All Classes

Class	Description
AsyncInferenceExecutor	AsyncInferenceExecutor provides a simple abstraction for executing tasks asynchronously using a fixed-size thread pool.
AsyncMLInferenceFunction<T,R>	Asynchronous ML inference function for Flink streams.
AsyncMLPredictFunction	Async function for non-blocking inference.
AsyncModelInferenceFunction<IN,OUT>	Asynchronous function for performing ML inference in Apache Flink streams.
AsyncResultHandler<T>	Handles async inference results.
AuthConfig	Configuration for authentication with remote ML inference endpoints.
AuthConfig.Builder	Builder for creating AuthConfig instances.
BatchInferenceProcessor	Batches inference requests for improved throughput.
CacheConfig	Configuration for model and result caching in SQL inference.
CacheConfig.Builder
CacheStrategy	Defines caching strategies for ML inference operations in Otter Stream.
CEPInferenceIntegration	Integration between Flink CEP and ML inference for pattern-based decisions.
ConfigurationValidator	Validates SQL inference configurations.
ConfigurationValidator.ValidationResult	Result of configuration validation.
DDLParserHelper	Helper for parsing SQL DDL options.
DecisionEngine<T>	Generic decision engine abstraction.
DroolsDecisionEngine	Stateless Drools-based decision engine.
EndpointConfig
EndpointConfig.Builder
FeaturePreprocessor	Preprocesses features before inference (normalization, encoding, etc.).
FraudDetectionExample	Example demonstrating real-time fraud detection using OtterStream's ML inference capabilities.
FunctionRegistrationHelper	Helper class for registering SQL functions programmatically.
HttpInferenceClient	HTTP-based remote inference client for REST API model endpoints.
HttpModelLoader	Loads models from HTTP/HTTPS endpoints.
InferenceCircuitBreaker	Circuit breaker to prevent cascading failures in inference operations.
InferenceCircuitBreaker.State
InferenceConfig	Comprehensive configuration for ML inference operations in Apache Flink streams.
InferenceConfig.Builder	Builder for creating InferenceConfig instances with sensible defaults.
InferenceContext	Context for inference execution with metadata.
InferenceEngine<T>	Core interface for ML inference engines in Otter Stream.
InferenceEngine.EngineCapabilities	Describes the capabilities of an inference engine.
InferenceEngineFactory	Factory for creating inference engines based on model format.
InferenceErrorBuilder	Builder for user-friendly error messages.
InferenceException	Exception thrown when inference operations fail.
InferenceMetrics	Collects and records metrics for ML inference operations.
InferenceMetricsCollector	Collects and tracks inference metrics per model.
InferenceMetricsCollector.ModelMetrics	Metrics for a single model.
InferenceResult	Container for ML inference results including predictions and metadata.
InferenceRetryHandler	Handles retry logic for failed inference operations.
InferenceSession	Wrapper class for ONNX Runtime sessions providing simplified access to inference capabilities.
InputOutputSchema	Schema definition for model inputs and outputs.
InputOutputSchema.FieldSchema
InputOutputSchemaExtractor	Extracts input/output schema from loaded models.
JsonFeatureExtractor	Extracts features from JSON strings for model input.
LocalInferenceEngine<T>	Abstract base class for local inference engines that load models from files.
LocalModelLoader	Loads models from local filesystem or HDFS.
MetricsCollector	Central collector managing metrics for multiple models.
MinioModelLoader	Loads models from MinIO object storage.
MLInferenceDynamicTableFactory	Factory for creating ML inference table sources.
MLInferenceDynamicTableSource	Dynamic table source for ML inference with lookup support.
MLInferenceFunction	Flink SQL scalar function for ML inference.
MLInferenceFunctionFactory
MLInferenceLookupFunction	Lookup function for temporal joins with ML predictions.
MLPredictAggregateFunction	Aggregate function for batch inference over windows.
MLPredictAggregateFunction.Accumulator
MLPredictScalarFunction	Flink SQL Scalar Function for ML model inference.
MLPredictTableFunction	Table function that returns multiple rows.
ModelCache<K,V>	Thread-safe LRU cache for storing ML model predictions and inference results.
ModelCache	Thread-safe LRU cache for loaded inference engines.
ModelConfig	Configuration for ML models in Otter Stream inference framework.
ModelConfig.Builder	Builder for creating ModelConfig instances.
ModelDescriptor	Metadata descriptor for a registered model.
ModelFormat	Enumeration of supported ML model formats in Otter Stream.
ModelHealthChecker	Performs periodic health checks on loaded models.
ModelHealthChecker.HealthStatus	Health status for a single model.
ModelLoader<T>	Interface for loading ML models from various sources.
ModelLoader
ModelLoaderFactory	Factory for creating appropriate model loaders based on source type.
ModelLoadException	Exception thrown when model loading fails.
ModelLoadingContext	Context information for model loading operations.
ModelLoadingProgressTracker	Tracks progress of model loading operations.
ModelLoadingProgressTracker.LoadingProgress	Represents loading progress for a single model.
ModelMetadata	Immutable metadata container for machine learning models.
ModelMetadata.Builder	Builder for constructing ModelMetadata instances.
ModelRegistrationManager	Manages model registration, loading, and lifecycle.
ModelRegistry	Central registry for model metadata and lifecycle management.
ModelServerConnectionPool	Manages HTTP connection pooling for remote model servers.
ModelSession	Manages stateful inference sessions.
ModelSource	Interface for different model source implementations.
ModelSourceConfig	Configuration for model source locations and loading strategies.
ModelSourceConfig.Builder
ModelSourceConfig.SourceType	Enumeration of supported source types.
ModelVersionManager	Manages multiple versions of a model.
ModelWarmupUtility	Utility for warming up models to avoid cold start latency.
OnnxInferenceEngine	ONNX Runtime implementation of LocalInferenceEngine for ML inference.
OnnxModelLoader	ModelLoader implementation for loading ONNX models.
OtterStreamSQLConstants	Constants used throughout Otter Stream SQL module.
PatternInferenceFunction<T,R>	Process function that applies ML inference to CEP pattern matches.
PmmlInferenceEngine	PMML (Predictive Model Markup Language) implementation of LocalInferenceEngine.
ReinforcementHandler	Handles feedback loops for reinforcement learning scenarios.
RemoteInferenceEngine	Abstract base class for remote inference engines communicating with external model endpoints.
ResultPostprocessor	Postprocesses inference results (denormalization, thresholding, etc.).
RuleEngineProvider	Provides a rule engine instance for Flink SQL and DataStream pipelines.
RuleOutcome	Mutable rule outcome passed as a Drools global.
S3ModelLoader	Loads ML models from AWS S3 or S3-compatible storage (e.g.
SageMakerInferenceClient	AWS SageMaker remote inference client for hosted ML models.
SerializationUtils	Serialization utilities for distributing objects in Flink.
SqlInferenceConfig	Configuration for SQL-based ML inference operations.
SqlInferenceConfig.Builder
TensorConverter	Converts between Java objects and TensorFlow tensors.
TensorFlowGraphDefEngine	TensorFlow GraphDef (frozen graph) inference engine.
TensorFlowInferenceEngine	TensorFlow SavedModel inference engine using TensorFlow Java API.
TensorFlowSavedModelEngine	TensorFlow SavedModel inference engine.
TorchScriptInferenceEngine	TorchScript (PyTorch) implementation of LocalInferenceEngine using Deep Java Library (DJL).
TypeUtils	Utilities for Flink type conversions.
ValidationUtils	Validation utilities for input data.
VertexAIInferenceClient	Google Vertex AI remote inference client for Google Cloud ML models.
XGBoostInferenceEngine	XGBoost inference engine for gradient boosting tree models.