AI Solution

Creating a Real-Time Chatbot with AI Agents and Oracle REST Data Services

Introduction

Chatbots have become more conversational with AI, but they’re still limited by their large language model training data set. This can be a problem if you want them to understand new data on the fly. That’s where retrieval-augmented generation (RAG) can help, augmenting the data in real time during conversations.

In this project, we’ll build an API-driven chatbot with RAG using OCI Generative AI Agents, Oracle APEX, and Oracle REST Data Services, which will provide an endpoint for the chatbot so that it can “speak” to users.

Demo

Demo: Creating a Real-Time Chatbot with AI Agents and Oracle REST Data Services (1:47)

Prerequisites and setup

  1. Oracle Cloud account—sign-up page
  2. OCI Generative AI Agents—documentation
  3. OCI SDK and command-line interface—configuration
  4. OCI Generative AI—Python SDK
  5. OCI Generative AI Agents API—documentation
  6. Python 3.10—documentation
  7. Open source package manager—Conda

注:为免疑义,本网页所用以下术语专指以下含义:

  1. Oracle专指Oracle境外公司而非甲骨文中国。
  2. 相关Cloud或云术语均指代Oracle境外公司提供的云技术或其解决方案。