Got {'error': 'Format duration is not supported by Outlines'} error when I sent message in patient-intake-ui.

Hello, thank you for your great assets for AI agents in healthcare.

I tried "industries/healthcare/agentic-healthcare-front-desk".
But, I can't test this application by bellow errors.

This is the screenshot when I sent message("hello").

And more, I attached docker compose logs.

patient-intake-ui  | Traceback (most recent call last):
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/queueing.py", line 536, in process_events
patient-intake-ui  |     response = await route_utils.call_process_api(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/route_utils.py", line 321, in call_process_api
patient-intake-ui  |     output = await app.get_blocks().process_api(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1935, in process_api
patient-intake-ui  |     result = await self.call_function(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1532, in call_function
patient-intake-ui  |     prediction = await utils.async_iteration(iterator)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 671, in async_iteration
patient-intake-ui  |     return await iterator.__anext__()
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 664, in __anext__
patient-intake-ui  |     return await anyio.to_thread.run_sync(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 56, in run_sync
patient-intake-ui  |     return await get_async_backend().run_sync_in_worker_thread(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 2470, in run_sync_in_worker_thr
ead
patient-intake-ui  |     return await future
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 967, in run
patient-intake-ui  |     result = context.run(func, *args)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 647, in run_sync_iterator_async
patient-intake-ui  |     return next(iterator)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 809, in gen_wrapper
patient-intake-ui  |     response = next(iterator)
patient-intake-ui  |   File "/app/utils/ui.py", line 86, in interact
patient-intake-ui  |     for event in events:
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/pregel/__init__.py", line 1612, in stream
patient-intake-ui  |     for _ in runner.tick(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/pregel/runner.py", line 104, in tick
patient-intake-ui  |     run_with_retry(t, retry_policy, writer=writer)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/pregel/retry.py", line 40, in run_with_retry
patient-intake-ui  |     task.proc.invoke(task.input, config)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/utils/runnable.py", line 410, in invoke
patient-intake-ui  |     input = context.run(step.invoke, input, config, **kwargs)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/utils/runnable.py", line 184, in invoke
patient-intake-ui  |     ret = context.run(self.func, input, **kwargs)
patient-intake-ui  |   File "/app/graph_definitions/graph_patient_intake_only.py", line 103, in __call__
patient-intake-ui  |     result = self.runnable.invoke(state)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/runnables/base.py", line 3047, in invoke
patient-intake-ui  |     input_ = context.run(step.invoke, input_, config)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/runnables/base.py", line 5430, in invoke
patient-intake-ui  |     return self.bound.invoke(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 372, in invok
e
patient-intake-ui  |     self.generate_prompt(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 957, in gener
ate_prompt
patient-intake-ui  |     return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 776, in gener
ate
patient-intake-ui  |     self._generate_with_cache(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 1022, in _gen
erate_with_cache
patient-intake-ui  |     result = self._generate(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_nvidia_ai_endpoints/chat_models.py", line 383, in _gener
ate
patient-intake-ui  |     response = self._client.get_req(payload=payload, extra_headers=extra_headers)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_nvidia_ai_endpoints/_common.py", line 478, in get_req
patient-intake-ui  |     response, session = self._post(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_nvidia_ai_endpoints/_common.py", line 374, in _post
patient-intake-ui  |     self._try_raise(response)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_nvidia_ai_endpoints/_common.py", line 467, in _try_raise
patient-intake-ui  |     raise Exception(f"{header}\n{body}") from None
patient-intake-ui  | Exception: [###] Format duration is not supported by Outlines
patient-intake-ui  | {'error': 'Format duration is not supported by Outlines'}
patient-intake-ui  | Traceback (most recent call last):
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/queueing.py", line 536, in process_events
patient-intake-ui  |     response = await route_utils.call_process_api(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/route_utils.py", line 321, in call_process_api
patient-intake-ui  |     output = await app.get_blocks().process_api(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1935, in process_api
patient-intake-ui  |     result = await self.call_function(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1532, in call_function
patient-intake-ui  |     prediction = await utils.async_iteration(iterator)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 671, in async_iteration
patient-intake-ui  |     return await iterator.__anext__()
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 664, in __anext__
patient-intake-ui  |     return await anyio.to_thread.run_sync(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 56, in run_sync
patient-intake-ui  |     return await get_async_backend().run_sync_in_worker_thread(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 2470, in run_sync_in_worker_thr
ead
patient-intake-ui  |     return await future
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 967, in run
patient-intake-ui  |     result = context.run(func, *args)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 647, in run_sync_iterator_async
patient-intake-ui  |     return next(iterator)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 809, in gen_wrapper
patient-intake-ui  |     response = next(iterator)
patient-intake-ui  |   File "/app/utils/ui.py", line 86, in interact
patient-intake-ui  |     for event in events:
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/pregel/__init__.py", line 1612, in stream
patient-intake-ui  |     for _ in runner.tick(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/pregel/runner.py", line 104, in tick
patient-intake-ui  |     run_with_retry(t, retry_policy, writer=writer)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/pregel/retry.py", line 40, in run_with_retry
patient-intake-ui  |     task.proc.invoke(task.input, config)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/utils/runnable.py", line 410, in invoke
patient-intake-ui  |     input = context.run(step.invoke, input, config, **kwargs)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langgraph/utils/runnable.py", line 184, in invoke
patient-intake-ui  |     ret = context.run(self.func, input, **kwargs)
patient-intake-ui  |   File "/app/graph_definitions/graph_patient_intake_only.py", line 103, in __call__
patient-intake-ui  |     result = self.runnable.invoke(state)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/runnables/base.py", line 3047, in invoke
patient-intake-ui  |     input_ = context.run(step.invoke, input_, config)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/runnables/base.py", line 5430, in invoke
patient-intake-ui  |     return self.bound.invoke(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 372, in invok
e
patient-intake-ui  |     self.generate_prompt(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 957, in gener
ate_prompt
patient-intake-ui  |     return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 776, in gener
ate
patient-intake-ui  |     self._generate_with_cache(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 1022, in _gen
erate_with_cache
patient-intake-ui  |     result = self._generate(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_nvidia_ai_endpoints/chat_models.py", line 383, in _gener
ate
patient-intake-ui  |     response = self._client.get_req(payload=payload, extra_headers=extra_headers)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_nvidia_ai_endpoints/_common.py", line 478, in get_req
patient-intake-ui  |     response, session = self._post(
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_nvidia_ai_endpoints/_common.py", line 374, in _post
patient-intake-ui  |     self._try_raise(response)
patient-intake-ui  |   File "/usr/local/lib/python3.10/dist-packages/langchain_nvidia_ai_endpoints/_common.py", line 467, in _try_raise
patient-intake-ui  |     raise Exception(f"{header}\n{body}") from None
patient-intake-ui  | Exception: [###] Format duration is not supported by Outlines
patient-intake-ui  | {'error': 'Format duration is not supported by Outlines'}

Reproduce the failure with the healthcare front-desk application and its Docker Compose logs. Start at /app/utils/ui.py line 86 and graph_definitions/graph_patient_intake_only.py line 103, then inspect the NVIDIA endpoint request shown in the traceback. Done means sending a message completes without the Outlines duration-format error.