Problem with ‘rasa export’ command

Hi :grinning:~ I met a problem when trying to import existing conversations from rasa open source to rasaX(installed using docker-compose). After getting all the settings done(tracker store and event broker), the result of command ‘rasa export --debug’ looks like this.

Two main problems here:

  1. I have defined all the slots in domain files, and the model runs without error in rasa server. Why there are errors about non existent slots?
  2. Checking the rabbitmq queue list as well as the rasaX postgres db, connection is setup between rasa and rabbitmq, but no data is received in rasaX. The rasaX UI shows 0 conversations. And the export process seems to be in a waiting state forever, with no more loggings.

I am not sure what went wrong here, please help me~

Can you run a rasa data validate to see if it reports errors in your training data?

Also the log from Rasa X.

Hi Greg Stephens! I tried the rasa data validate command, and it seems that nothing is wrong

Also, below is the rasax container logs for your reference~

Thank you so much~ :smiling_face_with_three_hearts:

Aside from the export, is your bot working correctly and are live events being forwarded to Rasa X?

My bot alone is working correctly, but live events cannot be forwarded to RasaX :frowning_face:

Paste into markdown blocks the following:

  • docker-compose ps output
  • rasa-production container log for a section of the log where you had a conversation (this should show any errors sending the events to the Pika/RabbitMQ event broker
  • RabbitMQ event broker log from the same timeframe as the rasa-production events

Greg

Hi Greg! Thank u~

docker-compose ps

docker-compose: error while loading shared libraries: libz.so.1: failed to map segment from shared object: Operation not permitted

docker ps

I’m not using rasa-production container for conversation, but a existing rasa open source project instead. Maybe the problem lies in here? Please help :worried:

Logs of the rasa-production container is here

2021-04-08 08:01:11.723769: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: cannot open shared object file: No such file or directory
2021-04-08 08:01:11.723802: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2021-04-08 08:01:16.549465: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2021-04-08 08:01:16.549503: W tensorflow/stream_executor/cuda/cuda_driver.cc:312] failed call to cuInit: UNKNOWN ERROR (303)
2021-04-08 08:01:16.549531: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (89e2c0825501): /proc/driver/nvidia/version does not exist
2021-04-08 08:01:43.535297: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 3000000000 Hz
2021-04-08 08:01:43.535583: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x42423e0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-04-08 08:01:43.535607: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
/opt/venv/lib/python3.8/site-packages/tzlocal/unix.py:158: UserWarning: Can not find any timezone configuration, defaulting to UTC.
warnings.warn('Can not find any timezone configuration, defaulting to UTC.')
/opt/venv/lib/python3.8/site-packages/rasa/utils/train_utils.py:96: FutureWarning: `loss_type=softmax` is deprecated. Please update your configuration file to use`loss_type=cross_entropy` instead. (will be removed in 3.0.0)
rasa.shared.utils.io.raise_deprecation_warning(
/opt/venv/lib/python3.8/site-packages/rasa/utils/train_utils.py:558: UserWarning: constrain_similarities is set to `False`. It is recommended to set it to `True` when using cross-entropy loss. It will be set to `True` by default, Rasa Open Source 3.0.0 onwards.
rasa.shared.utils.io.raise_warning(
/opt/venv/lib/python3.8/site-packages/rasa/utils/train_utils.py:531: UserWarning: model_confidence is set to `softmax`. It is recommended to try using `model_confidence=linear_norm` to make it easier to tune fallback thresholds.
rasa.shared.utils.io.raise_warning(
/opt/venv/lib/python3.8/site-packages/rasa/shared/core/slots.py:268: FutureWarning: UnfeaturizedSlot is deprecated and will be removed in Rasa Open Source 3.0. Please change the type and configure the 'influence_conversation' flag for slot 'requested_slot' instead.
rasa.shared.utils.io.raise_warning(
Starting Rasa X in production mode... 🚀
2021-04-08 08:43:52.393562: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: cannot open shared object file: No such file or directory
2021-04-08 08:43:52.393621: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2021-04-08 08:43:54.479749: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2021-04-08 08:43:54.479799: W tensorflow/stream_executor/cuda/cuda_driver.cc:312] failed call to cuInit: UNKNOWN ERROR (303)
2021-04-08 08:43:54.479839: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (89e2c0825501): /proc/driver/nvidia/version does not exist
2021-04-08 08:43:55.870845: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 3000000000 Hz
2021-04-08 08:43:55.871197: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x423e6e0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-04-08 08:43:55.871224: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version

Logs of running rasa open source project server is here

There are some logs that rasa.core.brokers.pika about connection established but no more.

nohup: ignoring input
2021-04-13 09:56:52.835693: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: cannot open shared object file: No such file or directory
2021-04-13 09:56:52.835750: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2021-04-13 09:56:54.405321: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2021-04-13 09:56:54.405375: W tensorflow/stream_executor/cuda/cuda_driver.cc:312] failed call to cuInit: UNKNOWN ERROR (303)
2021-04-13 09:56:54.405400: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (sgpvmc0669): /proc/driver/nvidia/version does not exist
2021-04-13 09:56:54 DEBUG    rasa.cli.utils  - Parameter 'endpoints' not set. Using default location 'endpoints.yml' instead.
2021-04-13 09:56:54 DEBUG    rasa.cli.utils  - Parameter 'credentials' not set. Using default location 'credentials.yml' instead.
2021-04-13 09:56:54 DEBUG    rasa.core.utils  - Available web server routes:
/conversations/<conversation_id:path>/messages     POST                           add_message
/conversations/<conversation_id:path>/tracker/events POST                           append_events
/webhooks/rasa                                     GET                            custom_webhook_RasaChatInput.health
/webhooks/rasa/webhook                             POST                           custom_webhook_RasaChatInput.receive
/webhooks/rest                                     GET                            custom_webhook_RestInput.health
/webhooks/rest/webhook                             POST                           custom_webhook_RestInput.receive
/model/test/intents                                POST                           evaluate_intents
/model/test/stories                                POST                           evaluate_stories
/conversations/<conversation_id:path>/execute      POST                           execute_action
/domain                                            GET                            get_domain
/                                                  GET                            hello
/model                                             PUT                            load_model
/model/parse                                       POST                           parse
/conversations/<conversation_id:path>/predict      POST                           predict
/conversations/<conversation_id:path>/tracker/events PUT                            replace_events
/conversations/<conversation_id:path>/story        GET                            retrieve_story
/conversations/<conversation_id:path>/tracker      GET                            retrieve_tracker
/status                                            GET                            status
/model/predict                                     POST                           tracker_predict
/model/train                                       POST                           train
/conversations/<conversation_id:path>/trigger_intent POST                           trigger_intent
/model                                             DELETE                         unload_model
/version                                           GET                            version
2021-04-13 09:56:54 INFO     root  - Starting Rasa server on http://localhost:5005
2021-04-13 09:56:54 DEBUG    rasa.core.utils  - Using the default number of Sanic workers (1).
2021-04-13 09:56:54 INFO     rasa.model  - Loading model models/20210402-111328.tar.gz...
2021-04-13 09:56:54 DEBUG    rasa.model  - Extracted model to '/tmp/tmpma7syn20'.
2021-04-13 09:56:54 DEBUG    urllib3.connectionpool  - Starting new HTTPS connection (1): api.segment.io:443
2021-04-13 09:56:54 DEBUG    rasa.telemetry  - Skipping telemetry reporting: HTTPSConnectionPool(host='api.segment.io', port=443): Max retries exceeded with url: /v1/track (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f7938b68090>: Failed to establish a new connection: [Errno -2] Name or service not known'))
2021-04-13 09:56:54 INFO     root  - Enabling coroutine debugging. Loop id 78540192.
2021-04-13 09:56:54 INFO     rasa.model  - Loading model models/20210402-111328.tar.gz...
2021-04-13 09:56:55 DEBUG    rasa.model  - Extracted model to '/tmp/tmp5yo06c_h'.
2021-04-13 09:56:55 DEBUG    rasa.utils.tensorflow.models  - Loading the model from /tmp/tmp5yo06c_h/nlu/component_5_DIETClassifier.tf_model with finetune_mode=False...
2021-04-13 09:56:55.107811: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 3000000000 Hz
2021-04-13 09:56:55.108129: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x4e1c6a0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-04-13 09:56:55.108158: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2021-04-13 09:56:55 DEBUG    rasa.nlu.classifiers.diet_classifier  - Following metrics will be logged during training:
2021-04-13 09:56:55 DEBUG    rasa.nlu.classifiers.diet_classifier  -   t_loss (total loss)
2021-04-13 09:56:55 DEBUG    rasa.nlu.classifiers.diet_classifier  -   i_acc (intent acc)
 2021-04-13 09:56:55 DEBUG    rasa.nlu.classifiers.diet_classifier  -   i_loss (intent loss)
2021-04-13 09:56:55 DEBUG    rasa.utils.tensorflow.models  - Finished loading the model.
2021-04-13 09:56:55 DEBUG    rasa.utils.tensorflow.models  - Building tensorflow prediction graph...
2021-04-13 09:56:58 DEBUG    rasa.utils.tensorflow.models  - Finished building tensorflow prediction graph.
/usr/local/lib/python3.7/site-packages/rasa/utils/train_utils.py:437: UserWarning: constrain_similarities is set to `False`. It is recommended to set it to `True` when using cross-entropy loss. It will be set to `True` by default, Rasa Open Source 3.0.0 onwards.category=UserWarning,
/usr/local/lib/python3.7/site-packages/rasa/utils/train_utils.py:410: UserWarning: model_confidence is set to `softmax`. It is recommended to set it to `cosine`. It will be set to `cosine` by default, Rasa Open Source 3.0.0 onwards.category=UserWarning,
2021-04-13 09:56:58 DEBUG    rasa.nlu.classifiers.diet_classifier  - Failed to load model for 'ResponseSelector'. Maybe you did not provide enough training data and no model was trained or the path '/tmp/tmp5yo06c_h/nlu' doesn't exist?
2021-04-13 09:56:58 INFO     rasa.core.brokers.pika  - Connecting to RabbitMQ ...
2021-04-13 09:56:59 INFO     rasa.core.brokers.pika  - RabbitMQ connection to '127.0.0.1' was established.
2021-04-13 09:56:59 DEBUG    rasa.core.brokers.pika  - RabbitMQ channel was opened. Declaring fanout exchange 'rasa-exchange'.
2021-04-13 09:56:59 DEBUG    rasa.core.brokers.broker  - Instantiated event broker to 'PikaEventBroker'.
2021-04-13 09:56:59 DEBUG    rasa.core.tracker_store  - Attempting to connect to database via 'postgresql://rbadmin_app2:***@localhost/rasa_test'.
2021-04-13 09:56:59 DEBUG    rasa.core.tracker_store  - Connection to SQL database 'rasa_test' successful.
2021-04-13 09:56:59 DEBUG    rasa.core.tracker_store  - Connected to SQLTrackerStore.
2021-04-13 09:56:59 DEBUG    rasa.core.lock_store  - Connected to lock store 'InMemoryLockStore'.
2021-04-13 09:56:59 DEBUG    rasa.model  - Extracted model to '/tmp/tmp06fv2nq0'.
2021-04-13 09:56:59 DEBUG    rasa.utils.tensorflow.models  - Loading the model from /tmp/tmp06fv2nq0/core/policy_1_TEDPolicy/ted_policy.tf_model with finetune_mode=False...
2021-04-13 09:56:59 DEBUG    rasa.utils.tensorflow.models  - Finished loading the model.
2021-04-13 09:56:59 DEBUG    rasa.utils.tensorflow.models  - Building tensorflow prediction graph...
2021-04-13 09:57:03 DEBUG    rasa.utils.tensorflow.models  - Finished building tensorflow prediction graph.
2021-04-13 09:57:03 DEBUG    rasa.core.nlg.generator  - Instantiated NLG to 'TemplatedNaturalLanguageGenerator'.
2021-04-13 09:57:03 INFO     root  - Rasa server is up and running.
2021-04-13 09:57:20 DEBUG    rasa.core.lock_store  - Issuing ticket for conversation 'jitesh97'.
2021-04-13 09:57:20 DEBUG    rasa.core.lock_store  - Acquiring lock for conversation 'jitesh97'.
2021-04-13 09:57:20 DEBUG    rasa.core.lock_store  - Acquired lock for conversation 'jitesh97'.
2021-04-13 09:57:20 DEBUG    rasa.core.tracker_store  - Recreating tracker from sender id 'jitesh97'
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - The latest session for conversation ID 'jitesh97' has expired.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Starting a new session for conversation ID 'jitesh97'.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Policy prediction ended with events '[]'.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Action 'action_session_start' ended with events '[<rasa.shared.core.events.SessionStarted object at 0x7f78f6fd0e50>, ActionExecuted(action: action_listen, policy: None, confidence: None)]'.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Current slot values:
    rate: None
    idea: None
    email: None
    more: None
    requested_slot: None
    session_started_metadata: None
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Received user message '/restart' with intent '{'name': 'restart', 'confidence': 1.0}' and entities '[]'
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Logged UserUtterance - tracker now has 13 events.
2021-04-13 09:57:20 DEBUG    rasa.core.policies.memoization  - Current tracker state:[state 1] user intent: restart | previous action name: action_listen
2021-04-13 09:57:20 DEBUG    rasa.core.policies.memoization  - There is no memorised next action
2021-04-13 09:57:20 DEBUG    rasa.core.policies.rule_policy  - Current tracker state:[state 1] user text: /restart | previous action name: action_listen
2021-04-13 09:57:20 DEBUG    rasa.core.policies.rule_policy  - There is no applicable rule.
2021-04-13 09:57:20 DEBUG    rasa.core.policies.rule_policy  - Predicted default action 'action_restart'.
2021-04-13 09:57:20 DEBUG    rasa.core.policies.ensemble  - Made prediction using user intent.
2021-04-13 09:57:20 DEBUG    rasa.core.policies.ensemble  - Added `DefinePrevUserUtteredFeaturization(False)` event.
2021-04-13 09:57:20 DEBUG    rasa.core.policies.ensemble  - Predicted next action using policy_2_RulePolicy.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Predicted next action 'action_restart' with confidence 1.00.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Policy prediction ended with events '[<rasa.shared.core.events.DefinePrevUserUtteredFeaturization object at 0x7f78f6f7dd50>]'.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Action 'action_restart' ended with events '[BotUttered('If you want to re-answer questions, click the upper-right button and choose [Restart].', {"elements": null, "quick_replies": null, "buttons": null, "attachment": null, "image": null, "custom": null}, {"template_name": "utter_restart"}, 1618279040.1426716), <rasa.shared.core.events.Restarted object at 0x7f78f6ced190>]'.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Current slot values:
    rate: None
    idea: None
    email: None
    more: None
    requested_slot: None
    session_started_metadata: None
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Predicted next action 'action_session_start' with confidence 1.00.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Policy prediction ended with events '[]'.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Action 'action_session_start' ended with events '[<rasa.shared.core.events.SessionStarted object at 0x7f78f6bd3a10>, ActionExecuted(action: action_listen, policy: None, confidence: None)]'.
2021-04-13 09:57:20 DEBUG    rasa.core.processor  - Current slot values:
    rate: None
    idea: None
    email: None
    more: None
    requested_slot: None
    session_started_metadata: None
2021-04-13 09:57:20 DEBUG    rasa.core.tracker_store  - Recreating tracker from sender id 'jitesh97'
2021-04-13 09:57:20 DEBUG    rasa.core.tracker_store  - Tracker with sender_id 'jitesh97' stored to database
2021-04-13 09:57:20 DEBUG    rasa.core.lock_store  - Deleted lock for conversation 'jitesh97'.
2021-04-13 09:57:26 DEBUG    rasa.core.lock_store  - Issuing ticket for conversation 'jitesh97'.
2021-04-13 09:57:26 DEBUG    rasa.core.lock_store  - Acquiring lock for conversation 'jitesh97'.
2021-04-13 09:57:26 DEBUG    rasa.core.lock_store  - Acquired lock for conversation 'jitesh97'.
2021-04-13 09:57:26 DEBUG    rasa.core.tracker_store  - Recreating tracker from sender id 'jitesh97'
2021-04-13 09:57:27 DEBUG    rasa.nlu.classifiers.diet_classifier  - There is no trained model for 'ResponseSelector': The component is either not trained or didn't receive enough training data.
2021-04-13 09:57:27 DEBUG    rasa.nlu.selectors.response_selector  - Adding following selector key to message property: default
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Received user message 'hello there' with intent '{'id': 8355873976953206928, 'name': 'greet', 'confidence': 0.9999998807907104}' and entities '[]'
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Logged UserUtterance - tracker now has 3 events.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.memoization  - Current tracker state:[state 1] user intent: greet | previous action name: action_listen
2021-04-13 09:57:27 DEBUG    rasa.core.policies.memoization  - There is a memorised next action 'utter_greet'
2021-04-13 09:57:27 DEBUG    rasa.core.policies.rule_policy  - Current tracker state:[state 1] user text: hello there | previous action name: action_listen
2021-04-13 09:57:27 DEBUG    rasa.core.policies.rule_policy  - There is no applicable rule.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.rule_policy  - Current tracker state:[state 1] user intent: greet | previous action name: action_listen
2021-04-13 09:57:27 DEBUG    rasa.core.policies.rule_policy  - There is a rule for the next action 'utter_greet'.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.ensemble  - Made prediction using user intent.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.ensemble  - Added `DefinePrevUserUtteredFeaturization(False)` event.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.ensemble  - Predicted next action using policy_2_RulePolicy.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Predicted next action 'utter_greet' with confidence 1.00.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Policy prediction ended with events '[<rasa.shared.core.events.DefinePrevUserUtteredFeaturization object at 0x7f78f6eed810>]'.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Action 'utter_greet' ended with events '[BotUttered('Hey there~ Nice to meet you. My name is Robson.', {"elements": null, "quick_replies": null, "buttons": null, "attachment": null, "image": null, "custom": null}, {"template_name": "utter_greet"}, 1618279047.1550605)]'.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.memoization  - Current tracker state:
[state 1] user intent: greet | previous action name: action_listen
[state 2] user intent: greet | previous action name: utter_greet
2021-04-13 09:57:27 DEBUG    rasa.core.policies.memoization  - There is a memorised next action 'utter_rate'
2021-04-13 09:57:27 DEBUG    rasa.core.policies.rule_policy  - Current tracker state:
[state 1] user intent: greet | previous action name: action_listen
[state 2] user intent: greet | previous action name: utter_greet
2021-04-13 09:57:27 DEBUG    rasa.core.policies.rule_policy  - There is a rule for the next action 'utter_rate'.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.ensemble  - Predicted next action using policy_2_RulePolicy.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Predicted next action 'utter_rate' with confidence 1.00.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Policy prediction ended with events '[]'.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Action 'utter_rate' ended with events '[BotUttered('How do you like our chatbot showcase? ', {"elements": null, "quick_replies": null, "buttons": [{"title": "Great", "payload": "/rate_good"}, {"title": "Not Bad", "payload": "/rate_soso"}, {"title": "Inadequate", "payload": "/rate_bad"}], "attachment": null, "image": null, "custom": null}, {"template_name": "utter_rate"}, 1618279047.1621578)]'.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.memoization  - Current tracker state:
[state 1] user intent: greet | previous action name: action_listen
[state 2] user intent: greet | previous action name: utter_greet
[state 3] user intent: greet | previous action name: utter_rate
2021-04-13 09:57:27 DEBUG    rasa.core.policies.memoization  - There is a memorised next action 'action_listen'
2021-04-13 09:57:27 DEBUG    rasa.core.policies.rule_policy  - Current tracker state:
[state 1] user intent: greet | previous action name: action_listen
[state 2] user intent: greet | previous action name: utter_greet
[state 3] user intent: greet | previous action name: utter_rate
2021-04-13 09:57:27 DEBUG    rasa.core.policies.rule_policy  - There is a rule for the next action 'action_listen'.
2021-04-13 09:57:27 DEBUG    rasa.core.policies.ensemble  - Predicted next action using policy_2_RulePolicy.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Predicted next action 'action_listen' with confidence 1.00.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Policy prediction ended with events '[]'.
2021-04-13 09:57:27 DEBUG    rasa.core.processor  - Action 'action_listen' ended with events '[]'.
2021-04-13 09:57:27 DEBUG    rasa.core.tracker_store  - Recreating tracker from sender id 'jitesh97'
2021-04-13 09:57:27 DEBUG    rasa.core.tracker_store  - Tracker with sender_id 'jitesh97' stored to database
2021-04-13 09:57:27 DEBUG    rasa.core.lock_store  - Deleted lock for conversation 'jitesh97'.

Logs of rabbitmq is here

2021-04-13 01:56:59.014 [info] <0.1117.3> accepting AMQP connection <0.1117.3> (172.18.0.1:44570 -> 172.18.0.4:5672)
2021-04-13 01:56:59.017 [info] <0.1117.3> connection <0.1117.3> (172.18.0.1:44570 -> 172.18.0.4:5672): user 'user' authenticated and granted access to vhost '/'
2021-04-13 01:57:43.823 [warning] <0.747.0> closing AMQP connection <0.747.0> (172.18.0.1:42268 -> 172.18.0.4:5672, vhost: '/', user: 'user'):
client unexpectedly closed TCP connection

You may need sudo docker-compose ps to see this list.

Although you are using an external rasa oss for production, can you talk to the bot in the Rasa X UI i.e. in the Talk to your Bot screen? if rasa-production on the same deployment cannot connect to rabbit properly either, then that is likely where the problem lies.

This:

client unexpectedly closed TCP connection

Indicates the connection to rabbit is broken at some point. If this is at startup, this might not be a problem, since the container can take a bit to start.

Check the resources on your rabbit pod - are they as recommended in the installation instructions? Did you set a value for RABBITMQ_DISK_FREE_LIMIT?

For what it’s worth, this thread has some explanation of the components involved in a successful rasa export or successful connection of rasa-production to database:

In case it’s helpful

1 Like

I’ll check this out, try what you suggested, and update the latest progress here.

So nice of you, Thank you so much!! :smiling_face_with_three_hearts: :smiling_face_with_three_hearts:

I see the red Disk Space, is this where the problem lies? :grinning: :grinning:

Yep I think so! Your “low watermark” seems to be set to 7.6 GB, so 3.4 is too low and if you click on the red box, it should give you some warning about it. See here Free Disk Space Alarms — RabbitMQ - it says,

Your action is either to free up enough memory or disk resource to allow the RabbitMQ broker to run, or configure the high and low water marks for either disk or memory or both.

1 Like

Yeah!! With your help I finally managed to get the export done, the live connection goes all well, and chat by rasax UI works. :tada: :tada: :tada:

But errors still exists when doing rasa export, as shown below.

  1. The non existent slot problem. Although it‘s not related to the export problem, I’m not sure if it matters? Can we just ignore them?
  2. Failed to publish two events due to error ‘’. There is no specific error description here. Quite confused. :thinking:
  1. The non-existent slot thing is probably a “false positive” - Rasa isn’t using the real domain when exporting, but the data loading functions still give these warnings. You can safely ignore it.
  2. Do these two events end up in the tracker store? If yes , it can be that it did not receive back confirmation of publishing, although it actually made it through.
1 Like

hi melinda~ We are just about to launch our first project using rasa, but a disk space problem arises. [This is my post about the problem] (Docker disk space problem)

In our testing environment, we only have 12G for /var (where docker lies), I know rasaX requires at least 50G. We will prepare a much larger server for production. Now more than 90% of 12G is used up, which is quite abnormal because testing data is really small.

Will this problem be automatically solved if more disk space is provided? We’re worried if it’s gonna rapidly eat up all the disk space in a short time. Could you please give us some advice~ Really really appreciated! :bowing_woman: :bowing_woman: