Efficient Query Routing using Agentic RAG

摘要

The industry is abuzz with the term "Vertical Agents," yet there’s often little clarity on how Agents work. At its core, however, an Agent is simply a workflow designed to automate tasks using environment tools and enhance its ability to reason, plan, decompose, and execute a given task. In this talk, we’ll explore the necessity of planning and reasoning in various industries and build a practical use case. The application will answer user questions based on provided academic notes, and if the information isn’t available, it will search the web. We'll utilize an RAG approach to define and manage a custom knowledge base. With Agentic RAG, the audience will gain clarity on routing concepts, learn how to design an efficient architecture, and understand how the Thought-Action-Observation loop enables an Agent to function effectively. For the tutorial, we will use LlamaIndex for the routing with its ReAcT Agent and Qdrant as the vector database.

說明