private async Task <List <ScoreRecord> > InspectModelRegistration()
{
var results = new List <ScoreRecord>();
log.LogTrace($"Checking that a Model has been registered for each document type");
var documentTypesForChallenge = Environment.GetEnvironmentVariable("DocumentTypesForChallenge").Split(',').ToList();
foreach (var documentType in documentTypesForChallenge)
{
log.LogTrace($"Checking {documentType}");
var mtr = HorusSql.GetModelIdByDocumentFormat(documentType);
if (mtr.DocumentFormat != null)
{
log.LogTrace($"Model {mtr.ModelId} has been registered for {documentType}");
results.Add(new ScoreRecord {
Type = $"Training", Notes = $"{mtr.ModelId} has been registered for document type {documentType}", Score = 500
});
}
}
return(results);
}
public async Task <DocumentProcessingJob> StartRecognizer([ActivityTrigger] DocumentProcessingJob job, ILogger log, Microsoft.Azure.WebJobs.ExecutionContext ec)
{
var snip = $"Orchestration { job.OrchestrationId}: { ec.FunctionName} - ";
var model = HorusSql.GetModelIdByDocumentFormat(job.DocumentFormat);
job.Model = model;
log.LogTrace($"{snip} Document Name={job.DocumentName}, Format={job.DocumentFormat}, Model={model.ModelId}, Version={model.ModelVersion}");
var queryString = HttpUtility.ParseQueryString(string.Empty);
queryString["includeTextDetails"] = "True";
var uri = $"{recognizerServiceBaseUrl}{BaseConstants.FormRecognizerApiPath}/{model.ModelId}/{BaseConstants.FormRecognizerAnalyzeVerb}?{queryString}";
log.LogTrace($"{snip} Recognizer Uri={uri}");
HttpResponseMessage response;
byte[] image = null;
byte[] md5hash = null;
var orchestrationBlob = await orchestrationBlobClient.GetBlobReferenceFromServerAsync(new Uri(job.OrchestrationBlobUrl));
using (var memoryStream = new MemoryStream())
{
await orchestrationBlob.DownloadToStreamAsync(memoryStream);
image = memoryStream.ToArray();
using (var md5 = MD5.Create())
{
memoryStream.Position = 0;
md5hash = md5.ComputeHash(memoryStream);
}
}
job.Thumbprint = BitConverter.ToString(md5hash).Replace("-", " ");
log.LogTrace($"{snip} Orchestration Blob={job.OrchestrationBlobName} downloaded. Thumbprint={job.Thumbprint}");
client.DefaultRequestHeaders.Add("Ocp-Apim-Subscription-Key", recognizerApiKey);
using (var postContent = new ByteArrayContent(image))
{
postContent.Headers.ContentType = new MediaTypeHeaderValue(job.ContentType);
response = await client.PostAsync(uri, postContent);
}
string getUrl = "";
if (response.IsSuccessStatusCode)
{
log.LogTrace($"{snip} Recognition request successful.");
HttpHeaders headers = response.Headers;
if (headers.TryGetValues("operation-location", out IEnumerable <string> values))
{
getUrl = values.First();
log.LogTrace($"{snip} Recognition progress can be tracked at {getUrl}");
}
}
else
{
log.LogTrace($"{snip} Recognition request unsuccessful.");
throw new Exception($"{snip} That didnt work. Trying to submit image for analysis {uri} Content:{response.Content.ReadAsStringAsync().Result}");
}
job.RecognizerStatusUrl = getUrl;
log.LogInformation($"{snip} Completed successfully");
return(job);
}