HuggingFaceProvider Class

Extends AIProviderBase

Implements IUsesCredential, IChatTask, IObjectDetectionTask

HuggingFace cloud provider – supports chat/VLM (IChatTask) and object detection (IObjectDetectionTask).

Normalized detections shape: [{ "score":float, "label":string, "box":[xmin,ymin,xmax,ymax] }, ...]

Protected Properties

DefaultSupportedTypes : override InferenceType

[Get]

Signature

override InferenceType DefaultSupportedTypes

Properties

SupportsVision : bool

[Get]

Indicates whether this provider prepares and sends image inputs for supported multimodal models.

Disable for pure-text models to reduce request overhead and validation checks.

See IChatTask and your model's capabilities on the provider dashboard.

Signature

bool SupportsVision

Methods

ChatAsync ( req , stream , ct )	Sends a chat turn to a Hugging Face Inference endpoint and returns assistant text. Supports optional image inputs when the selected model is multimodal. See IChatTask. HF Inference: https://huggingface.co/docs/api-inference/index⁠ Signature async Task< ChatResponse > ChatAsync(ChatRequest req, IProgress< ChatDelta > stream=null, CancellationToken ct=default) Parameters `req: ChatRequest` Message payload and (optionally) images prepared by the editor or runtime. `stream: IProgress< ChatDelta >` Optional progress receiver for partial tokens; final text is always delivered. `ct: CancellationToken` Cancellation token for request assembly and HTTP. Returns `async Task< ChatResponse >` ChatResponse with assistant text and raw payload for diagnostics.
DetectAsync ( imageJpgOrPng , ct )	Runs object detection using a Hugging Face model and returns structured detections. Handles tensor or JSON outputs depending on the model’s task definition. See IObjectDetectionTask. HF Tasks: https://huggingface.co/docs/inference-providers/tasks/object-detection⁠ Signature async Task< string > DetectAsync(byte[] imageJpgOrPng, CancellationToken ct=default) Parameters `imageJpgOrPng: byte[]` Encoded image data (e.g., JPG/PNG). Must be non-empty. `ct: CancellationToken` Cancellation token to abort pre-processing or HTTP. Returns `async Task< string >` Normalized detection set (boxes, scores, class ids) for downstream visualization.
DetectAsync ( src , ct )	Performs object detection on a RenderTexture by encoding it to JPEG and calling the byte[] overload. This provides compatibility with the IObjectDetectionTask interface while adapting to cloud providers. Signature async Task< byte[]> DetectAsync(RenderTexture src, CancellationToken ct=default) Parameters `src: RenderTexture` Source RenderTexture to analyze. `ct: CancellationToken` Cancellation token for aborting the operation. Returns `async Task< byte[]>` UTF-8 encoded JSON string as byte array containing detection results.