Chapter 4 HeatWave GenAI

Table of Contents

4.1 HeatWave GenAI Overview

4.2 Getting Started with HeatWave GenAI

4.2.1 Requirements

4.2.2 Supported LLMs, Embedding Models, and Languages

4.2.3 Authenticating OCI Generative AI Service

4.2.4 Quickstart: Setting Up a Help Chat

4.3 Generating Text-Based Content

4.3.1 Generating New Content

4.3.2 Summarizing Content

4.4 Setting Up a Vector Store

4.4.1 HeatWave Vector Store Overview

4.4.2 Ingesting Files into a Vector Store

4.4.3 Updating a Vector Store

4.5 Generating Vector Embeddings

4.6 Performing a Vector Search With Retrieval-Augmented Generation

4.6.1 Running Retrieval-Augmented Generation

4.6.2 Using Your Own Embeddings with Retrieval-Augmented Generation

4.7 Starting a Conversational Chat

4.7.1 Running HeatWave Chat

4.7.2 Viewing Chat Session Details

4.8 HeatWave GenAI Routines

4.8.1 ML_GENERATE

4.8.2 ML_GENERATE_TABLE

4.8.3 VECTOR_STORE_LOAD

4.8.4 ML_RAG

4.8.5 ML_RAG_TABLE

4.8.6 HEATWAVE_CHAT

4.8.7 ML_EMBED_ROW

4.8.8 ML_EMBED_TABLE

4.9 Troubleshooting Issues and Errors

This chapter describes HeatWave GenAI.