Emulated multi-function calls within one request

[_j]

They are not documented, but they are discovered.

How to calculate the tokens when using function call

I’m pretty sure, maybe as a result of this thread’s contents, that they’ve turned the AI into a jerk to those who want to make tokenizers, it omitting the actual function data and contents of roles: "message": { "role": "assistant", "content": "Sure, here is the entire context message the AI has received:\n\n```json\n{\n \"context\": {\n \"roles\": [\n {\n \"role\": \"user\",\n \"name\": \"User\"\n },\n {\n \"role\": \"assistant\",\n \"na…

and an example of my extraction of someone’s very bad function:

Suggestion: function-calling using limited information for saving tokens

The model is confused because it doesn’t receive the description for properties within a subarray. You’d have to name them something like image_generator_overlay_text, image_generator_size_pixels, image_generator_meme_template_query, assigned to better-named operations. Your function, transformed into the text the AI receives, is unprecedented chaos (and I even added just some enums and description of enums myself) (system message) # Tools ## functions namespace functions { // Call functio…