FuncReAct: ReAct Agent Using OpenAI Function Calling

Author(s): Vatsal Saglani

Originally published on Towards AI.

Part 2— Setting up the base for the ReAct RAG bot
Prompting techniques.

In the previous blog, we got an introduction to prompt engineering and the two basic prompting techniques — zero-shot and few-shot prompting. Along with the implementation using OpenAI function calling.

In this blog, we will look at a new prompting technique called ReAct. This technique was proposed in the paper ReAct: Synergizing Reasoning and Acting in Language Models. The word “ReAct” comes from the acts of reasoning and taking actions.

The prompting techniques we saw in the previous blog don’t provide a glaring insight into what the model is trying to do, and sometimes it will just answer just for the… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI