Built-in AI/ML Functions with Confluent Cloud for Apache Flink

Confluent Cloud for Apache Flink® provides built-in functions that run AI/ML inference directly in Flink SQL, without separate model-serving infrastructure.

Built-in functions support these AI/ML tasks:

• Detect Anomalies with the ML_DETECT_ANOMALIES function

• Forecast Trends with the AI_FORECAST function

• Analyze Sentiment with the AI_SENTIMENT function

• Detect PII with the AI_DETECT_PII function

The following functions are available for building AI/ML workflows.

• AI_COMPLETE: Generate text completions.

• AI_DETECT_PII: Detect and redact personally identifiable information (PII) in text.

• AI_EMBEDDING: Create embeddings.

• AI_FORECAST: Forecast future values in time-series data using foundation models.

• AI_SENTIMENT: Analyze sentiment toward specific aspects in text using aspect-based sentiment analysis.

• AI_TOOL_INVOKE: Invoke MCP tools.

• ML_DETECT_ANOMALIES: Detect anomalies in your data.

• ML_EVALUATE: Evaluate the performance of an AI/ML model.

• ML_PREDICT: Run a remote AI/ML model for tasks like predicting outcomes, generating text, and classification.

Confluent Cloud for Apache Flink has many other functions for building AI/ML workflows.

• Aggregate Functions

• Collection Functions

• Comparison Functions

• Conditional Functions

• Datetime Functions

• Hash Functions

• JSON Functions

• ML Preprocessing Functions

• Model Inference Functions

• Numeric Functions

• String Functions

• Table API Functions

Related content

• ML Preprocessing Functions

• Model Inference Functions

Note

This website includes content developed at the Apache Software Foundation under the terms of the Apache License v2.