public static async Task Run(Stream blobStream, string name, TraceWriter log)
{
log.Info($"Processing blob:{name}");
// parse the document to extract images
IEnumerable <PageImage> pages = DocumentParser.Parse(blobStream).Pages;
// create and apply the skill set to create annotations
SkillSet <PageImage> skillSet = CreateCognitiveSkillSet();
var annotations = await skillSet.ApplyAsync(pages);
// Commit them to Cosmos DB to be used by full corpus skills such as Topics
await cosmosDb.SaveAsync(annotations);
// index the annotated document with azure search
AnnotatedDocument document = new AnnotatedDocument(annotations.Select(a => a.Get <AnnotatedPage>("page-metadata")));
var searchDocument = new SearchDocument(name)
{
Metadata = document.Metadata,
Text = document.Text,
LinkedEntities = annotations
.SelectMany(a => a.Get <EntityLink[]>("linked-entities") ?? new EntityLink[0])
.GroupBy(l => l.Name)
.OrderByDescending(g => g.Max(l => l.Score))
.Select(l => l.Key)
.ToList(),
};
var batch = IndexBatch.MergeOrUpload(new[] { searchDocument });
var result = await indexClient.Documents.IndexAsync(batch);
if (!result.Results[0].Succeeded)
{
log.Error($"index failed for {name}: {result.Results[0].ErrorMessage}");
}
}
private static async Task <IEnumerable <Annotation> > ProcessDocument(Stream blobStream)
{
// parse the document to extract images
IEnumerable <PageImage> pages = DocumentParser.Parse(blobStream).Pages;
// create and apply the skill set to create annotations
SkillSet <PageImage> skillSet = CreateCognitiveSkillSet();
var annotations = await skillSet.ApplyAsync(pages);
return(annotations);
}
