运行评测兼容接口
curl --request POST \
--url http://localhost:8000/dev/apps/{app_name}/eval_sets/{eval_set_id}/run_eval \
--header 'Content-Type: application/json' \
--data '
{
"evalMetrics": [
{
"metricName": "tool_trajectory_avg_score",
"threshold": 1
}
]
}
'import requests
url = "http://localhost:8000/dev/apps/{app_name}/eval_sets/{eval_set_id}/run_eval"
payload = { "evalMetrics": [
{
"metricName": "tool_trajectory_avg_score",
"threshold": 1
}
] }
headers = {"Content-Type": "application/json"}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify({evalMetrics: [{metricName: 'tool_trajectory_avg_score', threshold: 1}]})
};
fetch('http://localhost:8000/dev/apps/{app_name}/eval_sets/{eval_set_id}/run_eval', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));[
{
"evalSetFile": "<string>",
"evalSetId": "<string>",
"evalId": "<string>",
"finalEvalStatus": 1,
"overallEvalMetricResults": [
{
"metricName": "<string>",
"evalStatus": 1,
"threshold": 123,
"criterion": {
"threshold": 123,
"includeIntermediateResponsesInFinal": false
},
"customFunctionPath": "<string>",
"score": 123,
"details": {
"rubricScores": [
{
"rubricId": "<string>",
"rationale": "<string>",
"score": 123
}
]
}
}
],
"evalMetricResultPerInvocation": [
{
"actualInvocation": {
"userContent": {
"parts": [
{
"mediaResolution": {
"level": "MEDIA_RESOLUTION_UNSPECIFIED",
"numTokens": 123
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "<string>",
"id": "<string>"
},
"executableCode": {
"code": "<string>",
"language": "LANGUAGE_UNSPECIFIED",
"id": "<string>"
},
"fileData": {
"displayName": "<string>",
"fileUri": "<string>",
"mimeType": "<string>"
},
"functionCall": {
"id": "<string>",
"args": {},
"name": "<string>",
"partialArgs": [
{
"boolValue": true,
"jsonPath": "<string>",
"nullValue": "NULL_VALUE",
"numberValue": 123,
"stringValue": "<string>",
"willContinue": true
}
],
"willContinue": true
},
"functionResponse": {
"willContinue": true,
"scheduling": "SCHEDULING_UNSPECIFIED",
"parts": [
{
"inlineData": {
"mimeType": "<string>",
"data": "<string>",
"displayName": "<string>"
},
"fileData": {
"fileUri": "<string>",
"mimeType": "<string>",
"displayName": "<string>"
}
}
],
"id": "<string>",
"name": "<string>",
"response": {}
},
"inlineData": {
"data": "<string>",
"displayName": "<string>",
"mimeType": "<string>"
},
"text": "<string>",
"thought": true,
"thoughtSignature": "<string>",
"videoMetadata": {
"endOffset": "<string>",
"fps": 123,
"startOffset": "<string>"
},
"toolCall": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"args": {}
},
"toolResponse": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"response": {}
},
"partMetadata": {}
}
],
"role": "<string>"
},
"invocationId": "",
"finalResponse": {
"parts": [
{
"mediaResolution": {
"level": "MEDIA_RESOLUTION_UNSPECIFIED",
"numTokens": 123
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "<string>",
"id": "<string>"
},
"executableCode": {
"code": "<string>",
"language": "LANGUAGE_UNSPECIFIED",
"id": "<string>"
},
"fileData": {
"displayName": "<string>",
"fileUri": "<string>",
"mimeType": "<string>"
},
"functionCall": {
"id": "<string>",
"args": {},
"name": "<string>",
"partialArgs": [
{
"boolValue": true,
"jsonPath": "<string>",
"nullValue": "NULL_VALUE",
"numberValue": 123,
"stringValue": "<string>",
"willContinue": true
}
],
"willContinue": true
},
"functionResponse": {
"willContinue": true,
"scheduling": "SCHEDULING_UNSPECIFIED",
"parts": [
{
"inlineData": {
"mimeType": "<string>",
"data": "<string>",
"displayName": "<string>"
},
"fileData": {
"fileUri": "<string>",
"mimeType": "<string>",
"displayName": "<string>"
}
}
],
"id": "<string>",
"name": "<string>",
"response": {}
},
"inlineData": {
"data": "<string>",
"displayName": "<string>",
"mimeType": "<string>"
},
"text": "<string>",
"thought": true,
"thoughtSignature": "<string>",
"videoMetadata": {
"endOffset": "<string>",
"fps": 123,
"startOffset": "<string>"
},
"toolCall": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"args": {}
},
"toolResponse": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"response": {}
},
"partMetadata": {}
}
],
"role": "<string>"
},
"intermediateData": {
"toolUses": [],
"toolResponses": [],
"intermediateResponses": []
},
"creationTimestamp": 0,
"rubrics": [
{
"rubricId": "<string>",
"rubricContent": {
"textProperty": "<string>"
},
"description": "<string>",
"type": "<string>"
}
],
"appDetails": {
"agentDetails": {}
}
},
"expectedInvocation": {
"userContent": {
"parts": [
{
"mediaResolution": {
"level": "MEDIA_RESOLUTION_UNSPECIFIED",
"numTokens": 123
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "<string>",
"id": "<string>"
},
"executableCode": {
"code": "<string>",
"language": "LANGUAGE_UNSPECIFIED",
"id": "<string>"
},
"fileData": {
"displayName": "<string>",
"fileUri": "<string>",
"mimeType": "<string>"
},
"functionCall": {
"id": "<string>",
"args": {},
"name": "<string>",
"partialArgs": [
{
"boolValue": true,
"jsonPath": "<string>",
"nullValue": "NULL_VALUE",
"numberValue": 123,
"stringValue": "<string>",
"willContinue": true
}
],
"willContinue": true
},
"functionResponse": {
"willContinue": true,
"scheduling": "SCHEDULING_UNSPECIFIED",
"parts": [
{
"inlineData": {
"mimeType": "<string>",
"data": "<string>",
"displayName": "<string>"
},
"fileData": {
"fileUri": "<string>",
"mimeType": "<string>",
"displayName": "<string>"
}
}
],
"id": "<string>",
"name": "<string>",
"response": {}
},
"inlineData": {
"data": "<string>",
"displayName": "<string>",
"mimeType": "<string>"
},
"text": "<string>",
"thought": true,
"thoughtSignature": "<string>",
"videoMetadata": {
"endOffset": "<string>",
"fps": 123,
"startOffset": "<string>"
},
"toolCall": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"args": {}
},
"toolResponse": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"response": {}
},
"partMetadata": {}
}
],
"role": "<string>"
},
"invocationId": "",
"finalResponse": {
"parts": [
{
"mediaResolution": {
"level": "MEDIA_RESOLUTION_UNSPECIFIED",
"numTokens": 123
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "<string>",
"id": "<string>"
},
"executableCode": {
"code": "<string>",
"language": "LANGUAGE_UNSPECIFIED",
"id": "<string>"
},
"fileData": {
"displayName": "<string>",
"fileUri": "<string>",
"mimeType": "<string>"
},
"functionCall": {
"id": "<string>",
"args": {},
"name": "<string>",
"partialArgs": [
{
"boolValue": true,
"jsonPath": "<string>",
"nullValue": "NULL_VALUE",
"numberValue": 123,
"stringValue": "<string>",
"willContinue": true
}
],
"willContinue": true
},
"functionResponse": {
"willContinue": true,
"scheduling": "SCHEDULING_UNSPECIFIED",
"parts": [
{
"inlineData": {
"mimeType": "<string>",
"data": "<string>",
"displayName": "<string>"
},
"fileData": {
"fileUri": "<string>",
"mimeType": "<string>",
"displayName": "<string>"
}
}
],
"id": "<string>",
"name": "<string>",
"response": {}
},
"inlineData": {
"data": "<string>",
"displayName": "<string>",
"mimeType": "<string>"
},
"text": "<string>",
"thought": true,
"thoughtSignature": "<string>",
"videoMetadata": {
"endOffset": "<string>",
"fps": 123,
"startOffset": "<string>"
},
"toolCall": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"args": {}
},
"toolResponse": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"response": {}
},
"partMetadata": {}
}
],
"role": "<string>"
},
"intermediateData": {
"toolUses": [],
"toolResponses": [],
"intermediateResponses": []
},
"creationTimestamp": 0,
"rubrics": [
{
"rubricId": "<string>",
"rubricContent": {
"textProperty": "<string>"
},
"description": "<string>",
"type": "<string>"
}
],
"appDetails": {
"agentDetails": {}
}
},
"evalMetricResults": []
}
],
"userId": "<string>",
"sessionId": "<string>",
"evalMetricResults": []
}
]{
"detail": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}兼容接口
运行评测兼容接口
deprecated
直接返回逐用例评测结果数组
仅在启用开发界面的服务中可用,例如 veadk web 或 adk api_server --with_ui;默认 adk api_server 不提供此接口
POST
/
dev
/
apps
/
{app_name}
/
eval_sets
/
{eval_set_id}
/
run_eval
运行评测兼容接口
curl --request POST \
--url http://localhost:8000/dev/apps/{app_name}/eval_sets/{eval_set_id}/run_eval \
--header 'Content-Type: application/json' \
--data '
{
"evalMetrics": [
{
"metricName": "tool_trajectory_avg_score",
"threshold": 1
}
]
}
'import requests
url = "http://localhost:8000/dev/apps/{app_name}/eval_sets/{eval_set_id}/run_eval"
payload = { "evalMetrics": [
{
"metricName": "tool_trajectory_avg_score",
"threshold": 1
}
] }
headers = {"Content-Type": "application/json"}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify({evalMetrics: [{metricName: 'tool_trajectory_avg_score', threshold: 1}]})
};
fetch('http://localhost:8000/dev/apps/{app_name}/eval_sets/{eval_set_id}/run_eval', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));[
{
"evalSetFile": "<string>",
"evalSetId": "<string>",
"evalId": "<string>",
"finalEvalStatus": 1,
"overallEvalMetricResults": [
{
"metricName": "<string>",
"evalStatus": 1,
"threshold": 123,
"criterion": {
"threshold": 123,
"includeIntermediateResponsesInFinal": false
},
"customFunctionPath": "<string>",
"score": 123,
"details": {
"rubricScores": [
{
"rubricId": "<string>",
"rationale": "<string>",
"score": 123
}
]
}
}
],
"evalMetricResultPerInvocation": [
{
"actualInvocation": {
"userContent": {
"parts": [
{
"mediaResolution": {
"level": "MEDIA_RESOLUTION_UNSPECIFIED",
"numTokens": 123
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "<string>",
"id": "<string>"
},
"executableCode": {
"code": "<string>",
"language": "LANGUAGE_UNSPECIFIED",
"id": "<string>"
},
"fileData": {
"displayName": "<string>",
"fileUri": "<string>",
"mimeType": "<string>"
},
"functionCall": {
"id": "<string>",
"args": {},
"name": "<string>",
"partialArgs": [
{
"boolValue": true,
"jsonPath": "<string>",
"nullValue": "NULL_VALUE",
"numberValue": 123,
"stringValue": "<string>",
"willContinue": true
}
],
"willContinue": true
},
"functionResponse": {
"willContinue": true,
"scheduling": "SCHEDULING_UNSPECIFIED",
"parts": [
{
"inlineData": {
"mimeType": "<string>",
"data": "<string>",
"displayName": "<string>"
},
"fileData": {
"fileUri": "<string>",
"mimeType": "<string>",
"displayName": "<string>"
}
}
],
"id": "<string>",
"name": "<string>",
"response": {}
},
"inlineData": {
"data": "<string>",
"displayName": "<string>",
"mimeType": "<string>"
},
"text": "<string>",
"thought": true,
"thoughtSignature": "<string>",
"videoMetadata": {
"endOffset": "<string>",
"fps": 123,
"startOffset": "<string>"
},
"toolCall": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"args": {}
},
"toolResponse": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"response": {}
},
"partMetadata": {}
}
],
"role": "<string>"
},
"invocationId": "",
"finalResponse": {
"parts": [
{
"mediaResolution": {
"level": "MEDIA_RESOLUTION_UNSPECIFIED",
"numTokens": 123
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "<string>",
"id": "<string>"
},
"executableCode": {
"code": "<string>",
"language": "LANGUAGE_UNSPECIFIED",
"id": "<string>"
},
"fileData": {
"displayName": "<string>",
"fileUri": "<string>",
"mimeType": "<string>"
},
"functionCall": {
"id": "<string>",
"args": {},
"name": "<string>",
"partialArgs": [
{
"boolValue": true,
"jsonPath": "<string>",
"nullValue": "NULL_VALUE",
"numberValue": 123,
"stringValue": "<string>",
"willContinue": true
}
],
"willContinue": true
},
"functionResponse": {
"willContinue": true,
"scheduling": "SCHEDULING_UNSPECIFIED",
"parts": [
{
"inlineData": {
"mimeType": "<string>",
"data": "<string>",
"displayName": "<string>"
},
"fileData": {
"fileUri": "<string>",
"mimeType": "<string>",
"displayName": "<string>"
}
}
],
"id": "<string>",
"name": "<string>",
"response": {}
},
"inlineData": {
"data": "<string>",
"displayName": "<string>",
"mimeType": "<string>"
},
"text": "<string>",
"thought": true,
"thoughtSignature": "<string>",
"videoMetadata": {
"endOffset": "<string>",
"fps": 123,
"startOffset": "<string>"
},
"toolCall": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"args": {}
},
"toolResponse": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"response": {}
},
"partMetadata": {}
}
],
"role": "<string>"
},
"intermediateData": {
"toolUses": [],
"toolResponses": [],
"intermediateResponses": []
},
"creationTimestamp": 0,
"rubrics": [
{
"rubricId": "<string>",
"rubricContent": {
"textProperty": "<string>"
},
"description": "<string>",
"type": "<string>"
}
],
"appDetails": {
"agentDetails": {}
}
},
"expectedInvocation": {
"userContent": {
"parts": [
{
"mediaResolution": {
"level": "MEDIA_RESOLUTION_UNSPECIFIED",
"numTokens": 123
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "<string>",
"id": "<string>"
},
"executableCode": {
"code": "<string>",
"language": "LANGUAGE_UNSPECIFIED",
"id": "<string>"
},
"fileData": {
"displayName": "<string>",
"fileUri": "<string>",
"mimeType": "<string>"
},
"functionCall": {
"id": "<string>",
"args": {},
"name": "<string>",
"partialArgs": [
{
"boolValue": true,
"jsonPath": "<string>",
"nullValue": "NULL_VALUE",
"numberValue": 123,
"stringValue": "<string>",
"willContinue": true
}
],
"willContinue": true
},
"functionResponse": {
"willContinue": true,
"scheduling": "SCHEDULING_UNSPECIFIED",
"parts": [
{
"inlineData": {
"mimeType": "<string>",
"data": "<string>",
"displayName": "<string>"
},
"fileData": {
"fileUri": "<string>",
"mimeType": "<string>",
"displayName": "<string>"
}
}
],
"id": "<string>",
"name": "<string>",
"response": {}
},
"inlineData": {
"data": "<string>",
"displayName": "<string>",
"mimeType": "<string>"
},
"text": "<string>",
"thought": true,
"thoughtSignature": "<string>",
"videoMetadata": {
"endOffset": "<string>",
"fps": 123,
"startOffset": "<string>"
},
"toolCall": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"args": {}
},
"toolResponse": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"response": {}
},
"partMetadata": {}
}
],
"role": "<string>"
},
"invocationId": "",
"finalResponse": {
"parts": [
{
"mediaResolution": {
"level": "MEDIA_RESOLUTION_UNSPECIFIED",
"numTokens": 123
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "<string>",
"id": "<string>"
},
"executableCode": {
"code": "<string>",
"language": "LANGUAGE_UNSPECIFIED",
"id": "<string>"
},
"fileData": {
"displayName": "<string>",
"fileUri": "<string>",
"mimeType": "<string>"
},
"functionCall": {
"id": "<string>",
"args": {},
"name": "<string>",
"partialArgs": [
{
"boolValue": true,
"jsonPath": "<string>",
"nullValue": "NULL_VALUE",
"numberValue": 123,
"stringValue": "<string>",
"willContinue": true
}
],
"willContinue": true
},
"functionResponse": {
"willContinue": true,
"scheduling": "SCHEDULING_UNSPECIFIED",
"parts": [
{
"inlineData": {
"mimeType": "<string>",
"data": "<string>",
"displayName": "<string>"
},
"fileData": {
"fileUri": "<string>",
"mimeType": "<string>",
"displayName": "<string>"
}
}
],
"id": "<string>",
"name": "<string>",
"response": {}
},
"inlineData": {
"data": "<string>",
"displayName": "<string>",
"mimeType": "<string>"
},
"text": "<string>",
"thought": true,
"thoughtSignature": "<string>",
"videoMetadata": {
"endOffset": "<string>",
"fps": 123,
"startOffset": "<string>"
},
"toolCall": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"args": {}
},
"toolResponse": {
"id": "<string>",
"toolType": "TOOL_TYPE_UNSPECIFIED",
"response": {}
},
"partMetadata": {}
}
],
"role": "<string>"
},
"intermediateData": {
"toolUses": [],
"toolResponses": [],
"intermediateResponses": []
},
"creationTimestamp": 0,
"rubrics": [
{
"rubricId": "<string>",
"rubricContent": {
"textProperty": "<string>"
},
"description": "<string>",
"type": "<string>"
}
],
"appDetails": {
"agentDetails": {}
}
},
"evalMetricResults": []
}
],
"userId": "<string>",
"sessionId": "<string>",
"evalMetricResults": []
}
]{
"detail": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}此接口已废弃,直接返回逐用例结果数组。新接口将该数组放在
完整调用条件与新接口见对应评测接口
runEvalResults 中,其他评测前提与执行影响相同
评测会重新调用模型与工具,可能产生费用和外部操作
请求体
application/json
响应
请求成功
评测集 ID
评测用例 ID
最终评测状态
可用选项:
1, 2, 3 用例级指标结果
Show child attributes
Show child attributes
逐调用指标结果
Show child attributes
Show child attributes
用户 ID
会话 ID
最后修改于 2026年9月19日