How to Call JavaScript Functions with the OpenAI SDK (Function Calling)

2026-05-16 · Source: Artificial Intelligence in Plain English - Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

OpenAI's Function Calling feature enables Large Language Models (LLMs) to interact with external code by defining JavaScript functions that the model can decide when and how to invoke. This capability allows LLMs to return structured JSON objects specifying a function to call and its arguments, rather than just generating text. The user's code then executes the specified function, and its output can optionally be fed back to the model to formulate a final response. This process effectively provides the LLM with a "toolbox" of custom functions, allowing it to select and utilize appropriate tools based on user requests, such as a `getWeather` tool for weather-related queries.

Key takeaway

For AI Engineers building interactive applications, OpenAI's Function Calling feature significantly expands LLM capabilities beyond text generation. You should consider defining custom JavaScript functions to allow your LLM to execute specific actions or retrieve real-time data, thereby creating more dynamic and powerful user experiences. This approach enables your applications to perform complex tasks by orchestrating external tools.

Key insights

OpenAI Function Calling enables LLMs to invoke external JavaScript functions, returning structured JSON for execution.

Principles

• LLMs can act as intelligent orchestrators for external tools.
• Structured JSON facilitates programmatic interaction with LLM outputs.

Method

Define custom functions for the model. Model returns JSON with function name and arguments. Your code executes the function and feeds results back to the model.

In practice

• Integrate LLMs with APIs via custom functions.
• Enhance LLM responses with real-time data or actions.

Topics

• OpenAI Function Calling
• JavaScript SDK
• LLM Integration
• Custom Functions
• Structured Output

Best for: AI Engineer, Software Engineer

Related on AIssential

• Day 14: Function Calling Explained Simply (For DevOps & Cloud Engineers) — Function Calling empowers LLMs to interact with external systems, transforming them from text generators into actionable AI agents.
• Structured Outputs with LLMs: JSON Mode, Function Calling, and When to Use Each — LLM structured output methods vary in schema enforcement, suiting different application reliability and consistency needs.
• Ollama Python library 0.4 with function calling improvements — Ollama's 0.4 Python library simplifies tool integration by directly accepting Python functions and auto-generating JSON schemas.
• How I Added AI-Powered Natural Language Parsing to My iOS App with Firebase Cloud Functions — Domain-specific context and server-side LLM calls significantly enhance natural language parsing for consumer apps.
• openai / openai-agents-python — The OpenAI Agents SDK enables building flexible, multi-agent LLM workflows with robust control and extensibility.
• [Day 5/100] Tool Use and Function Calling, Explained from Scratch — Function calling is trained, constrained text generation parsed into structured data, not direct function execution.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence in Plain English - Medium.