Colang 2.0 multi_modal tutorial error

[rgstephens]

Running the multi_modal_demo_v2_x tutorial when trying to start the number guessing flow, play the number guessing game, it fails with this error if I run it as a server.

Total processing took 0.33 seconds. LLM Stats: 0 total calls, 0 total time, 0 total tokens, 0 total prompt tokens, 0 total completion tokens, [] as latencies
INFO:     127.0.0.1:53421 - "POST /v1/chat/completions HTTP/1.1" 200 OK
ERROR:nemoguardrails.server.api:Providing `assistant` messages as input is not supported for Colang 2.0 configurations.
Traceback (most recent call last):
  File "/Users/greg/Dev/nemo/NeMo-Guardrails-rgstephens/nemoguardrails/server/api.py", line 337, in chat_completion
    res = await llm_rails.generate_async(
  File "/Users/greg/Dev/nemo/NeMo-Guardrails-rgstephens/nemoguardrails/rails/llm/llmrails.py", line 629, in generate_async
    events = self._get_events_for_messages(messages, state)
  File "/Users/greg/Dev/nemo/NeMo-Guardrails-rgstephens/nemoguardrails/rails/llm/llmrails.py", line 490, in _get_events_for_messages
    raise ValueError(
ValueError: Providing `assistant` messages as input is not supported for Colang 2.0 configurations.

Does this demo require a special UI?

[drazvan]

The server UI does not work with Colang 2.0. You can only test it through the nemoguardrails chat CLI. We'll try to fix for 0.10 as well.

[rgstephens]

Thanks, with the multi-modal gestures are there any interfaces that you're working with that support this with graphics or digital human interfaces?

[grupocopa]

Hey @drazvan, how are you?

I am trying to test my NeMo Framework Colang 2.x with a platform which has a Firebase database, where I have the control of the whole events and thread ids.

I want to know if this problem is still on a bug, and if is that a way to make API requisitions to ask my models inside NeMo, like Colang 1.0, to have async requisitions as different users with their properly userids