Google

A specific application of LLM tool use involves granting the model access to a web search tool. This capability enables the LLM to retrieve external information to answer questions that require up-to-date or specialized knowledge, such as identifying the location of the 2028 Olympics.

Using Web Search as an External Tool for LLMs

An example of how to prompt a Large Language Model for tool use involves providing both an instruction and a specific question. For instance, to find out where the 2028 Olympics will be held using a web search tool, the LLM can be given the following complete prompt:

`Your task is to answer the following question. You may use external tools, such as web search, to assist you.`

`Where will the 2028 Olympics be held?`

Example of a Prompt for LLM Tool Use

Analyze the situation described in the case study. What is the fundamental limitation of the language model causing these errors, and what specific type of external tool would most directly address this problem by allowing the model to access real-time information?

E-commerce Chatbot Malfunction

An AI assistant is built on a large language model. Consider the two user queries below. Identify which query would necessitate the use of an external web search tool for the model to provide an accurate and current answer, and explain why the other query likely does not require it.

Query A: 'Summarize the main plot of Shakespeare's Hamlet.'
Query B: 'What are the top-rated new movies released this week?'

Analyzing Query Requirements for an LLM

An AI assistant is powered by a large language model whose knowledge is based on a fixed dataset from over a year ago. To enhance its functionality, developers have integrated a tool that allows it to perform live web searches. For which of the following user requests would the use of this web search tool be most critical for providing a correct and useful response?

Learn Before

Related