon is made of rock."
The prompt used to generate the response.
"You are a helpful assistant. Use the provided context to answer the user query."
The model parameters used to generate the response.
{
"isCustom": false,
"maxTokens": 2048,
"modelName": "gpt-4-1106-preview",
"temperature": 0,
"topP": 0.9
}
Debug information generated by Scorecard during the execution of the testrecord.
{
"completion_token_count": 92,
"latency_seconds": 3.23607873916626,
"prompt_token_count": 28,
"total_cost": 0.00304,
"total_token_count": 120
}
The error message for the testrecord.
"Error generating a model response."
Response
15
The creation date and time of the testrecord.
"2025-02-06T00:05:50.146678"
The ID of the run the testrecord belongs to.
334
The ID of the testset the testrecord belongs to.
13
The ID of the testcase the testrecord belongs to.
124
The user query for the testrecord.
"What is the moon made of?"
The context for the testrecord.
"After the Apollo missions, we know the moon is made of cheese."
The actual response of the model for the testrecord.
"The moon is made of cheese."
The ideal response for the testrecord.
"The moon is made of rock."
The current status of the testrecord.
"awaiting_scoring"
The prompt used to generate the testrecord.
"You are a helpful assistant. Use the provided context to answer the user query."
The model parameters used when generating the testrecord.
{
"isCustom": false,
"maxTokens": 2048,
"modelName": "gpt-4-1106-preview",
"temperature": 0,
"topP": 0.9
}
Debug information produced during the testrecord's generation.
{
"completion_token_count": 92,
"latency_seconds": 3.23607873916626,
"prompt_token_count": 28,
"total_cost": 0.00304,
"total_token_count": 120
}
The error message for the testrecord.
"Error generating a model response."
Was this page helpful?