Rewriter

public class Rewriter extends Object

Provides an interface for performing text rewriting.

It supports both standard and streaming inferences, as well as methods for preparing and cleaning up model resources.

Typical usage:


 RewritingRequest request = RewritingRequest.builder(text).build();

 ListenableFuture future = rewriter.runInference(request);
 Futures.addCallback(future, new FutureCallback<>() {
     @Override
     public void onSuccess(RewritingResult result) {
         Log.d(TAG, result.getResults(0).getText());
     }

     @Override
     public void onFailure(Throwable t) {
         Log.e(TAG, "Failed to rewrite", t);
     }
 }, executor);

Public Method Summary

ListenableFuture<Integer>
checkFeatureStatus()
Checks the current availability status of the rewriting feature.
void
close()
Releases resources associated with the rewriting engine.
ListenableFuture<Void>
downloadFeature(DownloadCallback callback)
Downloads the required model assets for the rewriting feature if they are not already available.
ListenableFuture<String>
getBaseModelName()
Returns the name of the base model used by this rewriter instance.
ListenableFuture<Void>
prepareInferenceEngine()
Prepares the inference engine for use by loading necessary models and initializing runtime components.
ListenableFuture<RewritingResult>
runInference(RewritingRequest request)
Performs asynchronous rewriting on the provided input request.
ListenableFuture<RewritingResult>
runInference(RewritingRequest request, StreamingCallback streamingCallback)
Performs streaming rewriting inference on the provided input request.

Inherited Method Summary

Public Methods

public ListenableFuture<Integer> checkFeatureStatus ()

Checks the current availability status of the rewriting feature.

Returns

public void close ()

Releases resources associated with the rewriting engine.

This should be called when the rewriter is no longer needed. Can be safely called multiple times.

public ListenableFuture<Void> downloadFeature (DownloadCallback callback)

Downloads the required model assets for the rewriting feature if they are not already available.

Use this method to proactively download models before inference. The provided DownloadCallback is invoked to report progress and completion status.

Parameters
callback a non-null DownloadCallback for receiving download updates.
Returns
  • a ListenableFuture that completes when the download finishes or fails. It completes immediately if already downloaded.

public ListenableFuture<String> getBaseModelName ()

Returns the name of the base model used by this rewriter instance.

The model name may be used for logging, debugging, or feature gating purposes.

Returns

public ListenableFuture<Void> prepareInferenceEngine ()

Prepares the inference engine for use by loading necessary models and initializing runtime components.

If the models haven't been downloaded yet, it will trigger the download and wait for it to complete first.

While calling this method is optional, we recommend invoking it well before the first inference call to reduce the latency of the initial inference.

Returns

public ListenableFuture<RewritingResult> runInference (RewritingRequest request)

Performs asynchronous rewriting on the provided input request.

This is the standard, non-streaming version of inference. The full rewrite suggestions are returned once the model completes processing.

This method is non-blocking. To handle the result, callers should attach a listener to the returned ListenableFuture using Futures.addCallback(ListenableFuture, FutureCallback , Executor) or similar methods. The inference runs on background threads and may complete at a later time depending on model availability and input size.

The returned ListenableFuture is cancellable. If the inference is no longer needed (e.g., the user navigates away or input changes), calling future.cancel(true) will attempt to interrupt the process and free up resources.

Note that inference requests may fail under certain conditions such as:

  • Invalid or malformed input in the RewritingRequest
  • Exceeded usage quota or failed safety checks
Appropriate GenAiException handling should be implemented when attaching the callback to the future.
Parameters
request a non-null RewritingRequest containing input text.
Returns

public ListenableFuture<RewritingResult> runInference (RewritingRequest request, StreamingCallback streamingCallback)

Performs streaming rewriting inference on the provided input request.

Only one RewritingSuggestion will be streamed out via the StreamingCallback, while there could be multiple RewritingSuggestions in the final RewritingResult. The streamed out RewritingSuggestion is not guaranteed to be the first one in the final result list.

Streaming can be interrupted by a GenAiException. In that case, consider removing any already streamed partial output from the UI.

The returned ListenableFuture is cancellable. If the inference is no longer needed (e.g., the user navigates away or input changes), calling future.cancel(true) will attempt to interrupt the process and free up resources.

Note that inference requests may fail under certain conditions such as:

  • Invalid or malformed input in the RewritingRequest
  • Exceeded usage quota or failed safety checks
Appropriate GenAiException handling should be implemented when attaching the callback to the future.
Parameters
request a non-null RewritingRequest containing the input text.
streamingCallback a non-null StreamingCallback for receiving streamed results.
Returns