join in ok, connected, llm ,tts config ok, but no Conversation

[themass]

I run 01-local demo for server and rtvi-web-demo for client

2024-08-26 17:13:11.097 | INFO | pipecat.transports.services.daily:on_participant_joined:468 - Participant joined a3b53542-cc5e-4a6a-b800-e84091fdbb1e
2024-08-26 17:13:11.098 | INFO | main:on_first_participant_joined:61 - First participant joined
2024-08-26 17:13:11.192 | INFO | main:on_call_state_updated:70 - Call state joined
2024-08-26 17:13:12.951 | INFO | pipecat.transports.services.daily:join:272 - Joined xxxxxxx
2024-08-26 17:13:12.952 | INFO | pipecat.transports.services.daily:_start_transcription:288 - Enabling transcription with settings language='en' tier='nova' model='2-conversationalai' profanity_filter=True redact=False endpointing=True punctuate=True includeRawResponse=True extra={'interim_results': True}
2024-08-26 17:13:13.725 | DEBUG | pipecat.transports.services.daily:on_transcription_started:495 - Transcription started: {'startedBy': '48880c13-be10-4edb-90ed-e28fc87c1bdd', 'language': 'en', 'tier': 'nova', 'transcriptId': '84c5546f-d9a4-421f-8fa5-4178bfbe71c7', 'model': '2-conversationalai'}
2024-08-26 17:13:13.742 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking PipelineSource#1 -> LLMUserResponseAggregator#0
2024-08-26 17:13:13.742 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking LLMUserResponseAggregator#0 -> LLM
2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking LLM -> FunctionCaller#0
2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking FunctionCaller#0 -> TTS
2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking TTS -> RTVITTSTextProcessor#0
2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking RTVITTSTextProcessor#0 -> LLMAssistantResponseAggregator#0
2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking LLMAssistantResponseAggregator#0 -> DailyOutputTransport#0
2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking DailyOutputTransport#0 -> PipelineSink#1
2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking Pipeline#0 -> Pipeline#1
2024-08-26 17:13:14.879 | DEBUG | pipecat.services.openai:_stream_chat_completions:103 - Generating chat: [{"content": "You are Chatbot, a friendly, helpful robot. Your output will be converted to audio so don't include special characters other than '!' or '?' in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by saying hello.", "role": "system", "name": "system"}, {"content": "Greet the user", "role": "assistant", "name": "assistant"}]
2024-08-26 17:13:16.276 | DEBUG | pipecat.processors.frame_processor:stop_ttfb_metrics:40 - LLM TTFB: 1.3974647521972656
2024-08-26 17:13:16.317 | DEBUG | pipecat.services.cartesia:run_tts:192 - Generating TTS: [Hello!]
2024-08-26 17:13:16.318 | DEBUG | pipecat.processors.frame_processor:stop_processing_metrics:56 - TTS processing time: 0.0007891654968261719
2024-08-26 17:13:16.374 | DEBUG | pipecat.services.cartesia:run_tts:192 - Generating TTS: [How can I assist you today?]
2024-08-26 17:13:16.374 | DEBUG | pipecat.processors.frame_processor:stop_processing_metrics:56 - TTS processing time: 0.00040912628173828125
2024-08-26 17:13:16.375 | DEBUG | pipecat.processors.frame_processor:stop_processing_metrics:56 - LLM processing time: 1.496906042098999
2024-08-26 17:13:16.688 | DEBUG | pipecat.processors.frame_processor:stop_ttfb_metrics:40 - TTS TTFB: 0.3707418441772461
{"timestamp":"2024-08-26T09:14:27.881769Z","level":"ERROR","fields":{"message":"send transport changed to failed"},"target":"daily_core::soup::sfu::mediasoup_manager"}
{"timestamp":"2024-08-26T09:14:28.151822Z","level":"ERROR","fields":{"message":"recv transport changed to failed"},"target":"daily_core::soup::sfu::mediasoup_manager"}

[themass]

[sadimoodi]

I run 01-local demo for server and rtvi-web-demo for client

2024-08-26 17:13:11.097 | INFO | pipecat.transports.services.daily:on_participant_joined:468 - Participant joined a3b53542-cc5e-4a6a-b800-e84091fdbb1e 2024-08-26 17:13:11.098 | INFO | main:on_first_participant_joined:61 - First participant joined 2024-08-26 17:13:11.192 | INFO | main:on_call_state_updated:70 - Call state joined 2024-08-26 17:13:12.951 | INFO | pipecat.transports.services.daily:join:272 - Joined xxxxxxx 2024-08-26 17:13:12.952 | INFO | pipecat.transports.services.daily:_start_transcription:288 - Enabling transcription with settings language='en' tier='nova' model='2-conversationalai' profanity_filter=True redact=False endpointing=True punctuate=True includeRawResponse=True extra={'interim_results': True} 2024-08-26 17:13:13.725 | DEBUG | pipecat.transports.services.daily:on_transcription_started:495 - Transcription started: {'startedBy': '48880c13-be10-4edb-90ed-e28fc87c1bdd', 'language': 'en', 'tier': 'nova', 'transcriptId': '84c5546f-d9a4-421f-8fa5-4178bfbe71c7', 'model': '2-conversationalai'} 2024-08-26 17:13:13.742 | DEBUG | pipecat.processors.frame_processor🔗133 - Linking PipelineSource#1 -> LLMUserResponseAggregator#0 2024-08-26 17:13:13.742 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking LLMUserResponseAggregator#0 -> LLM 2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking LLM -> FunctionCaller#0 2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking FunctionCaller#0 -> TTS 2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking TTS -> RTVITTSTextProcessor#0 2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking RTVITTSTextProcessor#0 -> LLMAssistantResponseAggregator#0 2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking LLMAssistantResponseAggregator#0 -> DailyOutputTransport#0 2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking DailyOutputTransport#0 -> PipelineSink#1 2024-08-26 17:13:13.743 | DEBUG | pipecat.processors.frame_processor:link:133 - Linking Pipeline#0 -> Pipeline#1 2024-08-26 17:13:14.879 | DEBUG | pipecat.services.openai:_stream_chat_completions:103 - Generating chat: [{"content": "You are Chatbot, a friendly, helpful robot. Your output will be converted to audio so don't include special characters other than '!' or '?' in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by saying hello.", "role": "system", "name": "system"}, {"content": "Greet the user", "role": "assistant", "name": "assistant"}] 2024-08-26 17:13:16.276 | DEBUG | pipecat.processors.frame_processor:stop_ttfb_metrics:40 - LLM TTFB: 1.3974647521972656 2024-08-26 17:13:16.317 | DEBUG | pipecat.services.cartesia:run_tts:192 - Generating TTS: [Hello!] 2024-08-26 17:13:16.318 | DEBUG | pipecat.processors.frame_processor:stop_processing_metrics:56 - TTS processing time: 0.0007891654968261719 2024-08-26 17:13:16.374 | DEBUG | pipecat.services.cartesia:run_tts:192 - Generating TTS: [How can I assist you today?] 2024-08-26 17:13:16.374 | DEBUG | pipecat.processors.frame_processor:stop_processing_metrics:56 - TTS processing time: 0.00040912628173828125 2024-08-26 17:13:16.375 | DEBUG | pipecat.processors.frame_processor:stop_processing_metrics:56 - LLM processing time: 1.496906042098999 2024-08-26 17:13:16.688 | DEBUG | pipecat.processors.frame_processor:stop_ttfb_metrics:40 - TTS TTFB: 0.3707418441772461 {"timestamp":"2024-08-26T09:14:27.881769Z","level":"ERROR","fields":{"message":"send transport changed to failed"},"target":"daily_core::soup::sfu::mediasoup_manager"} {"timestamp":"2024-08-26T09:14:28.151822Z","level":"ERROR","fields":{"message":"recv transport changed to failed"},"target":"daily_core::soup::sfu::mediasoup_manager"}

where is the 01-local code that you used to run the backend?
i am trying to run the example here , which is similar but not getting any transcription.

[ttamoud]

Check the bot-ready message forwarded by the Rtvi framework, thats probably whats causing the issue, frontend probably not receiveing the the signal correctly.

[sadimoodi]

Check the bot-ready message forwarded by the Rtvi framework, thats probably whats causing the issue, frontend probably not receiveing the the signal correctly.

can u point at the backend code required to run this frontend? i was looking here but the code doesnt seem to be correct.

[sadimoodi]

can u help by answering how did u get the bot status to be connected? it keeps showing us initializing, see below:

[themass]

just config these env and run the demo server
https://github.com/rtvi-ai/rtvi-infra-examples/tree/main/01-local

[ttamoud]

These are outdated, the rtvi standard has been updated few times since, not working anymore.
The rtvi standard backend ( rtvi-infra-examples ) used to send a bot-ready message that the frontend received and changed bot status from initializing to connected. The rtvi standard has been updated a few times since, but not the frontend and the infra-examples backend which causes it to brake.