Error while running Riva Virtual Assistant Example

AI & Data Science Deep Learning (Training & Inference) Riva
1

Please provide the following information when requesting support.

Hardware - GPU RTX5880
Hardware - CPU
Operating System 22.04
Riva Version 2.16.0
TLT Version (if relevant)
How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here)

I’m working on Riva Virtual Assistant Example and Virtual Assistant (with Rasa) and both appear
There was an error during a service call. We are unable to proceed further. Please check the console for the Error Log. Please resolve this server error and refresh the page to continue
This problem is that the ASR service can be started, but NLU cannot be started. Why?
This is my docker logs riva-speech log

I0912 05:37:45.753426 105 grpc_server.cc:2469] Started GRPCInferenceService at 0.0.0.0:8001
I0912 05:37:45.753723 105 http_server.cc:4554] Started HTTPService at 0.0.0.0:8000
I0912 05:37:45.795589 105 http_server.cc:282] Started Metrics Service at 0.0.0.0:8002
  > Triton server is ready...
I0912 05:37:46.623492   276 riva_server.cc:125] Using Insecure Server Credentials
I0912 05:37:46.631359   276 model_registry.cc:143] Successfully registered: conformer-en-US-asr-offline-asr-bls-ensemble for ASR Triton URI: localhost:8001
I0912 05:37:46.633265   276 model_registry.cc:143] Successfully registered: conformer-en-US-asr-streaming-asr-bls-ensemble for ASR Triton URI: localhost:8001
I0912 05:37:46.656914   276 model_registry.cc:143] Successfully registered: riva-punctuation-en-US for NLP Triton URI: localhost:8001
I0912 05:37:46.677443   276 model_registry.cc:143] Successfully registered: riva-punctuation-en-US for NLP Triton URI: localhost:8001
I0912 05:37:46.695243   276 model_registry.cc:143] Successfully registered: fastpitch_hifigan_ensemble-English-US for TTS Triton URI: localhost:8001
I0912 05:37:46.737378   276 riva_server.cc:171] Riva Conversational AI Server listening on 0.0.0.0:50051
W0912 05:37:48.330585   285 stats_reporter.cc:93] Error sending metrics (401). Invalid API key?
I0912 05:39:11.763635   283 grpc_riva_asr.cc:1370] ASRService.StreamingRecognize called.
I0912 05:39:11.766822   283 grpc_riva_asr.cc:1438] Using model conformer-en-US-asr-streaming-asr-bls-ensemble from Triton localhost:8001 for inference
I0912 05:39:20.578884   309 grpc_riva_nlp.cc:466] NLPService.AnalyzeIntent called.
E0912 05:39:20.579121   309 model_registry.cc:274] model riva_intent_weather this model is not a Riva API model
I0912 05:39:27.562173   496 grpc_riva_asr.cc:1370] ASRService.StreamingRecognize called.
I0912 05:39:27.563695   496 grpc_riva_asr.cc:1438] Using model conformer-en-US-asr-streaming-asr-bls-ensemble from Triton localhost:8001 for inference
I0912 05:39:41.884351   309 grpc_riva_nlp.cc:466] NLPService.AnalyzeIntent called.
E0912 05:39:41.884433   309 model_registry.cc:274] model riva_intent_weather this model is not a Riva API model

config.sh

# Enable or Disable Riva Services
# For any language other than en-US: service_enabled_nlp must be set to false
service_enabled_asr=true
service_enabled_nlp=true
service_enabled_tts=true
service_enabled_nmt=true
.......

#Enable Riva Enterprise
# If enrolled in Enterprise, enable Riva Enterprise by setting configuration
# here. You must explicitly acknowledge you have read and agree to the EULA.
RIVA_API_KEY='c3R0O.........'
RIVA_API_NGC_ORG='yfd......
RIVA_EULA=accept

Is it required to fill in at Riva Enterprise?
config.py

  GNU nano 6.2                                                      config.py                                                               
client_config = {
    "CLIENT_APPLICATION": "WEBAPPLICATION", # Default and only config value for this version
    "PORT": 8009, # The port your flask app will be hosted at
    "DEBUG": True, # When this flag is set, the UI displays detailed Riva data
    "VERBOSE": True  # print logs/details for diagnostics
}

riva_config = {
    "RIVA_SPEECH_API_URL": "192.1xxxxx:50051", # Replace the IP & port with your hosted Riva endpoint
    "ENABLE_QA": "QA unavailable in this VA version. Coming soon",
    "WEATHERSTACK_ACCESS_KEY": "81507c16eec27dxxxxx",  # Get your access key at - https://weatherstack.com/
    "VERBOSE": True  # print logs/details for diagnostics
}

asr_config = {
    "VERBOSE": True,
    "SAMPLING_RATE": 16000,
    "LANGUAGE_CODE": "en-US",  # a BCP-47 language tag
    "ENABLE_AUTOMATIC_PUNCTUATION": True,

I feel that Riva’s service is up because ASR can be used.

python3 main.py logs

[stateDM] Initializing the state machine for uid:  1
[1] Starting chatbot ASR task
[Riva ASR] Creating Stream ASR channel: 192.168.1.47:50051
[Riva ASR] Starting Background ASR process
[Riva ASR] StreamingRecognize Start
[1] ASR background task started
[Riva Chatbot] Chatbot created with user conversation index:[1]
[stateDM] Executing state: initialState
[1] Response from RivaDM: {'context': {}, 'text': '', 'uid': 1, 'payload': {}, 'response': [{'type': 'text', 'payload': {'text': 'Hi, welcome to Riva weather service. How may I help you?'}, 'delay': 0}]}
[Riva Chatbot] Client connected
[1] TTS Disabled
[1] audio speak: 1726120921552
[1] Pausing ASR requests.
[1] Attempt at Unpausing ASR requests on REQUEST_COMPLETE.
[1] ASR successfully unpaused for Request Complete
[Riva ASR] Transcript: what's 
[1] Pausing ASR requests.
[stateDM] Executing state: userInput
[Riva NLU] Error during NLU request
[stateDM] No next state, waiting for user input
[1] Response from RivaDM: {'context': {}, 'text': "what's ", 'uid': 1, 'payload': {}}
'response'

I hope you can help me solve it as soon as possible. Thank you very much.