From the course: Introduction to AI Orchestration with LangChain and LlamaIndex
Join today to access over 24,400 courses taught by industry experts.
Implementing a ReAct agent
From the course: Introduction to AI Orchestration with LangChain and LlamaIndex
Implementing a ReAct agent
When we were discussing RAG, we talked briefly about how Bing Chat works with its ability to reach out over the web to look up information. Here, we're going to implement something similar. Now, I don't have access to Bing internals, and I can't say for sure if they're using a REACT agent or something else. Nevertheless, we'll finish this chapter with a powerful research tool in hand. Since we started out talking about Bing, it's only fair to use Bing Search here. In order for this to work, you'll need an API key from Bing Search and you can get this on the Azure website. The free plan will be perfectly fine for up to 1000 searches a month, and once you have your API key, put it in the environment variable, "BING_SUBSCRIPTION_KEY." Agents work with a list of available tools, and LangChain takes a pretty broad view of what constitutes a tool. You can see a list of some ready-built ones on the LangChain website, where dozens available, including AWS Access, Show Access, File System…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
