We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
The latest version throws these errors:
2025-01-02 17:56:23,429 - ERROR livekit.agents - Error in _main_task Traceback (most recent call last): File ".venv/lib/python3.11/site-packages/livekit/agents/utils/log.py", line 16, in async_fn_logs return await fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File ".venv/lib/python3.11/site-packages/livekit/agents/multimodal/multimodal_agent.py", line 440, in _main_task self._session._push_audio(f) ^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'RealtimeSession' object has no attribute '_push_audio' {"pid": 70605, "job_id": "AJ_XKj9HCV3ev3q"} ... 025-01-02 17:56:44,426 - ERROR livekit - failed to emit event playout_stopped Traceback (most recent call last): File ".venv/lib/python3.11/site-packages/livekit/rtc/event_emitter.py", line 58, in emit callback(*callback_args) File ".venv/lib/python3.11/site-packages/livekit/agents/multimodal/multimodal_agent.py", line 403, in _on_playout_stopped if self._model.capabilities.supports_truncate: ^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'RealtimeModel' object has no attribute 'capabilities' {"pid": 70605, "job_id": "AJ_XKj9HCV3ev3q"}
I'm using the same code as in main.py in the playground https://github.com/livekit-examples/realtime-playground/blob/main/agent/main.py#L107-L118
main.py
The effect is that the AI voice comes through but the user's voice is not sent to OpenAI
This doesn't occur with 0.12.5
$ uv pip list | grep livekit livekit 0.18.3 livekit-agents 0.12.6 livekit-api 0.8.1 livekit-plugins-openai 0.10.11 livekit-protocol 0.8.0
Also, not sure if it is related, but there's a type error now
The text was updated successfully, but these errors were encountered:
Looks like the _push_audio error is caused by the Google Gemini PR #1240
_push_audio
https://github.com/livekit/agents/pull/1240/files#diff-befd34593d416d90bf9a5627bdc07bd03f10bd8e174dbe8106de458450aa029aR440
Sorry, something went wrong.
this is an issue with incompatible versions of the openai plugin. can you update the plugin to 0.10.13 ?
0.10.13
@davidzhao the issue i get with 0.10.13 is about WeakSet (#1326)
WeakSet
but with livekit-plugins-openai 0.10.14, now it works. Thanks 🙏
0.10.14
$ uv pip list | grep livekit livekit 0.18.3 livekit-agents 0.12.7 livekit-api 0.8.1 livekit-plugins-openai 0.10.14
No branches or pull requests
The latest version throws these errors:
I'm using the same code as in
main.py
in the playgroundhttps://github.com/livekit-examples/realtime-playground/blob/main/agent/main.py#L107-L118
The effect is that the AI voice comes through but the user's voice is not sent to OpenAI
This doesn't occur with 0.12.5
$ uv pip list | grep livekit livekit 0.18.3 livekit-agents 0.12.6 livekit-api 0.8.1 livekit-plugins-openai 0.10.11 livekit-protocol 0.8.0
Also, not sure if it is related, but there's a type error now
The text was updated successfully, but these errors were encountered: