Mark Daoust

The tflite page doesn't get regular updates either: https://www.tensorflow.org/lite/guide/ops_compatibility That xla command still works. One solution would be to integrate this into api-reference generator, add an XLA column to the...

> can we reopen this ticket adding also the XLA label? Done. It's an internal tool that runs those. They're run from the target version's github branch, with bazel available,...

Yes. It's possible that just integrating it into generate2.py with `subprocess.check_output(['bazel', 'run', '-c', 'opt', '--', 'tensorflow/compiler/tf2xla:tf2xla_supported_ops'])` could get the job done.

If anyone gets it working locally then it's my job to be sure it works in the CI.

Hi, I'm not able to reproduce any errors with these prompts, so this seems fixed. Thanks for reporting.

Interesting. What's the use case for sending an empty list of parts? It looks like this will ask the model to generate another response without a user response in between,...

@Vital1162 > This problem happened when ```max_output_tokens''' was too small for the response so no need to delete generation_config. That my experience This has been fixed, now it does return...

The main issue here is the `max_output_tokens` thing which is fixed. Closing. Please re-raise any persistent issues.

Yeah, so uploads go through a different channel compared to regular API calls. I had to customize the code to get that to work: https://github.com/google-gemini/generative-ai-python/blob/main/google/generativeai/client.py#L73 I haven't looked into it...

Okay, following up on my previous comment. It looks like the underlying `create_file` method doesn't actually support the necessary scopes. If I go into samples/rest/files.sh and substitute in the ADC...