Multimodal ContentAnalysis for .NET

var model = LM.LoadFromModelID("phi-3.5-mini");
var classifier = new Categorization(model);

// Define your categories
var categories = new[] {
    "Technical Support",
    "Billing Inquiry",
    "Feature Request",
    "General Feedback"
};

// Classify incoming text
int result = classifier.GetBestCategory(
    categories,
    "My payment didn't go through");

Console.WriteLine(categories[result]);
// Output: Billing Inquiry

// Or classify an image
var attachment = new Attachment("screenshot.png");
int imgResult = classifier.GetBestCategory(
    categories, attachment);

var model = LM.LoadFromModelID("phi-3.5-mini");
var ner = new NamedEntityRecognition(model);

// Define entity types to extract
ner.EntityDefinitions.Add(new EntityDefinition(
    NamedEntityType.Person));
ner.EntityDefinitions.Add(new EntityDefinition(
    NamedEntityType.Organization));
ner.EntityDefinitions.Add(new EntityDefinition(
    "Product", "Product names mentioned"));

string text = "John Smith joined Microsoft to lead " +
              "the Azure AI division in Seattle.";

var entities = ner.ExtractEntities(text);

foreach (var entity in entities)
{
    Console.WriteLine(
        $"{entity.Type}: {entity.Value}");
    foreach (var occ in entity.Occurrences)
        Console.WriteLine($"  at [{occ.Start}]");
}

var model = LM.LoadFromModelID("nomic-embed-text");
var embedder = new Embedder(model);

// Generate text embeddings
float[] queryVec = await embedder.GetEmbeddingsAsync(
    "machine learning algorithms");

// Batch embed multiple texts
var docs = new[] { "AI overview", "Neural networks" };
float[][] docVecs = await embedder.GetEmbeddingsAsync(docs);

// Calculate similarity
float sim = Embedder.GetCosineSimilarity(
    queryVec, docVecs[0]);

// Image embeddings
var visionModel = LM.LoadFromModelID("nomic-embed-vision");
var imgEmbedder = new Embedder(visionModel);

var image = new Attachment("photo.jpg");
float[] imgVec = await imgEmbedder.GetEmbeddingsAsync(
    image);