Performs Natural Language classification. **Signature:** export declare class TextClassifier extends TaskRunner ## Methods | Method | Modifiers | Description | |---|---|---| | [createFromOptions(wasmFileset, textClassifierOptions)](https://developers.google.com/edge/api/mediapipe/js/tasks-text.textclassifier#textclassifiercreatefromoptions) | `static` | Initializes the Wasm runtime and creates a new text classifier from the provided options. | | [createFromModelBuffer(wasmFileset, modelAssetBuffer)](https://developers.google.com/edge/api/mediapipe/js/tasks-text.textclassifier#textclassifiercreatefrommodelbuffer) | `static` | Initializes the Wasm runtime and creates a new text classifier based on the provided model asset buffer. | | [createFromModelPath(wasmFileset, modelAssetPath)](https://developers.google.com/edge/api/mediapipe/js/tasks-text.textclassifier#textclassifiercreatefrommodelpath) | `static` | Initializes the Wasm runtime and creates a new text classifier based on the path to the model asset. | | [setOptions(options)](https://developers.google.com/edge/api/mediapipe/js/tasks-text.textclassifier#textclassifiersetoptions) | | Sets new options for the text classifier. Calling `setOptions()` with a subset of options only affects those options. You can reset an option back to its default value by explicitly setting it to `undefined`. | | [classify(text)](https://developers.google.com/edge/api/mediapipe/js/tasks-text.textclassifier#textclassifierclassify) | | Performs Natural Language classification on the provided text and waits synchronously for the response. | ## TextClassifier.createFromOptions() {#textclassifiercreatefromoptions} Initializes the Wasm runtime and creates a new text classifier from the provided options. **Signature:** static createFromOptions(wasmFileset: WasmFileset, textClassifierOptions: TextClassifierOptions): Promise; ### Parameters | Parameter | Type | Description | |---|---|---| | wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. | | textClassifierOptions | TextClassifierOptions | The options for the text classifier. Note that either a path to the TFLite model or the model itself needs to be provided (via `baseOptions`). | **Returns:** Promise\ ## TextClassifier.createFromModelBuffer() {#textclassifiercreatefrommodelbuffer} Initializes the Wasm runtime and creates a new text classifier based on the provided model asset buffer. **Signature:** static createFromModelBuffer(wasmFileset: WasmFileset, modelAssetBuffer: Uint8Array | ReadableStreamDefaultReader): Promise; ### Parameters | Parameter | Type | Description | |---|---|---| | wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. | | modelAssetBuffer | Uint8Array \| ReadableStreamDefaultReader | An array or a stream containing a binary representation of the model. | **Returns:** Promise\ ## TextClassifier.createFromModelPath() {#textclassifiercreatefrommodelpath} Initializes the Wasm runtime and creates a new text classifier based on the path to the model asset. **Signature:** static createFromModelPath(wasmFileset: WasmFileset, modelAssetPath: string): Promise; ### Parameters | Parameter | Type | Description | |---|---|---| | wasmFileset | WasmFileset | A configuration object that provides the location of the Wasm binary and its loader. | | modelAssetPath | string | The path to the model asset. | **Returns:** Promise\ ## TextClassifier.setOptions() {#textclassifiersetoptions} Sets new options for the text classifier. Calling `setOptions()` with a subset of options only affects those options. You can reset an option back to its default value by explicitly setting it to `undefined`. **Signature:** setOptions(options: TextClassifierOptions): Promise; ### Parameters | Parameter | Type | Description | |---|---|---| | options | TextClassifierOptions | The options for the text classifier. | **Returns:** Promise\ ## TextClassifier.classify() {#textclassifierclassify} Performs Natural Language classification on the provided text and waits synchronously for the response. **Signature:** classify(text: string): TextClassifierResult; ### Parameters | Parameter | Type | Description | |---|---|---| | text | string | The text to process. | **Returns:** TextClassifierResult