From the course: Agentic AI for Developers: Concepts and Application for Enterprises
Join today to access over 24,700 courses taught by industry experts.
Setting up the customer service AI agent
From the course: Agentic AI for Developers: Concepts and Application for Enterprises
Setting up the customer service AI agent
- [Instructor] Let's not set up the customer service AI agent based on the functions and query engine we have created in the earlier video. First, we create tools based on the functions. For this, we use the function tool interface in LlamaIndex. For each of the functions, we create a corresponding tool. Then, we create a query engine tool for the support query engine. We have four tools now. Now we proceed to create an agent worker. The agent worker in LlamaIndex is equivalent to the task executor that we discussed in our agent AI concepts. To create an agent worker, we pass in the list of tools as well as the LLM. We set the verbose level to true so we can see how the agent internally executes its goal. Then, we proceed to create the agent. For this, we use the agent runner interface in LlamaIndex. The agent worker we created earlier is provided as a parameter to the agent runner. We now have the agent set up. Let's now execute some goals against it in the next video.
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.
