Overview
Function calling lets you define tools that the model can invoke. When the model decides to call a tool, it returns a structured JSON response that you execute in your application and feed back to the model.Basic Example
from openai import OpenAI
import json
client = OpenAI(
api_key="sk-samurai-YOUR_KEY",
base_url="https://api.samuraiapi.in/v1"
)
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city name, e.g. 'London'"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "Temperature unit"
}
},
"required": ["city"]
}
}
}
]
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
tools=tools,
tool_choice="auto"
)
message = response.choices[0].message
# Check if the model called a tool
if message.tool_calls:
tool_call = message.tool_calls[0]
args = json.loads(tool_call.function.arguments)
print(f"Called: {tool_call.function.name}({args})")
# => Called: get_weather({'city': 'Tokyo'})
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'sk-samurai-YOUR_KEY',
baseURL: 'https://api.samuraiapi.in/v1'
});
const tools = [
{
type: 'function',
function: {
name: 'get_weather',
description: 'Get the current weather for a city',
parameters: {
type: 'object',
properties: {
city: { type: 'string', description: 'City name' },
unit: { type: 'string', enum: ['celsius', 'fahrenheit'] }
},
required: ['city']
}
}
}
];
const response = await client.chat.completions.create({
model: 'gpt-4o',
messages: [{ role: 'user', content: "What's the weather in Tokyo?" }],
tools,
tool_choice: 'auto'
});
const toolCall = response.choices[0].message.tool_calls?.[0];
if (toolCall) {
const args = JSON.parse(toolCall.function.arguments);
console.log(`Called: ${toolCall.function.name}`, args);
}
Multi-Step Tool Use
After receiving a tool call, execute it and send the result back:# Step 1: Model requests tool call (see above)
# Step 2: Execute your function
def get_weather(city: str, unit: str = "celsius"):
return {"city": city, "temperature": 22, "unit": unit, "condition": "Sunny"}
result = get_weather(**args)
# Step 3: Send result back to model
messages = [
{"role": "user", "content": "What's the weather in Tokyo?"},
message, # assistant message with tool_calls
{
"role": "tool",
"tool_call_id": tool_call.id,
"content": json.dumps(result)
}
]
final_response = client.chat.completions.create(
model="gpt-4o",
messages=messages,
tools=tools
)
print(final_response.choices[0].message.content)
# => "The weather in Tokyo is currently 22°C and Sunny."
tool_choice Options
| Value | Behavior |
|---|---|
"auto" | Model decides whether to call a tool |
"none" | Model never calls tools |
"required" | Model must call at least one tool |
{"type": "function", "function": {"name": "X"}} | Force a specific function |