as learning data of nlu.md file,
Give me a [small]{“entity”: “size”, “group”: “1”} pizza with [mushrooms]{“entity”: “topping”, “group”: “1”} and a [large]{“entity”: “size”, “group”: “2”} [pepperoni]{“entity”: “topping”, “group”: “2”}
How can I extract entity role, entity group from tracker slot in knowledge_base?
Anyone knows a solution for this? Facing same problem.
Hi @edubrigham
Eg: Give me a [small]{“entity”: “size”, “group”: “1”} pizza with [mushrooms]{“entity”: “topping”, “group”: “1”} and a [large]{“entity”: “size”, “group”: “2”} [pepperoni]{“entity”: “topping”, “group”: “2”}
use
next(tracker.get_latest_entity_values(entity_type=“size”, entity_group=“1”))
For entity_role
Just the change the entity_group to entity_role
Eg:
I am from [USA]{“entity”:“Country”, “role”:“currentlocation”} and want to go to [UK]{“entity”:“Country”, “role”:“destination”}
next(tracker.get_latest_entity_values(entity_type=“Country”, entity_role=“destination”))
Hi Thank you for the help 
I’m sorry, but i’m still new to Rasa and i dont know where to adapt the actions to reflect what you wrote.
in my nlu.md file i’m declaring training data in the following fashion:
To make the link between entities “itemQty” to “itemType”, i declared the same “group” and “role” to differentiate between multiple orders (order1 , order2 , order3 , etc.) I would like to extract the role value of each entity pair (itemQty+itemName from role=orderItem1), and programmatically print out the value pairs.: ex.:
I want 1 coke and 2 Fanta
should print out: `
order1: [1]{“entity”: “itemQty”, “group”: “1”, “role”: “orderItem1”} [coke]{“entity”: “itemName”, “group”: “1”, “role”: “orderItem1”} order2: [2]{“entity”: “itemQty”, “group”: “2”, “role”: “orderItem2”} [Fanta]{“entity”: “itemName”, “group”: “2”, “role”: “orderItem2”}
My actions.py is based on the original formsbot actions.py file, but i adjusted the names of the entities to reflect the entities i am trying to extract.
from typing import Dict, Text, Any, List, Union, Optional
from rasa_sdk import Tracker
from rasa_sdk.executor import CollectingDispatcher
from rasa_sdk.forms import FormAction
class RestaurantForm(FormAction):
"""Example of a custom form action"""
def name(self) -> Text:
"""Unique identifier of the form"""
return "restaurant_form"
@staticmethod
def required_slots(tracker: Tracker) -> List[Text]:
"""A list of required slots that the form has to fill"""
return ["itemName", "itemQty", "tableNum", "preferences"]
def slot_mappings(self) -> Dict[Text, Union[Dict, List[Dict]]]:
"""A dictionary to map required slots to
- an extracted entity
- intent: value pairs
- a whole message
or a list of them, where a first match will be picked"""
return {
"itemName": self.from_entity(entity="itemName", not_intent="chitchat"),
"itemQty": [
self.from_entity(
entity="itemQty", intent=["itemName_order","say_itemQty_or_tableNum", "ask_unspecified_order"]
),
],
"tableNum": [
self.from_entity(
entity="tableNum", intent=["itemName_order", "say_itemQty_or_tableNum", "ask_unspecified_order", "ask_price"]
),
],
"preferences": [
self.from_intent(intent="deny", value="no additional preferences"),
self.from_text(not_intent="affirm"),
],
"feedback": [self.from_entity(entity="feedback"), self.from_text()],
}
# USED FOR DOCS: do not rename without updating in docs
@staticmethod
def itemName_db() -> List[Text]:
"""Database of supported itemNames"""
return [
"coke",
"cokes",
"cola",
"colas",
"beers",
"beer",
"beers",
"water",
"waters",
"mojito",
]
@staticmethod
def is_int(string: Text) -> bool:
"""Check if a string is an integer"""
try:
int(string)
return True
except ValueError:
return False
# USED FOR DOCS: do not rename without updating in docs
def validate_itemName(
self,
value: Text,
dispatcher: CollectingDispatcher,
tracker: Tracker,
domain: Dict[Text, Any],
) -> Dict[Text, Any]:
"""Validate itemName value."""
if value.lower() in self.itemName_db():
# validation succeeded, set the value of the "itemName" slot to value
return {"itemName": value}
else:
dispatcher.utter_message(template="utter_wrong_itemName")
# validation failed, set this slot to None, meaning the
# user will be asked for the slot again
return {"itemName": None}
def validate_itemQty(
self,
value: Text,
dispatcher: CollectingDispatcher,
tracker: Tracker,
domain: Dict[Text, Any],
) -> Dict[Text, Any]:
"""Validate itemQty value."""
if self.is_int(value) and int(value) > 0:
return {"itemQty": value}
else:
dispatcher.utter_message(template="utter_wrong_itemQty")
# validation failed, set slot to None
return {"itemQty": None}
def validate_tableNum(
self,
value: Text,
dispatcher: CollectingDispatcher,
tracker: Tracker,
domain: Dict[Text, Any],
) -> Dict[Text, Any]:
"""Validate itemQty value."""
if self.is_int(value) and int(value) > 0:
return {"tableNum": value}
else:
dispatcher.utter_message(template="utter_wrong_tableNum")
# validation failed, set slot to None
return {"tableNum": None}
def submit(
self,
dispatcher: CollectingDispatcher,
tracker: Tracker,
domain: Dict[Text, Any],
) -> List[Dict]:
"""Define what the form has to do
after all required slots are filled"""
# utter submit template
dispatcher.utter_message(template="utter_slots_values")
return []
Hi @edubrigham,
Define this in your submit method
a = next(tracker.get_latest_entity_values(entity_type="itemQty",
entity_group = "1", entity_role="orderItem1"))
b = next(tracker.get_latest_entity_values(entity_type="itemName",
entity_group = "1", entity_role="orderItem1"))
dispatcher.utter_message(text=a+b)
a = next(tracker.get_latest_entity_values(entity_type="itemQty",
entity_group = "2", entity_role="orderItem2"))
b = next(tracker.get_latest_entity_values(entity_type="itemName",
entity_group = "2", entity_role="orderItem2"))
dispatcher.utter_message(text=a+b)
I’m pretty sure I’m doing something wrong! I have followed your instructions and adapted the actions.py (4.7 KB) accordingly:
def submit(
self, dispatcher: CollectingDispatcher,
tracker: Tracker,
domain: Dict[Text, Any]) -> List[Dict]:
"""Define what the form has to do
after all required slots are filled"""
a = next(tracker.get_latest_entity_values(entity_type="itemQty", entity_group = "1", entity_role="orderItem1"))
b = next(tracker.get_latest_entity_values(entity_type="itemName", entity_group = "1", entity_role="orderItem1"))
print("Order1", a + b)
dispatcher.utter_message(text=a+b)
a = next(tracker.get_latest_entity_values(entity_type="itemQty", entity_group = "2", entity_role="orderItem2"))
b = next(tracker.get_latest_entity_values(entity_type="itemName", entity_group = "2", entity_role="orderItem2"))
print("Order2", a + b)
dispatcher.utter_message(text=a+b)
But this is the response from my actions server:
master ● rasa run actions -v -vv
2020-05-31 11:58:14 INFO rasa_sdk.endpoint - Starting action endpoint server...
2020-05-31 11:58:14 INFO rasa_sdk.executor - Registered function for 'restaurant_form'.
2020-05-31 11:58:14 DEBUG rasa_sdk.utils - Using the default number of Sanic workers (1).
2020-05-31 12:00:01 DEBUG rasa_sdk.executor - Received request to run 'restaurant_form'
2020-05-31 12:00:01 DEBUG rasa_sdk.forms - There is no active form
2020-05-31 12:00:01 DEBUG rasa_sdk.forms - Activated the form 'restaurant_form'
2020-05-31 12:00:01 DEBUG rasa_sdk.forms - No pre-filled required slots to validate.
2020-05-31 12:00:01 DEBUG rasa_sdk.forms - Validating user input '{'intent': {'name': 'itemName_order', 'confidence': 1.0}, 'entities': [{'entity': 'itemQty', 'start': 7, 'end': 8, 'role': 'orderItem1', 'group': '1', 'value': '1', 'extractor': 'DIETClassifier'}, {'entity': 'itemName', 'start': 9, 'end': 13, 'role': 'orderItem1', 'group': '1', 'value': 'beer', 'extractor': 'DIETClassifier'}, {'entity': 'itemQty', 'start': 18, 'end': 19, 'role': 'orderItem2', 'group': '2', 'value': '1', 'extractor': 'DIETClassifier'}, {'entity': 'itemName', 'start': 20, 'end': 24, 'role': 'orderItem2', 'group': '2', 'value': 'coke', 'extractor': 'DIETClassifier'}], 'intent_ranking': [{'name': 'itemName_order', 'confidence': 1.0}, {'name': 'deny', 'confidence': 1.3075308835652777e-08}, {'name': 'say_itemQty_or_tableNum', 'confidence': 8.540051332772691e-09}, {'name': 'feedback', 'confidence': 1.0265213123972217e-09}, {'name': 'restart', 'confidence': 4.484710380836532e-10}, {'name': 'ask_unspecified_order', 'confidence': 3.380443147626977e-10}, {'name': 'stop', 'confidence': 2.6472235514773956e-10}, {'name': 'greet', 'confidence': 2.62369348469349e-10}, {'name': 'ask_price', 'confidence': 2.5228685807121565e-10}, {'name': 'preferences', 'confidence': 8.4804066546873e-11}], 'response_selector': {'default': {'response': {'name': None, 'confidence': 0.0}, 'ranking': [], 'full_retrieval_intent': None}}, 'text': 'I want 1 beer and 1 coke'}'
2020-05-31 12:00:01 DEBUG rasa_sdk.forms - Extracted '['beer', 'coke']' for extra slot 'itemName'.
2020-05-31 12:00:01 DEBUG rasa_sdk.forms - Extracted '['1', '1']' for extra slot 'itemQty'.
2020-05-31 12:00:01 DEBUG rasa_sdk.forms - Validating extracted slots: {'itemName': ['beer', 'coke'], 'itemQty': ['1', '1']}
Exception occurred while handling uri: 'http://localhost:5055/webhook'
Traceback (most recent call last):
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/sanic/app.py", line 976, in handle_request
response = await response
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa_sdk/endpoint.py", line 102, in webhook
result = await executor.run(action_call)
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa_sdk/executor.py", line 385, in run
events = await action(dispatcher, tracker, domain)
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa_sdk/forms.py", line 584, in run
events.extend(await self._validate_if_required(dispatcher, tracker, domain))
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa_sdk/forms.py", line 551, in _validate_if_required
return await self.validate(dispatcher, tracker, domain)
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa_sdk/forms.py", line 414, in validate
return await self.validate_slots(slot_values, dispatcher, tracker, domain)
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa_sdk/forms.py", line 371, in validate_slots
validation_output = validate_func(value, dispatcher, tracker, domain)
File "/Users/eduardobrigham/Rasa/rasa_EN/actions/actions.py", line 86, in validate_itemName
if value.lower() in self.itemName_db():
AttributeError: 'list' object has no attribute 'lower'
Thank you 
Indeed i was doing something stupid! fixed it and now slots get filled:
Chat History
# Bot You
──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
1 action_listen
──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
2 [1]{"entity": "itemQty", "role": "orderItem1", "group": "1"} [coke]{"entity": "itemName", "role": "orderItem1", "group": "1"} and [1]{"entity": "itemQty",
"role": "orderItem2", "group": "2"} [beer]{"entity": "itemName", "role": "orderItem2", "group": "2"} pls
intent: itemName_order 1.00
──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
3 restaurant_form
1coke
1beer
Current slots:
feedback: None, itemName: None, itemQty: None, preferences: None, requested_slot: None, tableNum: None
------
2020-05-31 13:15:36 DEBUG rasa.core.tracker_store - Recreating tracker for id '1d3b4069cbd241fa96304e98e50719d3
and action server prints:
(venv) (base) rasa run actions -v -vv
2020-05-31 13:15:06 INFO rasa_sdk.endpoint - Starting action endpoint server...
2020-05-31 13:15:06 INFO rasa_sdk.executor - Registered function for 'restaurant_form'.
2020-05-31 13:15:06 DEBUG rasa_sdk.utils - Using the default number of Sanic workers (1).
2020-05-31 13:15:35 DEBUG rasa_sdk.executor - Received request to run 'restaurant_form'
Order1 1coke
Order2 1beer
2020-05-31 13:15:35 DEBUG rasa_sdk.executor - Finished running 'restaurant_form'I was going to start typing on the error you getting from
anyhow Nice @edubrigham 
Hello Chandran it seems i cried victory too soon! It’s definitely working well when I enter order1 AND order2, but I get an error if I just enter 1 intem instead of 2 (ex.:order1):
> I want 1 coke
Rasa action server
2020-05-31 21:21:06 DEBUG rasa_sdk.executor - Received request to run 'restaurant_form'
Exception occurred while handling uri: 'http://localhost:5055/webhook'
Traceback (most recent call last):
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa_sdk/executor.py", line 387, in run
events = action(dispatcher, tracker, domain)
File "/Users/eduardobrigham/Rasa/rasa_EN/actions/actions.py", line 15, in run
a = next(tracker.get_latest_entity_values(entity_type="itemQty", entity_group = "1", entity_role="orderItem1"))
StopIteration
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/sanic/app.py", line 976, in handle_request
response = await response
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa_sdk/endpoint.py", line 102, in webhook
result = await executor.run(action_call)
RuntimeError: coroutine raised StopIteration
Rasa interactive --debug
Your input -> I want 1 coke
2020-05-31 21:24:22 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
2020-05-31 21:24:22 DEBUG rasa.core.processor - Starting a new session for conversation ID 'f58da8adc1c64dc18546b15324ff4c08'.
2020-05-31 21:24:22 DEBUG rasa.core.processor - Action 'action_session_start' ended with events '[<rasa.core.events.SessionStarted object at 0x15ae17950>, <rasa.core.events.ActionExecuted object at 0x15ae17910>]'.
2020-05-31 21:24:22 DEBUG rasa.core.processor - Current slot values:
feedback: None
itemName: None
itemQty: None
preferences: None
requested_slot: None
tableNum: None
2020-05-31 21:24:22 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.
2020-05-31 21:24:22 DEBUG rasa.nlu.selectors.response_selector - Adding following selector key to message property: default
2020-05-31 21:24:22 DEBUG rasa.core.processor - Received user message 'I want 1 coke' with intent '{'name': 'itemName_order', 'confidence': 0.9990455508232117}' and entities '[{'entity': 'itemQty', 'start': 7, 'end': 8, 'value': '1', 'extractor': 'DIETClassifier'}, {'entity': 'itemName', 'start': 9, 'end': 13, 'value': 'coke', 'extractor': 'DIETClassifier'}]'
2020-05-31 21:24:22 DEBUG rasa.core.processor - Current slot values:
feedback: None
itemName: None
itemQty: None
preferences: None
requested_slot: None
tableNum: None
2020-05-31 21:24:22 DEBUG rasa.core.processor - Logged UserUtterance - tracker now has 4 events.
2020-05-31 21:24:22 DEBUG rasa.core.lock_store - Deleted lock for conversation 'f58da8adc1c64dc18546b15324ff4c08'.
2020-05-31 21:24:22 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
? Is the intent 'itemName_order' correct for 'I want [1](itemQty) [coke](itemName)' and are all entities labeled correctly? Yes
2020-05-31 21:25:02 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
2020-05-31 21:25:02 DEBUG rasa.core.policies.fallback - NLU confidence threshold met, confidence of fallback action set to core threshold (0.3).
2020-05-31 21:25:02 DEBUG rasa.core.policies.memoization - Current tracker state [None, None, None, {}, {'entity_itemQty': 1.0, 'prev_action_listen': 1.0, 'entity_itemName': 1.0, 'intent_itemName_order': 1.0}]
2020-05-31 21:25:02 DEBUG rasa.core.policies.memoization - There is a memorised next action 'utter_greet'
2020-05-31 21:25:02 DEBUG rasa.core.policies.form_policy - There is no active form
2020-05-31 21:25:02 DEBUG rasa.core.policies.ensemble - Predicted next action using policy_1_MemoizationPolicy
2020-05-31 21:25:02 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
------
Chat History
# Bot You
──────────────────────────────────────────────────────────────
1 action_listen
──────────────────────────────────────────────────────────────
2 I want [1](itemQty) [coke](itemName)
intent: itemName_order 1.00
Current slots:
feedback: None, itemName: None, itemQty: None, preferences: None, requested_slot: None, tableNum: None
------
2020-05-31 21:25:02 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
? The bot wants to run 'utter_greet', correct? No
2020-05-31 21:25:05 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
------
Chat History
# Bot You
──────────────────────────────────────────────────────────────
1 action_listen
──────────────────────────────────────────────────────────────
2 I want [1](itemQty) [coke](itemName)
intent: itemName_order 1.00
Current slots:
feedback: None, itemName: None, itemQty: None, preferences: None, requested_slot: None, tableNum: None
------
2020-05-31 21:25:05 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
? What is the next action of the bot? 0.00 restaurant_form
Thanks! The bot will now run restaurant_form.
2020-05-31 21:25:09 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
2020-05-31 21:25:09 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
2020-05-31 21:25:09 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
2020-05-31 21:25:09 DEBUG rasa.core.actions.action - Calling action endpoint to run action 'restaurant_form'.
2020-05-31 21:25:09 ERROR rasa.core.processor - Encountered an exception while running action 'restaurant_form'. Bot will continue, but the actions events are lost. Please check the logs of your action server for more information.
2020-05-31 21:25:09 DEBUG rasa.core.processor - Failed to execute custom action.
Traceback (most recent call last):
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa/core/actions/action.py", line 549, in run
json=json_body, method="post", timeout=DEFAULT_REQUEST_TIMEOUT
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa/utils/endpoints.py", line 154, in request
response.status, response.reason, await response.content.read()
rasa.utils.endpoints.ClientResponseError: 500, Internal Server Error, body='b'\n <h1>Internal Server Error</h1>\n <p>\n The server encountered an internal error and cannot complete\n your request.\n </p>\n''
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa/core/processor.py", line 644, in _run_action
events = await action.run(output_channel, nlg, tracker, self.domain)
File "/Users/eduardobrigham/Rasa/venv/lib/python3.7/site-packages/rasa/core/actions/action.py", line 572, in run
raise Exception("Failed to execute custom action.") from e
Exception: Failed to execute custom action.
2020-05-31 21:25:09 DEBUG rasa.core.processor - Action 'restaurant_form' ended with events '[]'.
2020-05-31 21:25:09 DEBUG rasa.core.processor - Current slot values:
feedback: None
itemName: None
itemQty: None
preferences: None
requested_slot: None
tableNum: None
2020-05-31 21:25:09 DEBUG rasa.core.lock_store - Deleted lock for conversation 'f58da8adc1c64dc18546b15324ff4c08'.
2020-05-31 21:25:09 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
2020-05-31 21:25:09 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
2020-05-31 21:25:09 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
2020-05-31 21:25:09 DEBUG rasa.core.policies.fallback - NLU confidence threshold met, confidence of fallback action set to core threshold (0.3).
2020-05-31 21:25:09 DEBUG rasa.core.policies.memoization - Current tracker state [None, None, {}, {'entity_itemQty': 1.0, 'prev_action_listen': 1.0, 'entity_itemName': 1.0, 'intent_itemName_order': 1.0}, {'prev_restaurant_form': 1.0, 'entity_itemQty': 1.0, 'entity_itemName': 1.0, 'intent_itemName_order': 1.0}]
2020-05-31 21:25:09 DEBUG rasa.core.policies.memoization - There is no memorised next action
2020-05-31 21:25:09 DEBUG rasa.core.policies.form_policy - There is no active form
2020-05-31 21:25:09 DEBUG rasa.core.policies.mapping_policy - There is no mapped action for the predicted intent, 'itemName_order'.
2020-05-31 21:25:09 DEBUG rasa.core.policies.ensemble - Predicted next action using policy_0_FallbackPolicy
2020-05-31 21:25:09 DEBUG rasa.core.tracker_store - Recreating tracker for id 'f58da8adc1c64dc18546b15324ff4c08'
------
Chat History
# Bot You
────────────────────────────────────────────────────────────────
1 action_listen
────────────────────────────────────────────────────────────────
2 I want [1](itemQty) [coke](itemName)
intent: itemName_order 1.00
────────────────────────────────────────────────────────────────
3 restaurant_form
Current slots:
feedback: None, itemName: None, itemQty: None, preferences: None, requested_slot: None, tableNum: NoneThey above works for only 2 items
If you want to work for N itemQty and itemName
use a loop
entities = tracker.latest_message['entities']
for e in entities:
if 'itemQty' in e['entity']:
a = next(tracker.get_latest_entity_values(
entity_type=e['entity'], entity_group=e['group'], entity_role=e['role']))
dispatcher.utter_message(a)
if 'itemName' in e['entity']:
b = next(tracker.get_latest_entity_values(
entity_type=e['entity'], entity_group=e['group'], entity_role=e['role']))
dispatcher.utter_message(b)I really appreciate your help Murali. listen, would you be interested in doing some (paid) dev work? it’s not much, and it is quite simple i’m sure, but those very simple tasks take me an enormous amount of time to find out how to do it. I’m sure you can do all that i need in a couple of hours. What do you think 
Sure. But its hourly basis. If you are okay with it.
no problem! I’ll send you an email