From the course: Build with AI: Agentic Applications with LlamaIndex and MCP

Unlock this course with a free trial

Join today to access over 25,200 courses taught by industry experts.

Using your Query Agent as a step for an agent workflow

Using your Query Agent as a step for an agent workflow - LlamaIndex Tutorial

From the course: Build with AI: Agentic Applications with LlamaIndex and MCP

Start my 1-month free trial Buy for my team

Using your Query Agent as a step for an agent workflow

“

Previously, JP walked us through the basics of a vector database like Weaviate, and the Weaviate query agent designed to work with all manner of searches and aggregations and questions. Now, let's build an agent workflow, which you learned about previously, but we'll create an agent that's able to search through clothing items in our e-commerce collection you created in Weaviate this time, but we'll design our workflow to have a decision step as to whether the incoming user question is a regular question that can be answered in natural language as a simple answer or whether the user actually is intending to search through and retrieve certain objects from Weaviate. You learned about the ask and search endpoints for the Weaviate query agent, so we're going to be either directing the query to ask or search. So first, let's create two custom events that will either have an ask query or a search query. We already have the beginnings of our agent workflow, where we've initialized it with…

Contents