Function calling enables dynamic workflows by allowing the model to select and suggest function calls based on user input, which helps in building agentic workflows. By defining a set of functions, or tools, you provide context that lets the model recommend and fill in function arguments as needed.
Function calling enables adaptive workflows that leverage real-time data and structured outputs, creating more dynamic and responsive model interactions.
Submit a Query with tools: Start by submitting a user query along with available tools defined in JSON Schema. This schema specifies parameters for each function.
The model processes and suggests: The model interprets the query, assesses intent, and decides if it will respond conversationally or suggest function calls. If a function is called, it fills in the arguments based on the schema.
Receive a model response: You’ll get a response from the model, which may include a function call suggestion. Execute the function with the provided arguments and return the result to the model for further interaction.
To get better quality in tool calling requests with gpt-oss-120b, it is recommended to set the reasoning_effort to high
Meta recommends using Llama 70B-Instruct for applications that combine conversation and tool calling. Llama 8B-Instruct cannot reliably maintain a conversation alongside tool-calling definitions. It can be used for zero-shot tool calling, but tool instructions should be removed for regular conversations.
Define a JSON schema for your function. You will need to specify:
The name of the function.
A description of what it does.
The parameters, their data types, and descriptions.
Example schema for getting the weather
Copy
Ask AI
{ "type": "function", "function": { "name": "get_weather", "description": "Gets the current weather information for a given city.", "parameters": { "type": "object", "properties": { "city": { "type": "string", "description": "Name of the city to get weather information for." } }, "required": ["city"] } }}
Step 2: Configure function calling in your request
When sending a request, include the function definition in the tools parameter and set tool_choice to the following:
auto : allows the model to choose between generating a message or calling a function. This is the default tool choice when the field is not specified.
required : This forces the model to generate a function call. The model will then always select one or more function(s) to call.
To enforce a specific function call, set tool_choice = {"type": "function", "function": {"name": "get_weather"}}. This ensures the model will only use the specified function.
The following code block shows a fake weather lookup that returns a random temperature between 20°C and 50°C. For accurate and real-time weather data, use a proper weather API.
Copy
Ask AI
import sambanovaimport randomimport json# Initialize the client with the SambaNova base URL and API keyclient = sambanova.SambaNova( base_url="your-sambanova-base-url", api_key="your-sambanova-api-key")MODEL = 'Meta-Llama-3.3-70B-Instruct'def get_weather(city: str) -> dict: """ Fake weather lookup: returns a random temperature between 20°C and 50°C. """ temp = random.randint(20, 50) return { "city": city, "temperature_celsius": temp }tools = [ { "type": "function", "function": { "name": "get_weather", "description": "Get weather of an location, the user shoud supply a location first", "parameters": { "type": "object", "properties": { "city": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", } }, "required": ["city"] }, } },]messages = [{"role": "user", "content": "What's the weather like in Paris today?"}]completion = client.chat.completions.create( model=MODEL, messages=messages, tools=tools)print(completion)
If the model chooses to call a function, you will find tool_calls in the response. Extract the function call details and execute the corresponding function with the provided parameters.
The following code block shows a fake weather lookup that returns a random temperature between 20°C and 50°C. For accurate and real-time weather data, use a proper weather API.
Copy
Ask AI
import sambanovaimport randomimport json# Define the SambaNova clientclient = sambanova.SambaNova( base_url="your-sambanova-base-url", api_key="your-sambanova-api-key")MODEL = 'Meta-Llama-3.3-70B-Instruct'def get_weather(city: str) -> dict: """ Fake weather lookup: returns a random temperature between 20°C and 50°C. """ temp = random.randint(20, 50) return { "city": city, "temperature_celsius": temp }tools = [ { "type": "function", "function": { "name": "get_weather", "description": "Get weather of an location, the user shoud supply a location first", "parameters": { "type": "object", "properties": { "city": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", } }, "required": ["city"] }, } },]messages = [{"role": "user", "content": "What's the weather like in Paris today?"}]completion = client.chat.completions.create( model=MODEL, messages=messages, tools=tools)print(completion)tool_call = completion.choices[0].message.tool_calls[0]args = json.loads(tool_call.function.arguments)result = get_weather(args["city"])messages.append({ # append model's function call message "role": "assistant", "content": None, "tool_calls": [tool_call]})messages.append({ # append result message "role": "tool", "tool_call_id": tool_call.id, "content": json.dumps(result)})completion_2 = client.chat.completions.create( model=MODEL, messages=messages,)print(completion_2.choices[0].message.content)
You can set the response_format parameter to your defined schema to ensure the model produces a JSON object that matches your specified structure.
Copy
Ask AI
import sambanovaimport json# Define the SambaNova clientclient = sambanova.SambaNova( base_url="your-sambanova-base-url", api_key="your-sambanova-api-key")MODEL = "DeepSeek-V3-0324"# Define the schemaresponse_format = { "type": "json_schema", "json_schema": { "name": "data_extraction", "schema": { "type": "object", "properties": { "section": { "type": "string" }, "products": { "type": "array", "items": { "type": "string" } } }, "required": ["section", "products"], "additionalProperties": False }, "strict": False }}# Call the APIcompletion = client.chat.completions.create( model=MODEL, messages=[ { "role": "system", "content": "You are an expert at structured data extraction. You will be given unstructured text and should convert it into the given structure." }, { "role": "user", "content": "the section 24 has appliances, and videogames" } ], response_format=response_format)# Print the parsed resultprint(completion)
Ensure to set the "strict" parameter to false, as true isn’t supported yet. When it is available, it will ensure the model strictly follows your function schema instead of making a best-effort attempt.
You can set the response_format parameter to json_object in your request to ensure that the model outputs a valid JSON. In case the mode is not able to generate a valid JSON, an error will be returned.
In case the model fails to generate a valid JSON, you will get an error message Model did not output valid JSON.
Copy
Ask AI
import sambanova# Define the SambaNova clientclient = sambanova.SambaNova( base_url="your-sambanova-base-url", api_key="your-sambanova-api-key")MODEL = 'Meta-Llama-3.3-70B-Instruct'def run_conversation(user_prompt): # Initial conversation with user input messages = [ { "role": "system", "content": "Always provide the response in this JSON format: {\"country\": \"name\", \"capital\": \"xx\"}" }, { "role": "user", "content": user_prompt, } ] # First API call to get model's response response = client.chat.completions.create( model=MODEL, messages=messages, max_tokens=500, response_format = { "type": "json_object"}, # stream = True ) response_message = response.choices[0].message print(response_message)run_conversation('what is the capital of Austria')