AI

Learn how to work with embeddings, vector search, and RAG using AlloyDB Omni, Gemini and Node.js

Generating artificial datasets that closely resemble real data without compromising sensitive information

Learn how to perform semantic search using Aiven for AlloyDB Omni. The vector embeddings for the search will be generated using SQL that calls out to VertexAI. The streamlit front-end will show search and insert functionalities in a webpage.

Adding long term memory to agent communication with OpenSearch®, Amazon Bedrock, RAG and LangChain

Integrating Valkey® pub/sub with Amazon Bedrock for AI agent communication

Make sense of social media data with Apache Kafka® and Apache Flink®

Ever wondered how to enrich your real-time streaming data with machine learning-driven analysis?

Build a knowledge chatbot powered by OpenSearch® and Amazon Bedrock

Learn the theory and the details of how to speed up PostgreSQL® pgvector queries using indexes IVFFlat, HNSW and traditional indexes

Use OpenSearch® as a vector database to generate responses to user queries using AI

Learn how to train AI models and perform live scoring with a set of SQL statements and Aiven for ClickHouse®

Learn how to use Aiven for OpenSearch® to search both images and text to return results!

An SQL optimization guide for developers. With best practices, warnings, and pro tips to speed up your SQL query optimization.