Give me an example code for calling the functions endpoint in python
#OpenAI Functions calling in python
thin bronze
thick zephyrBOT
Hi @thin bronze. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Sure, here is an example of how to call functions with the OpenAI Python API, based on the information extracted from the GitHub issues:
import openai
def run_conversation(user_input):
messages = [{"role": "user", "content": user_input}]
tools = [
{
"type": "function",
"function": {
"name": "get_online_data",
"description": "Get real-time data from the web",
"parameters": {
"type": "object",
"properties": {
"input": {
"type": "string",
"description": "What is the latest stock price of Apple?",
},
},
"required": ["input"],
},
},
}
]
response = openai.chat.completions.create(
model="gpt-3.5-turbo-1106",
messages=messages,
tools=tools,
tool_choice="auto",
)
response_message = response.choices[0].message
total_tokens = response.usage.total_tokens
if response.choices[0].message.tool_calls is None:
return response_message.content + " Total tokens used: " + str(total_tokens)
In this example, a function named get_online_data is defined and called within the run_conversation function. The get_online_data function is expected to retrieve real-time data from the web based on the user's input. The openai.chat.completions.create method is used to generate a response from the model, and the response is processed to extract the message content and the total number of tokens used.
Please note that you need to replace "gpt-3.5-turbo-1106" with the actual model you are using, and you need to define the get_online_data function according to your requirements.
This code is based on the information extracted from this GitHub issue (https://github.com/openai/openai-python/issues/703).
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
thin bronze
How do I make sure the model always chooses a function or tool? @thick zephyr
thick zephyrBOT
Let me check the knowledge base for you. One moment! :books:
To ensure that the model always chooses a function or tool, you can specify the tool_choice parameter in your API call. This parameter controls which function or tool is called by the model.
Here's an example of how to do this:
response = openai.chat.completions.create(
model="gpt-3.5-turbo-1106",
messages=messages,
tools=tools,
tool_choice={
"type": "function",
"function": {
"name": "my_function"
}
},
)
In this example, the tool_choice parameter is set to a specific function named my_function. This forces the model to call that function.
Please note that you need to replace "gpt-3.5-turbo-1106" with the actual model you are using, and "my_function" with the actual function you want the model to call.