Obter análise para seu projeto
As respostas às perguntas personalizadas usa o log de diagnóstico do Azure para armazenar os dados telemétricos e os logs de chat. Siga as etapas abaixo para executar consultas de exemplo para obter análises sobre o uso de seu projeto de respostas às perguntas personalizadas.
Habilite o log de diagnóstico para o seu recurso de idioma com respostas às perguntas personalizadas habilitadas.
Na etapa anterior, selecione Rastrear, além de Auditoria, RequestResponse e AllMetrics para registrar em log
Consultas do Kusto
Log de chat
// All QnA Traffic
AzureDiagnostics
| where ResourceProvider == "MICROSOFT.COGNITIVESERVICES"
| where OperationName=="CustomQuestionAnswering QueryKnowledgebases" // This OperationName is valid for custom question answering enabled resources
| extend answer_ = tostring(parse_json(properties_s).answer)
| extend question_ = tostring(parse_json(properties_s).question)
| extend score_ = tostring(parse_json(properties_s).score)
| extend kbId_ = tostring(parse_json(properties_s).kbId)
| project question_, answer_, score_, kbId_
Contagem de tráfego por base de dados de conhecimento e usuário em um período de tempo
// Traffic count per KB and user in a time period
let startDate = todatetime('2019-01-01');
let endDate = todatetime('2020-12-31');
AzureDiagnostics
| where ResourceProvider == "MICROSOFT.COGNITIVESERVICES"
| where OperationName=="CustomQuestionAnswering QueryKnowledgebases" // This OperationName is valid for custom question answering enabled resources
| where TimeGenerated <= endDate and TimeGenerated >=startDate
| extend kbId_ = tostring(parse_json(properties_s).kbId)
| extend userId_ = tostring(parse_json(properties_s).userId)
| summarize ChatCount=count() by bin(TimeGenerated, 1d), kbId_, userId_
Latência da API do GenerateAnswer
// Latency of GenerateAnswer
AzureDiagnostics
| where ResourceProvider == "MICROSOFT.COGNITIVESERVICES"
| where OperationName=="Generate Answer"
| project TimeGenerated, DurationMs
| render timechart
Latência média de todas as operações
// Average Latency of all operations
AzureDiagnostics
| where ResourceProvider == "MICROSOFT.COGNITIVESERVICES"
| project DurationMs, OperationName
| summarize count(), avg(DurationMs) by OperationName
| render barchart
Perguntas não respondidas
// All unanswered questions
AzureDiagnostics
| where ResourceProvider == "MICROSOFT.COGNITIVESERVICES"
| where OperationName=="CustomQuestionAnswering QueryKnowledgebases" // This OperationName is valid for custom question answering enabled resources
| extend answer_ = tostring(parse_json(properties_s).answer)
| extend question_ = tostring(parse_json(properties_s).question)
| extend score_ = tostring(parse_json(properties_s).score)
| extend kbId_ = tostring(parse_json(properties_s).kbId)
| where score_ == 0
| project question_, answer_, score_, kbId_
Chamadas de inferência predefinidas de respostas às perguntas personalizadas
// Show logs from AzureDiagnostics table
// Lists the latest logs in AzureDiagnostics table, sorted by time (latest first).
AzureDiagnostics
| where OperationName == "CustomQuestionAnswering QueryText"
| extend answer_ = tostring(parse_json(properties_s).answer)
| extend question_ = tostring(parse_json(properties_s).question)
| extend score_ = tostring(parse_json(properties_s).score)
| extend requestid = tostring(parse_json(properties_s)["apim-request-id"])
| project TimeGenerated, requestid, question_, answer_, score_