[bug] OpenFunctions-v2: how to continue conversation?

[tybalex]

This is more like a question rather than a bug, but what to do after the model returns a function call?

I followed this example:

To help with quick prototyping, we provide a hosted Gorilla Openfunctions-v2 model for inference. Or you can run it locally, or self-host it by accessing the model from [HuggingFace](https://huggingface.co/gorilla-llm/gorilla-openfunctions-v2). The example below, demonstrates how to invoke the hosted Gorilla Openfunctions-v2 model:
import openai

def get_gorilla_response(prompt="", model="gorilla-openfunctions-v2", functions=[]):
    openai.api_key = "EMPTY"  # Hosted for free with ❤️ from UC Berkeley
    openai.api_base = "http:https://luigi.millennium.berkeley.edu:8000/v1"
    try:
        completion = openai.ChatCompletion.create(
            model="gorilla-openfunctions-v2",
            temperature=0.0,
            messages=[{"role": "user", "content": prompt}],
            functions=functions,
        )
        # completion.choices[0].message.content, string format of the function call 
        # completion.choices[0].message.functions, Json format of the function call
        return completion.choices[0]
Prompt the model:
What's the weather like in the two cities of Boston and San Francisco?
Format your function call: The model will return the function call based on your request.
query = "What's the weather like in the two cities of Boston and San Francisco?"
functions = [
    {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location"],
        },
    }
]
Get Your Function Call: The model will return a Python function call based on your request.
This opens up possibilities for developers and non-developers alike, allowing them to leverage complex functionalities without writing extensive code.
Input:

get_gorilla_response(prompt=query, functions=[functions])
Output:

[get_current_weather(location='Boston, MA'), get_current_weather(location='San Francisco, CA')]

and assume I have function to check the weather of Boston and SF, how do I append those results back and continue the conversation?

[ShishirPatil]

Thanks for trying it out @tybalex
Let me preface it by mentioning that, OpenFunctions-v2 is currently tested for single-turn only, so multi-turn behavior is ill-defined. Anyways if you want to try it out. You would do as such:

completion = openai.ChatCompletion.create(
           model="gorilla-openfunctions-v2",
           temperature=0.0,
           messages=[{"role": "user", "content": prompt_1}, 
                                {"role": "assistant", "content": response_1},
                                {"role": "user", "content": prompt_2}],
           functions=functions,
       )

where you would replace prompt_1 is what you input the first time, response_1 is the LLM function call returned by the LLM, and prompt_2 is what you want to continue the convsersation.. Hope this helps!