curl --request POST \
--url https://api.egp.scale.com/v5/evaluations/filter \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"filters": [
{
"key": "<string>",
"operator": "==",
"value": "<string>",
"object": "metadata_filter"
}
]
}
'{
"items": [
{
"id": "<string>",
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"created_by": {
"id": "<string>",
"type": "user",
"object": "identity"
},
"tags": [
"<string>"
],
"datasets": [
{
"id": "<string>",
"created_by": {
"id": "<string>",
"type": "user",
"object": "identity"
},
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"tags": [
"<string>"
],
"current_version_num": 123,
"object": "dataset",
"description": "<string>",
"archived_at": "2023-11-07T05:31:56Z"
}
],
"status": "failed",
"object": "evaluation",
"description": "<string>",
"archived_at": "2023-11-07T05:31:56Z",
"status_reason": "<string>",
"progress": {
"workflows": {
"total": 123,
"completed": 123,
"failed": 123,
"pending": 123
},
"items": {
"total": 123,
"successful": 123,
"failed": 123,
"pending": 123,
"failed_items": []
}
},
"tasks": [
{
"configuration": {
"model": "<string>",
"messages": [
{}
],
"top_k": 123,
"frequency_penalty": 123,
"function_call": {},
"functions": [
{}
],
"logit_bias": {},
"logprobs": true,
"max_completion_tokens": 123,
"max_tokens": 123,
"metadata": {},
"modalities": [
"<string>"
],
"n": 123,
"parallel_tool_calls": true,
"prediction": {},
"presence_penalty": 123,
"reasoning_effort": "<string>",
"response_format": {},
"seed": 123,
"stop": "<string>",
"store": true,
"temperature": 123,
"tool_choice": "<string>",
"tools": [
{}
],
"top_logprobs": 123,
"top_p": 123,
"audio": {}
},
"task_type": "chat_completion",
"alias": "chat_completion"
}
],
"metadata": {}
}
],
"total": 123,
"has_more": true,
"object": "list",
"limit": 100
}Filter evaluations using metadata and other criteria. Supports up to 10 filters with AND logic.
curl --request POST \
--url https://api.egp.scale.com/v5/evaluations/filter \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"filters": [
{
"key": "<string>",
"operator": "==",
"value": "<string>",
"object": "metadata_filter"
}
]
}
'{
"items": [
{
"id": "<string>",
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"created_by": {
"id": "<string>",
"type": "user",
"object": "identity"
},
"tags": [
"<string>"
],
"datasets": [
{
"id": "<string>",
"created_by": {
"id": "<string>",
"type": "user",
"object": "identity"
},
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"tags": [
"<string>"
],
"current_version_num": 123,
"object": "dataset",
"description": "<string>",
"archived_at": "2023-11-07T05:31:56Z"
}
],
"status": "failed",
"object": "evaluation",
"description": "<string>",
"archived_at": "2023-11-07T05:31:56Z",
"status_reason": "<string>",
"progress": {
"workflows": {
"total": 123,
"completed": 123,
"failed": 123,
"pending": 123
},
"items": {
"total": 123,
"successful": 123,
"failed": 123,
"pending": 123,
"failed_items": []
}
},
"tasks": [
{
"configuration": {
"model": "<string>",
"messages": [
{}
],
"top_k": 123,
"frequency_penalty": 123,
"function_call": {},
"functions": [
{}
],
"logit_bias": {},
"logprobs": true,
"max_completion_tokens": 123,
"max_tokens": 123,
"metadata": {},
"modalities": [
"<string>"
],
"n": 123,
"parallel_tool_calls": true,
"prediction": {},
"presence_penalty": 123,
"reasoning_effort": "<string>",
"response_format": {},
"seed": 123,
"stop": "<string>",
"store": true,
"temperature": 123,
"tool_choice": "<string>",
"tools": [
{}
],
"top_logprobs": 123,
"top_p": 123,
"audio": {}
},
"task_type": "chat_completion",
"alias": "chat_completion"
}
],
"metadata": {}
}
],
"total": 123,
"has_more": true,
"object": "list",
"limit": 100
}tasks 1 <= x <= 1000asc, desc Request model for filtering evaluations
List of metadata filters to apply (maximum 10)
10Show child attributes
The metadata key to filter on
The comparison operator to use
==, !=, >=, <=, IN, NOT_IN The value to compare against (string for all types)
"metadata_filter"Successful Response
Show child attributes
The tags associated with the entity
Show child attributes
The tags associated with the entity
"dataset"failed, completed, running "evaluation"Reason for evaluation status
Progress of the evaluation's underlying async job
Show child attributes
Show child attributes
Tasks executed during evaluation. Populated with optional task view.
Show child attributes
Show child attributes
"chat_completion"Alias to title the results column. Defaults to the chat_completion
Metadata key-value pairs for the evaluation
The total of items that match the query. This is greater than or equal to the number of items returned.
Whether there are more items left to be fetched.
"list"The maximum number of items to return.