Tool and Function Calling

This guide demonstrates how to use RTP-LLM’s Function calling functionality.

OpenAI Compatible API

Currently, RTP-LLM supports Function Calling capabilities for the following models:

• qwen25/qwen3: Qwen 2.5 (e.g. Qwen/Qwen2.5-1.5B-Instruct, Qwen/Qwen2.5-7B-Instruct) and QwQ (i.e. Qwen/QwQ-32B), Qwen3-235B-A22B, etc.

• Kimi_k2

• Qwen3-Coder

Define Tools for Function Call

Below is a Python snippet that shows how to define a tool as a dictionary. The dictionary includes a tool name, a description, and property defined Parameters.

# Define tools
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {
                        "type": "string",
                        "description": "The city to find the weather for, e.g. 'San Francisco'",
                    },
                    "state": {
                        "type": "string",
                        "description": "the two-letter abbreviation for the state that the city is"
                        " in, e.g. 'CA' which would mean 'California'",
                    },
                    "unit": {
                        "type": "string",
                        "description": "The unit to fetch the temperature in",
                        "enum": ["celsius", "fahrenheit"],
                    },
                },
                "required": ["city", "state", "unit"],
            },
        },
    }
]

Define Messages

def get_messages():
    return [
        {
            "role": "user",
            "content": "What's the weather like in Boston today? Output a reasoning before act, then use the tools to help you.",
        }
    ]


messages = get_messages()

Initialize the Client

# Initialize OpenAI-like client
client = OpenAI(api_key="None", base_url=f"http://0.0.0.0:{port}/v1")
model_name = client.models.list().data[0].id

Non-Streaming Request

# Non-streaming mode test
response_non_stream = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0,
    top_p=0.95,
    max_tokens=1024,
    stream=False,  # Non-streaming
    tools=tools,
)
print("Non-stream response:")
print(response_non_stream)
print("==== content ====")
print(response_non_stream.choices[0].message.content)
print("==== tool_calls ====")
print(response_non_stream.choices[0].message.tool_calls)

Handle Tools

When the engine determines it should call a particular tool, it will return arguments or partial arguments through the response. You can parse these arguments and later invoke the tool accordingly.

name_non_stream = response_non_stream.choices[0].message.tool_calls[0].function.name
arguments_non_stream = (
    response_non_stream.choices[0].message.tool_calls[0].function.arguments
)

print(f"Final streamed function call name: {name_non_stream}")
print(f"Final streamed function call arguments: {arguments_non_stream}")

Streaming Request

# Streaming mode test
print("Streaming response:")
response_stream = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0,
    top_p=0.95,
    max_tokens=1024,
    stream=True,  # Enable streaming
    tools=tools,
)

texts = ""
tool_calls = []
name = ""
arguments = ""
for chunk in response_stream:
    if chunk.choices[0].delta.content:
        texts += chunk.choices[0].delta.content
    if chunk.choices[0].delta.tool_calls:
        tool_calls.append(chunk.choices[0].delta.tool_calls[0])
print("==== Text ====")
print(texts)

print("==== Tool Call ====")
for tool_call in tool_calls:
    print(tool_call)

Handle Tools

When the engine determines it should call a particular tool, it will return arguments or partial arguments through the response. You can parse these arguments and later invoke the tool accordingly.

# Parse and combine function call arguments
arguments = []
for tool_call in tool_calls:
    if tool_call.function.name:
        print(f"Streamed function call name: {tool_call.function.name}")

    if tool_call.function.arguments:
        arguments.append(tool_call.function.arguments)

# Combine all fragments into a single JSON string
full_arguments = "".join(arguments)
print(f"streamed function call arguments: {full_arguments}")

Define a Tool Function

# This is a demonstration, define real function according to your usage.
def get_current_weather(city: str, state: str, unit: "str"):
    return (
        f"The weather in {city}, {state} is 85 degrees {unit}. It is "
        "partly cloudly, with highs in the 90's."
    )


available_tools = {"get_current_weather": get_current_weather}

Execute the Tool

messages.append(response_non_stream.choices[0].message)

# Call the corresponding tool function
tool_call = messages[-1].tool_calls[0]
tool_name = tool_call.function.name
tool_to_call = available_tools[tool_name]
result = tool_to_call(**(json.loads(tool_call.function.arguments)))
print(f"Function call result: {result}")
# messages.append({"role": "tool", "content": result, "name": tool_name})
messages.append(
    {
        "role": "tool",
        "tool_call_id": tool_call.id,
        "content": str(result),
        "name": tool_name,
    }
)

print(f"Updated message history: {messages}")

Send Results Back to Model

final_response = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0,
    top_p=0.95,
    stream=False,
    tools=tools,
)
print("Non-stream response:")
print(final_response)

print("==== Text ====")
print(final_response.choices[0].message.content)