Function Calling
A capability where an LLM can generate structured output to invoke specific functions or APIs. The model decides which function to call and what parameters to pass based on the user's request.
Why It Matters
Function calling is the bridge between AI conversations and real-world actions. It enables AI to interact with databases, services, and business systems programmatically.
Example
A user asks 'What is the weather in Tokyo?' and the LLM generates a structured call: get_weather(city='Tokyo', units='celsius') which is then executed by the application.
Think of it like...
Like a doctor writing a precise prescription — they decide what medication and dosage you need, but the pharmacist (the function) actually prepares and dispenses it.
Related Terms
Tool Use
The ability of an AI model to interact with external tools, APIs, and systems to accomplish tasks beyond text generation. Tools extend the model's capabilities to include search, calculation, code execution, and more.
AI Agent
An AI system that can autonomously plan, reason, and take actions to accomplish goals. Unlike simple chatbots, agents can use tools, make decisions, execute multi-step workflows, and adapt their approach based on results.
API
Application Programming Interface — a set of rules and protocols that allow different software applications to communicate with each other. In AI, APIs let developers integrate AI capabilities into their applications.
Structured Output
The ability of an LLM to generate responses in a specific format like JSON, XML, or a defined schema. Structured output makes AI responses parseable by other software systems.