Werken met meerdere functies

AI-systemen ontwikkelen met de OpenAI API

Francesca Donadoni

Curriculum Manager, DataCamp

Parallel function calling

Een diagram van een aanroep naar de OpenAI API met function calling

Parallel function calling

Een diagram van een aanroep naar de OpenAI API met function calling met meerdere functies

Voorbeeldbericht

function_definition = [{'type': 'function','function':
        {'name': 'extract_job_info',
        'description': 'Get the job information from the body of the input text',
        'parameters': {
            'type': 'object',
            'properties': {
                'job': {'type': 'string', 'description': 'Job title'},
                'location': {'type': 'string', 'description': 'Location'}}
        }}
    }]

Voorbeeldbericht

function_definition.append({'type': 'function',
        'function':{
            'name': 'get_timezone',
            'description': 'Return the timezone corresponding to the location in the 
                            job advert',
            'parameters': {
            'type': 'object',
            'properties': {
                'timezone': {'type': 'string','description': 'Timezone'}}}
        }
    }
)

Voorbeeldbericht

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    tools=function_definition
)

Voorbeeldantwoord

# Print the arguments of the first function
print(response.choices[0].message.tool_calls[0].function.arguments)

{"job": "Data Scientist", "location": "San Francisco, CA"}

# Print the arguments of the second function
print(response.choices[0].message.tool_calls[1].function.arguments)

{"timezone": "America/Los_Angeles"}

Specifieke functies instellen

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    tools=function_definition,

    tool_choice='auto'

)

Specifieke functies instellen

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    tools=function_definition,
    tool_choice={'type': 'function', 
                         'function': {'name': 'extract_job_info'}
                 }
)

Antwoord dubbelchecken

messages = []
messages.append({"role": "system", "content": "Don't make assumptions about what 
values to plug into functions. Don't make up values to fill the response with."})
messages.append({"role": "system", "content": "Ask for clarification if needed."})
messages.append({"role": "user", "content": "What is the starting salary 
                                             for the role?"})

Antwoord dubbelchecken

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    tools=function_definition
)
print(response.choices[0].message.content)

I don't have information about the starting salary for the role. If you'd like, I 
can help you extract the job information from the description and then provide 
additional assistance.

Laten we oefenen!

AI-systemen ontwikkelen met de OpenAI API