Get top documents per topic from mallet lda

Question

I'm using java mallet's LDA engine to determine topics for a set of (some 30K) documents.

I've managed to train the model and serialize/deserialize it as needed.

The question is how do I find the top 'n' documents in each topic.

The closest thing I can find is 'getTopicDocuments' but this returns an array of integer ids and I have no idea what they relate to.

For the record he is my code I use to train the documents:

static void buildModel() throws IOException {

        // Begin by importing documents from text to feature sequences
        ArrayList<Pipe> pipeList = new ArrayList<Pipe>();

        // Pipes: lowercase, tokenize, remove stopwords, map to features
        // my own pipe that loads the the contents
        // of each file into the pipeline.
        pipeList.add(new FileToCharSequence());
        pipeList.add(new CharSequenceLowercase());
        pipeList.add(new CharSequence2TokenSequence(Pattern.compile("\\p{L}[\\p{L}\\p{P}]+\\p{L}")));
        // created a snowball based stemming Pipe
        pipeList.add(new Stemming());
       /// my ownversion of stopwords that stemms them
        pipeList.add(new TokenSequenceRemoveStemmedStopwords(
                new File(
                        "stoplist.txt"),
                "UTF-8", false, false, false));
        pipeList.add(new TokenSequenceRemoveNonAlpha());
        pipeList.add(new TokenSequence2FeatureSequence());

        InstanceList instances = new InstanceList(new SerialPipes(pipeList));


        var fileIterator = new UnlabeledFileIterator(new File("\path\to\docs"));

        
        instances.addThruPipe(fileIterator);
        System.out.println("Starting");


        // Create a model with 100 topics, alpha_t = 0.01, beta_w = 0.01
        // Note that the first parameter is passed as the sum over topics, while
        // the second is the parameter for a single dimension of the Dirichlet prior.
        int numTopics = 180;
        ParallelTopicModel model = new ParallelTopicModel(numTopics, 1.0, 0.01);

        model.addInstances(instances);

        // Use two parallel samplers, which each look at one half the corpus and combine
        // statistics after every iteration.
        model.setNumThreads(8);

        final int iterations = 2000;

        // Run the model for 50 iterations and stop (this is for testing only,
        // for real applications, use 1000 to 2000 iterations)
        model.setNumIterations(iterations);
        model.estimate();

        model.write(new File("LDA.model"));

    }