async def count_tokens(
        self,
        request: Optional[Union[generative_service.CountTokensRequest, dict]] = None,
        *,
        model: Optional[str] = None,
        contents: Optional[MutableSequence[content.Content]] = None,
        retry: OptionalRetry = gapic_v1.method.DEFAULT,
        timeout: Union[float, object] = gapic_v1.method.DEFAULT,
        metadata: Sequence[Tuple[str, str]] = (),
    if you don't use keyword args : model=model, contents=contents,  but position args, this will lead to : TypeError: count_tokens() takes from 1 to 2 positional arguments but 3 were given

* Add smkoe tests for count_tokens.

* fix docstring

…the readme (#129)

* Update links to https://github.com/google/generative-ai-docs

* Update links to https://github.com/google/generative-ai-docs

* aiter, anext not exist error

* Un-skip test, format with black.

* Fix aiter & anext implementations.

---------

Co-authored-by: Mark Daoust <markdaoust@google.com>

…c keyword (#140)

* Fix: Index out out range with empty parts []

while question was blocked by api, the parts is an empty list [], 
so the exp: 
if len(parts) > 1 or "text" not in parts[0]:
will raise list index out of range, but not ValueError

* simplify parts length check.

* Update error message.

---------

Co-authored-by: Mark Daoust <markdaoust@google.com>

* fix: handle empty string in ChatSession.send_message

* refactor: move empty string handling to content_types.to_content

* ValueError

---------

Co-authored-by: Mark Daoust <markdaoust@google.com>

* Update comments in class GenerativeModel

* typo

---------

Co-authored-by: Mark Daoust <markdaoust@google.com>

* import typeddict from typing_extentions

* Add typing-extensions

* Move shim logic to one file.

* typo

* simpilfy

* order

---------

Co-authored-by: Mark Daoust <markdaoust@google.com>