This article showcases the power of combining the LangChain framework with an LLM hosted on MySQL HeatWave GenAI. Our goal is to create an agent that can answer the question, "What is the current weather in Fahrenheit?". To do this, the agent must first fetch the weather (which is in Celsius) and then convert it to Fahrenheit, a classic multi-step task. This agent will demonstrate how a Large Language Model (LLM) can use tools and a logical sequence of steps to solve a problem.

Retrieval-Augmented Generation (RAG) is a powerful technique that enhances the capabilities of Large Language Models (LLMs) for enterprise data. By grounding the model in information from your vector store/knowledge base, RAG helps produce more accurate, relevant, and trustworthy answers. MySQL HeatWave is a fully managed MySQL database service that combines transactions, analytics, machine learning, and […]

This post will guide you through building a simple RAG workflow using the popular LangChain framework, powered entirely by the in-database AI capabilities of MySQL HeatWave GenAI. We will ingest a public blog post, index it in the HeatWave Vector Store, and use a HeatWave-hosted LLM to answer questions based on its content following the LangChain guide to creating vector stores and using them for RAG.

Introduction MySQL HeatWave is a fully managed MySQL database service that combines transactions, analytics, machine learning, and GenAI services, without ETL duplication. Also included is MySQL HeatWave Lakehouse, which allows users to query data in object storage, MySQL databases, or a combination of both. Users can deploy MySQL HeatWave–powered apps on a choice of public […]

Introduction MySQL HeatWave is a fully managed MySQL database service that combines transactions, analytics, machine learning, and GenAI services, without ETL duplication. Also included is MySQL HeatWave Lakehouse, which allows users to query data in object storage, MySQL databases, or a combination of both. Users can deploy MySQL HeatWave–powered apps on a choice of public […]

MySQL HeatWave Lakehouse enables queries on file formats like Parquet, Avro, ND-JSON and CSV in an object store. This blog introduces support for the Delta Lake table format, thereby enabling ACID-compliant applications on data in the object store. Introduction Delta Lake is an open-table format built for data lake environments. It stores data in Parquet […]

Ready to grow your querying skills? This post introduces curious newcomers to the WHERE clause in MySQL, showing how simple conditions, clever operators, and cheerful library metaphors can help you filter data like a pro. Find the exact records you need using approachable SQL examples—no dusty catalogs required!

We’re introducing a powerful set of enhancements aimed at boosting service availability and manageability thereby simplifying migrations from AWS Aurora, RDS, or MySQL on EC2, and improving performance. Before diving into the updates, here’s a quick refresher: MySQL HeatWave on AWS runs natively on AWS infrastructure, with every component—from the service console to the control […]

We’re introducing a powerful set of enhancements aimed at boosting service availability and manageability thereby simplifying migrations from AWS Aurora, RDS, or MySQL on EC2, and improving performance.

This blog post shows the performance evaluation of the BLOB_INLINE_SIZE column option for NDB tables in comparison without it, as well as the benefits of batching BLOB read and writes.