feat: function calling support in a chat session's `prompt` function

[giladgd]

Make it possible to provide functions that the model can call as part of the response.

It should be as simple as something like that:

const res = await chatSession.prompt("What is the current weather?", {
    functions: {
        getWeather: {
            description: "Get the current weather for a location"
            params: {
                location: {
                    type: "string"
                }
            },
            handler({location}) {
                console.log("Providing fake weather for location:", location);

                return {
                    temperature: 32,
                    raining: true,
                    unit: "celsius"
                };
            }
        },
        getCurrentLocation: {
            description: "Get the current location",
            handler() {
                console.log("Providing fake location");

                return "New York, New York, United States".
            }
        }
    }
});
console.log(res);

If you have ideas of a text format I can use to prompt the model with, please share. I'm looking for a format that can achieve all of these:

• A way to give the model the list of possible functions, while utilizing as few tokens for this as possible. It can also be OK to give the model only a brief overview of the available functions and let it fetch more info about a function on demand.
• Make it easy to stream regular text, while still distinguishing between regular text that the model writes and a function call it tries to do

I thought about implementing support for this format as part of GeneralChatPromptWrapper, but I'm not really sure whether this the safest way to distinguish between text and function calling:

You are a helpful, respectful and honest assistant. Always answer as helpfully as possible.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct.
If you don't know the answer to a question, please don't share false information.

Available functions:
` ` `
function getWeather(params: {location: string});
function getCurrentLocation();
` ` `

You can call these functions by writing a text like that:
[[call: myFunction({param1: "value"})]]

### Human:
What is the current weather?

### Assistant:

Then when the model will write text, it may go like that:

I'll get the current location to fetch the weather for it.
[[call: getCurrentLocation()]]

I'll then detect the function call in the model response and evaluate this text:

[[result: "New York, New York, United States"]]

So the model can then continue to provide completion:

I'll now get the current weather for New York, New York, United States.
[[call: getWeather({location: "New York, New York, United States"})]]

I'll then detect the function call in the model response and evaluate this text:

[[result: {temperature: 32, raining: true, unit: "celsius"}]]

So the model can then continue to provide completion:

The current weather for New York, New York, United States is 32 degrees celsius and it's currently raining

I plan to use grammar tricks to make sure the model can only call existing functions and with the right parameter types.

How you can help

• If you have an idea of a better format, please let me know
• If you have an idea of a good way to implement this in the LlamaChat (see LlamaChatPromptWrapper) format, this would also be very helpful

I'm currently working on a major change in this module, so if you'd like to help with implementing any of this, please let me know beforehand so your work won't become incompatible with the new changes

[github-actions[bot]]

:tada: This issue has been resolved in version 3.0.0-beta.2 :tada:

The release is available on:

• npm package (@beta dist-tag)
• GitHub release
• v3.0.0-beta.2

Your semantic-release bot :package::rocket:

[github-actions[bot]]

:tada: This issue has been resolved in version 3.0.0-beta.4 :tada:

The release is available on:

• npm package (@beta dist-tag)
• GitHub release
• v3.0.0-beta.4

Your semantic-release bot :package::rocket: