How to Build Agents With Websearch Capabilities
Last Updated on November 3, 2024 by Editorial Team
Author(s): Julia
Originally published on Towards AI.
This member-only story is on us. Upgrade to access all of Medium.
Photo by Mohammad Rahmani on UnsplashIn this article, we explore how to build an Agentic Retrieval-Augmented Generation (RAG) system using the Intel Neural Chat 7B model. The RAG system integrates a knowledge base with intelligent web search capabilities to generate precise answers from both a predefined dataset and live internet searches. Our example knowledge base focuses on the Seven Wonders of the Ancient World.
The goal is to build a system capable of answering questions based on an existing knowledge base and seamlessly falling back on a web search if the answer cannot be inferred from the documents in the knowledge base. This combines the best of retrieval and generation, forming an intelligent pipeline for question-answering tasks.
The core goal of this system is to:
Query a local knowledge base for answers.If no relevant answer is found, perform a web search.Finally, it returns the best possible answer using the Intel Neural Chat 7B model.
This setup leverages the concept of Agentic behavior, where the system decides which data source (local knowledge or web) to use based on the context, making it more dynamic and adaptable.
🧠💬Intel Neural Chat 7B: This model is used for… 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 aΒ sponsor.
Published via Towards AI