Starting MLX Chat on port 7860
Sharing: False
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Fetching 6 files: 100%|██████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 6.34it/s]
Traceback (most recent call last):
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/queueing.py", line 527, in process_events
response = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/route_utils.py", line 261, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/blocks.py", line 1786, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/blocks.py", line 1350, in call_function
prediction = await utils.async_iteration(iterator)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/utils.py", line 583, in async_iteration
return await iterator.__anext__()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/utils.py", line 709, in asyncgen_wrapper
response = await iterator.__anext__()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/chat_interface.py", line 545, in _stream_fn
first_response = await async_iteration(generator)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/utils.py", line 583, in async_iteration
return await iterator.__anext__()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/utils.py", line 576, in __anext__
return await anyio.to_thread.run_sync(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 2144, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 851, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/gradio/utils.py", line 559, in run_sync_iterator_async
return next(iterator)
^^^^^^^^^^^^^^
File "/Users/qian/projects/github/chat-with-mlx/chat_with_mlx/app.py", line 203, in chatbot
response = client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/_utils/_utils.py", line 275, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/resources/chat/completions.py", line 667, in create
return self._post(
^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/_base_client.py", line 1213, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/_base_client.py", line 902, in request
return self._request(
^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/_base_client.py", line 978, in _request
return self._retry_request(
^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/_base_client.py", line 1026, in _retry_request
return self._request(
^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/_base_client.py", line 978, in _request
return self._retry_request(
^^^^^^^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/_base_client.py", line 1026, in _retry_request
return self._request(
^^^^^^^^^^^^^^
File "/Users/qian/miniconda3/envs/mlx-chat/lib/python3.11/site-packages/openai/_base_client.py", line 993, in _request
raise self._make_status_error_from_response(err.response) from None
openai.InternalServerError: Error code: 503
Model has loaded, but got this error when ask. Change model got the same error.I was installed with the manual way, using the main branch to install.
chat-with-mlx (mlx-chat) 16:45:31