Build Low-Code Chatbot Solutions with Oracle’s AI Services

Introduction

Langflow is a low-code, open source platform used for building AI agents and workflows. Its drag-and-drop interface helps make it easy to develop applications without writing extensive code. It’s particularly effective for creating chatbots, undertaking document analysis, and orchestrating multiagent systems.

This solution demonstrates how developers can use Langflow with Oracle’s AI services to rapidly prototype and build AI applications. It showcases two chatbots created using Langflow. The first is a chatbot that integrates Oracle Cloud Infrastructure (OCI) Generative AI with Langflow. It uses a “chat memory” component to extend the basic prompting flow with data from previous chat messages, and is designed to provide contextually appropriate responses to prompts. The second example is a chatbot with retrieval-augmented generation capabilities that uses Oracle AI Vector Search (part of Oracle Database 23ai) to return relevant responses to questions after accessing authoritative documentation in an external knowledge repository.

Demo

Prerequisites and setup

1. Oracle Cloud account—sign-up page
2. OCI Generative AI—documentation
3. Oracle Database 23ai—documentation
4. Langflow—documentation

Getting started

• Detailed steps and sample code on GitHub