AI-Studio/app/MindWork AI Studio/Models/Hosting/Hosts/HostHuggingFace.cs
Thorsten Sommer d85b4e71b6
Some checks are pending
Build and Release / Determine run mode (push) Waiting to run
Build and Release / Sync Flatpak repo (push) Blocked by required conditions
Build and Release / Collect Flatpak artifacts (push) Blocked by required conditions
Build and Release / Verify (push) Waiting to run
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-aarch64-apple-darwin, osx-arm64, macos-latest, aarch64-apple-darwin, dmg,app,updater, dmg) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-aarch64-pc-windows-msvc.exe, win-arm64, windows-latest, aarch64-pc-windows-msvc, nsis,updater, nsis) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-aarch64-unknown-linux-gnu, linux-arm64, ubuntu-22.04-arm, aarch64-unknown-linux-gnu, appimage,updater, appimage) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-x86_64-apple-darwin, osx-x64, macos-latest, x86_64-apple-darwin, dmg,app,updater, dmg) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-x86_64-pc-windows-msvc.exe, win-x64, windows-latest, x86_64-pc-windows-msvc, nsis,updater, nsis) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-x86_64-unknown-linux-gnu, linux-x64, ubuntu-22.04, x86_64-unknown-linux-gnu, appimage,updater, appimage) (push) Blocked by required conditions
Build and Release / Prepare & create release (push) Blocked by required conditions
Build and Release / Publish release (push) Blocked by required conditions
Rebuilt how AI Studio knows what a model can do (#960)
2026-09-13 14:17:25 +02:00

36 lines
1.6 KiB
C#

using AIStudio.Models.Matching;
using AIStudio.Provider;
namespace AIStudio.Models.Hosting.Hosts;
/// <summary>
/// The Hugging Face router, whose names carry two wrappings rather than one.
/// </summary>
/// <remarks>
/// "google/gemma-4-31B-it:novita" says three things at once: who published the weights, which model
/// it is, and which inference provider should answer. The suffix goes first, because it is the
/// outermost and because it says nothing about the model -- a request routed to Novita and one
/// routed to Together AI reach the same weights.
///
/// This is the case the whole walk was written for. A host which took both off at once would work
/// here and nowhere else; taking one off at a time is what also covers the account path Fireworks
/// puts in front, without either host knowing about the other.
/// </remarks>
public sealed class HostHuggingFace : ModelHost
{
/// <inheritdoc />
public override LLMProviders Provider => LLMProviders.HUGGINGFACE;
/// <inheritdoc />
public override ModelSource Source => new("https://huggingface.co/docs/inference-providers/index", new DateOnly(2026, 9, 11), "Models are named as the hub names them, \"organization/model\", optionally followed by a colon and the inference provider to route to.");
/// <inheritdoc />
public override bool TryUnwrap(in ModelId id, out ModelId inner, out ModelVendor? declaredVendor)
{
declaredVendor = null;
if (HostNaming.TryStripRoutingSuffix(id, out inner))
return true;
return HostNaming.TrySplitOrganization(id, out inner, out declaredVendor);
}
}