Local AI in .NET.
No Python. No API key.

using System.Numerics.Tensors;
using Microsoft.Extensions.AI;
using Starlings.Models.E5;
using Starlings.Models.E5.Extensions.AI;

// One-time download, pinned by commit and checked by SHA-256. Inference never touches the network.
E5ModelFiles files = await E5ModelAssets.DownloadAsync();
using var embedder = E5EmbeddingGenerator.Create(files);

// e5 expects "passage: " on documents and "query: " on queries.
string[] docs = ["passage: The Eiffel Tower is in Paris.",
                 "passage: Der Rhein fließt durch Köln.",
                 "passage: 富士山は日本一高い山です。"];
var docVectors = await embedder.GenerateAsync(docs);
var query = await embedder.GenerateVectorAsync("query: Which river runs through Cologne?");

foreach (var (doc, v) in docs.Zip(docVectors))
    Console.WriteLine($"{TensorPrimitives.CosineSimilarity(query.Span, v.Vector.Span):F3}  {doc}");

using Microsoft.Extensions.AI;
using Starlings.Models.Qwen35;
using Starlings.Models.Qwen35.Extensions.AI;

Qwen35ModelFiles files = await Qwen35ModelAssets.DownloadAsync(Qwen35Variant.Fp32x); // about 3 GB, once
using IChatClient chat = Qwen35ChatClient.Create(files);

await foreach (var update in chat.GetStreamingResponseAsync("In one sentence, why is the sky blue?"))
    Console.Write(update.Text);

var getWeather = AIFunctionFactory.Create((string city) => $"18 C and sunny in {city}.",
    "get_weather", "Get the current weather for a city.");
using IChatClient agent = new ChatClientBuilder(chat).UseFunctionInvocation().Build();

ChatResponse answer = await agent.GetResponseAsync("What is the weather in Paris today?", new ChatOptions { Tools = [getWeather] });
Console.WriteLine(answer.Text);

using Starlings.Models.Gliner2;

Gliner2ModelFiles files = await Gliner2ModelAssets.DownloadAsync();
using var extractor = Gliner2EntityExtractor.Create(files);

var result = extractor.Extract("Tim Cook announced the iPhone 15 in Cupertino.", ["person", "product", "city"]);
foreach (var e in result.Entities)
    Console.WriteLine($"{e.Label}: {e.Text} [{e.Start}, {e.End}) {e.Confidence:F2}");

using System.Numerics.Tensors;
using Starlings.Models.EmbeddingGemma2;
using Starlings.Models.EmbeddingGemma2.Imaging.SkiaSharp;

EmbeddingGemma2ImageModelFiles files = await EmbeddingGemma2ModelAssets.DownloadImageAssetsAsync();
using var embedder = EmbeddingGemma2MultimodalEmbedder.Create(files);

float[] image = embedder.Embed(EmbeddingGemma2ImageDecoder.DecodeFile("photo.jpg")); // images take no prompt
float[] query = embedder.Embed(EmbeddingGemma2MultimodalInput.FromText("a photo of a cat"), EmbeddingGemma2Prompt.Query);
float score = TensorPrimitives.CosineSimilarity(image, query);

using Starlings.Tokenizers;

Tokenizer tokenizer = Tokenizer.FromFile("tokenizer.json");
TokenEncoding encoding = tokenizer.Encode("Hello, world!");
string text = tokenizer.Decode(encoding.Ids.AsSpan(), skipSpecialTokens: true);