Python SDK - Tools (Function Calling)

The Edgee Python SDK supports OpenAI-compatible function calling (tools), allowing models to request execution of functions you define. This enables models to interact with external APIs, databases, and your application logic.

Overview

Function calling works in two steps:

Request: Send a request with tool definitions. The model may request to call one or more tools.
Execute & Respond: Execute the requested functions and send the results back to the model.

Tool Definition

A tool is defined using a dictionary with the following structure:

{
    "type": "function",
    "function": {
        "name": "function_name",
        "description": "Function description",
        "parameters": {
            "type": "object",
            "properties": {...},
            "required": [...]
        }
    }
}

FunctionDefinition

Property	Type	Description
`name`	`str`	The name of the function (must be unique, a-z, A-Z, 0-9, _, -)
`description`	`str \| None`	Description of what the function does. Highly recommended - helps the model understand when to use it
`parameters`	`dict \| None`	JSON Schema object describing the function parameters

Parameters Schema

The parameters field uses JSON Schema format:

{
    "type": "object",
    "properties": {
        "paramName": {
            "type": "string" | "number" | "boolean" | "object" | "array",
            "description": "Parameter description"
        }
    },
    "required": ["paramName"]  # Array of required parameter names
}

Example - Defining a Tool:

response = edgee.send(
    model="gpt-5.2",
    input={
        "messages": [
            {"role": "user", "content": "What is the weather in Paris?"}
        ],
        "tools": [
            {
                "type": "function",
                "function": {
                    "name": "get_weather",
                    "description": "Get the current weather for a location",
                    "parameters": {
                        "type": "object",
                        "properties": {
                            "location": {
                                "type": "string",
                                "description": "The city and state, e.g. San Francisco, CA"
                            },
                            "unit": {
                                "type": "string",
                                "enum": ["celsius", "fahrenheit"],
                                "description": "Temperature unit"
                            }
                        },
                        "required": ["location"]
                    }
                }
            }
        ],
        "tool_choice": "auto"
    }
)

Tool Choice

The tool_choice parameter controls when and which tools the model should call:

Value	Type	Description
`"auto"`	`str`	Let the model decide whether to call tools (default)
`"none"`	`str`	Don’t call any tools, even if provided
`{"type": "function", "function": {"name": "function_name"}}`	`dict`	Force the model to call a specific function

Example - Force a Specific Tool:

response = edgee.send(
    model="gpt-5.2",
    input={
        "messages": [
            {"role": "user", "content": "What is the weather?"}
        ],
        "tools": [
            {
                "type": "function",
                "function": {
                    "name": "get_weather",
                    "description": "Get the current weather",
                    "parameters": {...}
                }
            }
        ],
        "tool_choice": {
            "type": "function",
            "function": {"name": "get_weather"}
        }
    }
)
# Model will always call get_weather

Example - Disable Tool Calls:

response = edgee.send(
    model="gpt-5.2",
    input={
        "messages": [
            {"role": "user", "content": "What is the weather?"}
        ],
        "tools": [
            {
                "type": "function",
                "function": {
                    "name": "get_weather",
                    "description": "Get the current weather",
                    "parameters": {...}
                }
            }
        ],
        "tool_choice": "none"
    }
)
# Model will not call tools, even though they're available

Tool Call Object Structure

When the model requests a tool call, you receive a ToolCall object in the response:

Property	Type	Description
`id`	`str`	Unique identifier for this tool call
`type`	`str`	Type of tool call (typically `"function"`)
`function`	`dict`	Function call details
`function["name"]`	`str`	Name of the function to call
`function["arguments"]`	`str`	JSON string containing the function arguments

Parsing Arguments

import json

tool_call = response.tool_calls[0]
args = json.loads(tool_call["function"]["arguments"])
# args is now a Python dictionary
print(args["location"])  # e.g., "Paris"

Complete Example

Here’s a complete end-to-end example with error handling:

import json
from edgee import Edgee

edgee = Edgee("your-api-key")

# Define the weather function
async def get_weather(location: str, unit: str = "celsius"):
    # Simulate API call
    return {
        "location": location,
        "temperature": 15,
        "unit": unit,
        "condition": "sunny"
    }

# Step 1: Initial request with tools
response1 = edgee.send(
    model="gpt-5.2",
    input={
        "messages": [
            {"role": "user", "content": "What is the weather in Paris and Tokyo?"}
        ],
        "tools": [
            {
                "type": "function",
                "function": {
                    "name": "get_weather",
                    "description": "Get the current weather for a location",
                    "parameters": {
                        "type": "object",
                        "properties": {
                            "location": {
                                "type": "string",
                                "description": "The city name"
                            },
                            "unit": {
                                "type": "string",
                                "enum": ["celsius", "fahrenheit"],
                                "description": "Temperature unit"
                            }
                        },
                        "required": ["location"]
                    }
                }
            }
        ],
        "tool_choice": "auto"
    }
)

# Step 2: Execute all tool calls
messages = [
    {"role": "user", "content": "What is the weather in Paris and Tokyo?"},
    response1.message  # Include assistant's message
]

if response1.tool_calls:
    for tool_call in response1.tool_calls:
        args = json.loads(tool_call["function"]["arguments"])
        result = await get_weather(args["location"], args.get("unit"))
        
        messages.append({
            "role": "tool",
            "tool_call_id": tool_call["id"],
            "content": json.dumps(result)
        })

# Step 3: Send results back
response2 = edgee.send(
    model="gpt-5.2",
    input={
        "messages": messages,
        "tools": [
            # Keep tools available for follow-up
            {
                "type": "function",
                "function": {
                    "name": "get_weather",
                    "description": "Get the current weather for a location",
                    "parameters": {
                        "type": "object",
                        "properties": {
                            "location": {"type": "string", "description": "The city name"},
                            "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
                        },
                        "required": ["location"]
                    }
                }
            }
        ]
    }
)

print(response2.text)

Example - Multiple Tools: You can provide multiple tools and let the model choose which ones to call:

response = edgee.send(
    model="gpt-5.2",
    input={
        "messages": [
            {"role": "user", "content": "Get the weather in Paris and send an email about it"}
        ],
        "tools": [
            {
                "type": "function",
                "function": {
                    "name": "get_weather",
                    "description": "Get the current weather for a location",
                    "parameters": {
                        "type": "object",
                        "properties": {
                            "location": {"type": "string", "description": "City name"}
                        },
                        "required": ["location"]
                    }
                }
            },
            {
                "type": "function",
                "function": {
                    "name": "send_email",
                    "description": "Send an email to a recipient",
                    "parameters": {
                        "type": "object",
                        "properties": {
                            "to": {"type": "string", "description": "Recipient email address"},
                            "subject": {"type": "string", "description": "Email subject"},
                            "body": {"type": "string", "description": "Email body"}
                        },
                        "required": ["to", "subject", "body"]
                    }
                }
            }
        ],
        "tool_choice": "auto"
    }
)

Streaming with Tools

The stream() method also supports tools. For details about streaming, see the Stream Method documentation.

for chunk in edgee.stream("gpt-5.2", {
    "messages": [
        {"role": "user", "content": "What is the weather in Paris?"}
    ],
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "description": "Get the current weather for a location",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {"type": "string", "description": "City name"}
                    },
                    "required": ["location"]
                }
            }
        }
    ],
    "tool_choice": "auto"
}):
    if chunk.text:
        print(chunk.text, end="", flush=True)
    
    # Check for tool calls in the delta
    tool_calls = chunk.choices[0].delta.tool_calls if chunk.choices else None
    if tool_calls:
        print(f"\nTool calls detected: {tool_calls}")
    
    if chunk.finish_reason == "tool_calls":
        print("\nModel requested tool calls")

Best Practices

1. Always Provide Descriptions

Descriptions help the model understand when to use each function:

# ✅ Good
{
    "name": "get_weather",
    "description": "Get the current weather conditions for a specific location",
    "parameters": {...}
}

# ❌ Bad
{
    "name": "get_weather",
    # Missing description
    "parameters": {...}
}

2. Use Clear Parameter Names

# ✅ Good
"properties": {
    "location": {"type": "string", "description": "The city name"}
}

# ❌ Bad
"properties": {
    "loc": {"type": "string"}  # Unclear name, no description
}

3. Mark Required Parameters

"parameters": {
    "type": "object",
    "properties": {
        "location": {"type": "string", "description": "City name"},
        "unit": {"type": "string", "description": "Temperature unit"}
    },
    "required": ["location"]  # location is required, unit is optional
}

4. Handle Multiple Tool Calls

Models can request multiple tool calls in a single response. Use parallel execution when possible:

import asyncio

if response.tool_calls and len(response.tool_calls) > 0:
    async def execute_tool_call(tool_call):
        args = json.loads(tool_call["function"]["arguments"])
        result = await execute_function(tool_call["function"]["name"], args)
        return {
            "tool_call_id": tool_call["id"],
            "result": result
        }
    
    # Execute all tool calls in parallel
    results = await asyncio.gather(*[
        execute_tool_call(tool_call) for tool_call in response.tool_calls
    ])
    
    # Add all tool results to messages
    for result in results:
        messages.append({
            "role": "tool",
            "tool_call_id": result["tool_call_id"],
            "content": json.dumps(result["result"])
        })

Example - Handling Multiple Tool Calls:

# Step 2: Execute all tool calls
messages = [
    {"role": "user", "content": "What is the weather in Paris and Tokyo?"},
    response1.message  # Include assistant's message
]

if response1.tool_calls:
    for tool_call in response1.tool_calls:
        args = json.loads(tool_call["function"]["arguments"])
        result = await get_weather(args["location"], args.get("unit"))
        
        messages.append({
            "role": "tool",
            "tool_call_id": tool_call["id"],
            "content": json.dumps(result)
        })

5. Error Handling in Tool Execution

if response.tool_calls:
    for tool_call in response.tool_calls:
        try:
            args = json.loads(tool_call["function"]["arguments"])
            result = await execute_function(tool_call["function"]["name"], args)
            
            messages.append({
                "role": "tool",
                "tool_call_id": tool_call["id"],
                "content": json.dumps(result)
            })
        except Exception as error:
            # Send error back to model
            messages.append({
                "role": "tool",
                "tool_call_id": tool_call["id"],
                "content": json.dumps({"error": str(error)})
            })

6. Keep Tools Available

Include tools in follow-up requests so the model can call them again if needed:

response2 = edgee.send(
    model="gpt-5.2",
    input={
        "messages": [...messages_with_tool_results],
        "tools": [
            # Keep the same tools available
            {"type": "function", "function": {...}}
        ]
    }
)

Example - Checking for Tool Calls:

if response.tool_calls:
    # Model wants to call a function
    for tool_call in response.tool_calls:
        print(f"Function: {tool_call['function']['name']}")
        print(f"Arguments: {tool_call['function']['arguments']}")

Example - Executing Functions and Sending Results:

# Execute the function
tool_call = response.tool_calls[0]
args = json.loads(tool_call["function"]["arguments"])
weather_result = await get_weather(args["location"], args.get("unit"))

# Send the result back
response2 = edgee.send(
    model="gpt-5.2",
    input={
        "messages": [
            {"role": "user", "content": "What is the weather in Paris?"},
            response.message,  # Include assistant's message with tool_calls
            {
                "role": "tool",
                "tool_call_id": tool_call["id"],
                "content": json.dumps(weather_result)
            }
        ],
        "tools": [
            # Include the same tools for potential follow-up calls
            {
                "type": "function",
                "function": {
                    "name": "get_weather",
                    "description": "Get the current weather for a location",
                    "parameters": {...}
                }
            }
        ]
    }
)

print(response2.text)
# "The weather in Paris is 15°C and sunny."

SDK Documentation

Documentation Index

​Overview

​Tool Definition

​FunctionDefinition

​Parameters Schema

​Tool Choice

​Tool Call Object Structure

​Parsing Arguments

​Complete Example

​Streaming with Tools

​Best Practices

​1. Always Provide Descriptions

​2. Use Clear Parameter Names

​3. Mark Required Parameters

​4. Handle Multiple Tool Calls

​5. Error Handling in Tool Execution

​6. Keep Tools Available