All Classes and Interfaces

Class
Description
Collects all samples to double[][] features and double[][] labels, then calls fit(double[][] features, double[][] labels) to fit Function<double[][],double[][]> which makes predictions for multiple features at once.
Creates a Function<double[][],double[]> predictor for each label element, predicts label elements using provided predictors and then combines
Creates a Function<double[][],double[]> predictor for each label element with features for later elements including labels for earlier.
Splits input by whitespace, lowercases and then computes frequency of each word
 
 
Caches image embeddings in a map which can be loaded and saved between runs Uses image digest as caching key
Caches image embeddings in a map which can be loaded and saved between runs Uses image digest as caching key
 
Caches text embeddings in a map which can be loaded and saved between runs Uses text digest as caching key
 
 
Chat requirement.
 
 
 
 
Model coordinates (identifier)
Generates an embedding from source.
EmbeddingGenerator requirement.
 
 
A predictor which is fitted (trained)
 
 
 
 
 
 
 
Converts image to text (String).
Caches image embeddings in a map which can be loaded and saved between runs Uses image digest as caching key
Base interface for interfaces to work with (large language) models.
Converts source to text (String).
Predicts output from input
 
 
Computes pair-wise similarity
 
Vector index item
Index id - item URI and embedding vector index for URIs with multiple vectors/chunks.
 
A simple implementation which treats a character as a token.
 
TextFloatVectorEmbeddingModel "business" interface focusing on ease of use and leaving token usage reporting to implementations.
A collection of strings pre-computed embeddings, e.g. web site contents.
A pre-computed embeddings
 
 
Can handle data: URIs