Apache Flink

Just as some problems are too big for one person to solve, some tasks are too complex for a single artificial intelligence (AI) agent to handle. Instead, the best approach is to decompose problems into smaller, specialized units so that multiple agents can work together as a team.

By combining Google A2A’s structured protocol with Kafka’s powerful event streaming capabilities, we can shift from brittle, point-to-point integrations to a dynamic ecosystem where agents publish insights, subscribe to context, and coordinate in real time. Observability, auditability, and...

An Apache Flink® job not producing results often indicates an issue with watermarks, which are necessary for handling out-of-order message processing in time-based aggregations from Kafka. Watermarks balance data loss and latency by defining how long to wait for late messages. Incorrectly setting...

Salesforce has Agentforce, Google launched Agentspace, and Snowflake recently announced Cortex Agents. But there’s a problem: They don’t talk to each other…

Introduction to Flink SQL FEDERATED_SEARCH() on Confluent cloud. FEDERATED_SEARCH() along with ML_PREDICT() enables developers to execute GenAI use cases with data streaming technologies.

Learn how Flink enables developers to connect real-time data to external models through remote inference, enabling seamless coordination between data processing and AI/ML workflows.

FLIP 304 lets you customize and enrich your Flink failure messaging: Assign types to failures, emit custom metrics per type, and expose your failure data to other tools.

Confluent’s Create Embeddings Action for Flink helps you generate vector embeddings from real-time data to create a live semantic layer for your AI workflows.

This blog details an end-to-end real-time prediction project leveraging the combined capabilities of Confluent Cloud stacks and Google Cloud Vertex AI. This project aims to deliver a streamlined solution for real-time prediction applications, catering to the evolving needs and challenges of moder...

The blog post provides a comprehensive overview of the Flink Table API, demonstrating how it enables developers to express complex data processing logic using Java or Python in a user-friendly manner. It also includes practical examples and guidance, making it a valuable resource for anyone...

With AI model inference in Flink SQL, Confluent allows you to simplify the development and deployment of RAG-enabled GenAI applications by providing a unified platform for both data processing and AI tasks. Learn how you can use it to build a RAG-enabled Q&A chatbot using real-time airline data.

The Apache Flink® community released Apache Flink 1.20 this week. In this blog post, we highlight some of the most interesting additions and improvements.

Confluent Cloud for Apache Flink®️ supports AI model inference and enables the use of models as resources in Flink SQL, just like tables and functions. You can use a SQL statement to create a model resource and invoke it for inference in streaming queries.

Part two in the series on using FlinkSQL, Kafka, and Streamlit dives into async.io, FlinkSQL syntax, and Streamlit barchart component structure.