Add notebook on fine tuning for function calling

[jhills20]

Summary

Adding fine tuning for function calling recipe. This generates synthetic data to improve the performance of function calling for a 'drone co-pilot ai'. The notebook shows how an untuned 3.5 Turbo fails to reject certain requests that the drone cannot do, and improperly calls functions. Then, the notebook creates invocations for every function, generates synthetic prompts that would lead to that invocation, and fine-tunes the model. The result is an improved model that properly rejects those questions.

Motivation

There is no notebook now on fine tuning for function calling, and this is a big customer need and ask.

---

For new content

When contributing new content, read through our contribution guidelines, and mark the following action items as completed:

• I have added a new entry in registry.yaml so that my content renders on the cookbook website.
• I have conducted a self-review of my content based on the c:
  • Relevance: This content is related to building with OpenAI technlogies and is useful to others.
  • Uniqueness: I have searched for related examples in the OpenAI Cookbook, and verified that my content offers new insights or unique information compared to existing documentation.
  • Spelling and Grammar: I have checked for spelling or grammatical mistakes.
  • Clarity: I have done a final read-through and verified that my submission is well-organized and easy to understand.
  • Correctness: The information I include is correct and all of my code executes successfully.
  • Completeness: I have explained everything fully, including all necessary references and citations.

We will rate each of these areas on a scale from 1 to 4, and will only accept contributions that score 3 or higher on all areas. Refer to our contributions guidelines for more details.

[ibigio]

This is going to be such an awesome notebook to share with people – love it!

[simonpfish]

This is a great notebook! People will find this very valuable. There is room for improvement in clarity, correctness, and grammar. I left some comments throughout the notebook.

Criteria	Description	Score	Explanation
Relevance	Is the content related to building with OpenAI technologies? Is it useful to others?	4	Your submission is highly relevant and provides useful information for individuals working with OpenAI tech.
Uniqueness	Does the content offer new insights or unique information compared to existing documentation?	4	The content presents completely unique perspectives and insights not covered in existing documentation.
Clarity	Is the language easy to understand? Are things well-explained? Is the title clear?	3	The language is clear, but there may be some sections where the structure or explanations could be improved.
Correctness	Are the facts, code snippets, and examples correct and reliable? Does everything execute correctly?	3	The factual information is accurate; however, there might be minor errors or improvements needed for code snippets.
Completeness	Is the content thorough and detailed? Are there things that weren’t explained fully?	4	The content is comprehensive and detailed, covering all necessary aspects of the topic.
Grammar	Are there grammatical or spelling errors present?	3	The submission has correct grammar with a few typos present.

[jhills20]

All changes should be made

[simonpfish]

Looks great! 🎉
Merging