Passing Functions as Tools

[ParthSareen]

Features:

• Pass in python functions as tools into .chat(tools=[python_func,...]) 🥳
• Follows Google Python Docstring Styleguide - See Google Docstrings
• Lenient on docstring specification - should handle unusual cases elegantly
• Can still use a mixture of Python functions as tools and JSON values - feature is purely additive.

Examples to come on follow up for both Pydantic and Functions as Tools

[ParthSareen]

Blocked on ollama/ollama#7613 to support typing options

[mxyng]

Is parameters required?

[ParthSareen]

So in the previous behavior - no.
But since the last Pydantic PR you have to provide Parameters. Tested out both the OpenAI Python SDK with Ollama and the current published version of ollama-python. I think it might be worthwhile to have the Tool class have optional on all params to make sure it is backwards compatible.

Seems like function calling still works with not a fully-fledged JSON (I'm sure it's flakey but not our job).

Proposed Tool def'n:

class Tool(SubscriptableBaseModel):
  type: Optional[Literal['function']] = 'function'

  class Function(SubscriptableBaseModel):
    name: Optional[str] = None
    description: Optional[str] = None

    class Parameters(SubscriptableBaseModel):
      type: Optional[Literal['object']] = 'object'
      required: Optional[Sequence[str]] = None

      class Property(SubscriptableBaseModel):
        model_config = ConfigDict(arbitrary_types_allowed=True)

        type: Optional[str] = None
        description: Optional[str] = None

      properties: Optional[Mapping[str, Property]] = None

    parameters: Optional[Parameters] = None

  function: Optional[Function] = None

[mxyng]

I tend to avoid regexp when possible since it's hard to grok. In this scenario, a simpler solution would be to split on the mandatory : than parse the pre-colon and post-colon sections independently. Here's an example that passes your tests

  for line in parsed_docstring['args'].splitlines():
    pre, _, post = line.partition(':')
    if not pre.strip():
      continue
    if not post.strip() and last_key:
      parsed_docstring[last_key] += ' ' + pre
      continue

    arg_name, _, _ = pre.replace('(', ' ').partition(' ')
    last_key = arg_name.strip()

    parsed_docstring[last_key] = post.strip()

[ParthSareen]

TODO @ParthSareen to spin out issue

[mxyng]

If null is the only type (for some reason), this will be an empty string

[ParthSareen]

I think this is okay, IMO something like:

def (a:None, b:type(None)):
  ...

is extremely unlikely