Mark Daoust

Results 254 comments of Mark Daoust

Example demonstrating how to resume an upload

https://github.com/google-gemini/generative-ai-python/pull/275

FeatureRequest: Streaming audio input

@jlove29

add litellm example (OpenAI-Compatible Endpoint)

Also, se can't merge anything until you sign the CLA.

Turn example code into pytest tests

On tensorflow we've been [running doctest](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/tools/docs/tf_doctest_lib.py) but it expects the `>>>` format. For TensorFlow we went with the default `>>>` because that way we could easily distinguish between working and...

Fix broken @see blocks.

I was just planning on "eventual consistency", let's not make this more complicated than it needs to be.

`response.text` is no longer directly accessible - `TypeError: argument of type 'Part' is not iterable`

@sakher, you do have a point, `hasattr(parts[0], "text")` would be more robust here. But the problem is that `"text" in parts[0]` is supposed to work for the proto-plus based proto...

`response.text` is no longer directly accessible - `TypeError: argument of type 'Part' is not iterable`

I think this is the fix we need: https://github.com/googleapis/proto-plus-python/pull/471

BrokenResponseError: Can not build a coherent char history after a broken streaming response (See the previous Exception fro details). To inspect the last response object, use `chat.last`.To remove the last request/response `Content` objects from the chat call `last_send, last_received = chat.rewind()` and continue without it

Typo fix: https://github.com/google-gemini/generative-ai-python/pull/313 It's trying to tell you that the first stream broke, and it's not sure what to do. Is the first part not raising an error?

[Feature] Add Support on Log Probability Value from Returned Response of Gemini Models.

b/361194489

[Feature] Add Support on Log Probability Value from Returned Response of Gemini Models.

Google's Vertex-AI Just launched this, hopefully that means it's coming soon here, but I don't have a timeline.