The ability to use tools, also known as function calls, has become a valuable mechanism for enabling LLMs to expand their abilities beyond out-of-box capabilities. This is especially important in bridging the abilities that LLMs are known to lack. Tools also provide a link to existing APIs and applications to expand, automate, optimise or enable a wider range of tasks.
Many models, including OpenAI GPTs and Anthropic Claude 3, support tools out of the box. For models that do not natively support tools and function calls, third-party frameworks that are specifically designed to excel in this area are available. For example, LangChain has built-in tools to run SQL queries, perform calculations, and perform vector searches. When the built-in tools don’t do what you need, you can define custom tools to expand LangChain’s capabilities.