YAML general overview
NLP engine configuration using YAML
General YAML file format
For each NLP engine project, we define new set of flow configuration files, and the chatbot platform itself stays the same. All models and installations are made based on the configuration files.
One project can be defined by one or more YAML files with extension .yaml (or .yml). Yaml is a standardized format described in many sources such as:
General YAML syntax
In NLP engine, all YAMLs are structured in root level as dictionaries (mappings). The dictionary keys in NLP engine are always strings, the values in the root level are usually dictionaries.
# YAML file
key1: dict1
key2: dict2
key3: dict3
...Strings in YAML can be wrapped in quotes, preferred form for keys is without wrapping. Following entries are equivalent (and the first one recommended):
key1: value1
"key1": value1
'key1': value1Comments
key: value # good comment
key: "value # broken comment (forgotten quote)Strings
String values are recommended to be wrapped into double quotes.
"nice string"
'nice string' # ok, but not preferred
nice string # ok in this case, but not preferred
"1" # strings containing digits must be wrapped
"'1'" # sometimes we want to encode quotes, in that case use both quote types
"-" # special characters must be wrapped in quotesIntegers and floats
Numbers are used in configuration section. In other sections, string are used instead.
1 # integers
10
-34
1.2 # floats
10.0
-34.3Lists
- first item string # string item on 1st position
- 3 # integer item in list on 2nd position
-
- a # other lists can be nested inside
- b
- [] # empty listDictionaries (mappings)
key: value # string key
"1": value # string key, do not use integer key, because JSON doesn't support them
empty: {} # empty dict can be written using {} syntaxOrdered dictionaries (equal to list of lists)
some_ordered_dict:
- first_key: first_value
- second_key: second_valueMerging YAML files
If more YAML files are provided and they have same substructure with the same keys, the values are merged if possible.
Example for two files A and B:
File A:
type: list
content:
- 1
- 2
note: exampleFile B:
type: list
content:
- 3
label: exampleMerged A and B:
type: list
content:
- 1
- 2
- 3
note: example
label: exampleExample for two incompatible files C and D:
File C:
type: "list"File B:
type: "string"Cannot merge two strings with different values.
Configuration
YAML configuration section
Following settings must be present at least in one YAML file of the given project.
All model settings are withing configuration key:
configuration:
KEY: VALUEExample of filled values:
version: "1.1"
configuration:
start_node: BEGIN_NODE
allow_jumping: true
allow_jumping_to_nodes:
- node_name_a
- node_name_b
language: en
description: frequently asked question answering for customer XXX
project: hcdemo
classifier:
tokenizer: nist
aspell: replace
stopwords: true
train:
epoch: 10
lr: 0.2
intent_threshold: 0.4
intent_relative_threshold: 1.3
speed_coefficient: 0.3
max_delay_milliseconds: 2500
debug: TrueParameters description: : 1. version (str): version of flow configuration. 2. start_node (str): The code of graph node in conversation flow in which the conversation starts. 3. allow_jumping (bool): If allowed, the user can leave conversation tree and starts new topic which is accessible from start_node. If forbidden, the user can visit only graph nodes allowed in conversation flow or nodes presented in allow_jumping_to_nodes. 4. allow_jumping_to_nodes: List of intents which can be jumped to from another intents (confidence of such intent prediction have some penalty to prefer intents in trees). 5. language: model is trained using data for given language code (tested for cs, sk and en). 6. description: notes about this project, not used in code 7. project: project code, will be used for folder naming in Linux 8. classifier: configuration of NLU module: > * 8.1. tokenizer (str): default value nist > * 8.2. aspell (replace/duplicate/whitelist/null): > one of values replace (replace misspelled words by their correct forms), > duplicate (add correct form of misspelled word to the end of utterance), > whitelist (use only whitelist corrections, ignore aspell, very good for speech channel) and > null (no correction and accentuation) > * 8.3. stopwords (bool): remove stopwords from text (e.g. the, be and and). 9. train: models for deep neural network, two parameters allowed in configuration: > * 9.1. epoch (int): how long will the training takes (recommended number between 3 and 15) > * 9.2. lr (float): learning rate, how fast will neural network learn, must be positive number 10. intent_threshold (float): if intent confidence is lower than this value, : return I_DONT_UNDERSTAND intent instead 11. intent_relative_threshold (float): if the first suggested intent confidence : is not higher than the second suggested intent confidence multiplied by this value, return I_DONT_UNDERSTAND intent instead 12. speed_coefficient (float): smaller value, smaller delay between messages sent by chatbot to : user, 1 gives enough time for average user to read everything before the next message is displayed. 13. max_delay_milliseconds (int): max. delay between messages sent by chatbot in milliseconds 14. debug (bool): if set for True, deployment will not fail on extractors which were not implemented yet (such : extractors will be replaced by one that return nothing)
How does the threshold work?
Test is performed only if more than one intent is considered.
Intent resolver predicts <0, n> pairs of original confidences and labels (oc1, label1), (oc2, label2), …. Original confidence is a number in range <0, 1> and the sum of original confidences is in range <0, inf).
Flow cuts off unreachable nodes and nodes not passing EXTRACTors entry conditions.
Also, we work with SSI (semantically same intent) groups. The rule is following:
while the label with the highest score is in the same SSI group as the second-best node, merge scores of these nodes and keep the label of winner
Example intent resolver scores:
label confidence SSI group yes_plain 0.003 YES yes_sure 0.0005 YES yes_maybe 0.0004 YES no_plain 0.0003 NO yes_super 0.00025 YES
is converted to:
label confidence SSI group yes_plain 0.0039 YES no_plain 0.0003 NO yes_super 0.00025 YES
and also normalized confidence is computed (the sum of normalized confidences is 1):
label confidence SSI group normalized confidence yes_plain 0.0039 YES 0.8764044943820224 no_plain 0.0003 NO 0.06741573033707865 yes_super 0.00025 YES 0.056179775280898875
After merging SSI nodes and computing normalized score, the threshold tests follow:
original threshold test:
If the first label original confidence is less than original threshold, no intent is selected.
With
original_intent_threshold=0.001, the labelyes_plainpasses and test continues.With
original_intent_threshold=0.005, the labelyes_plainfails and no intent is selected.normalized threshold test:
If the first label normalized confidence is bigger than intent_threshold, the first label is selected, otherwise, the next test follows.
with
intent_threshold=0.8, the labelyes_plainpasses and is returned (intent is selected)with
intent_threshold=0.9, the labelyes_plainfails and next test followsrelative threshold test:
If the best label confidence is X times bigger than the second-best label confidence, the best label is accepted and intent is selected.
with
intent_relative_threshold=10, the labelyes_plainpasses (0.067 * 10 < 0.87), intent is selectedwith
intent_relative_threshold=20, the labelyes_plainfails (0.067 * 20 > 0.87), no intent is selected
Designing the conversation flow
Flow attribute
In flow attribute, the conversation flow is represented using YAML syntax. To express the conversation in YAML, the flow is simplified to the oriented graph with nodes and edges (actions, conditions, gotos).
Nodes are usually named with CAPITAL_ASCII letters and underscores.
Edges of the graphs are: : * intents/user actions
automatic transitions based on conditions (based on system state)
simple automatic transitions
The conversation graph always starts in node defined in
configuration:
start_node: NODE_NAMENodes properties
Node properties order:
EXTRACT: entry check calls before entering NODE, enter only if all EXTRACT calls receive non-None response
CALL: system backend calls (interface agreements calls)
RESET: unset variables
SET: set variables
1, 2, …: produce outputs
CONDITIONS: try to change node to the first fulfilled condition
ACTIONS_SIGNALS: handle signals sent instead of user input
ACTIONS: wait for user utterance, after that, change node or continue
exclusive fallbacks (all variants are mutually exclusive):
GOTO: fallback
GOTO_REUSE_UTTERANCE: fallback leading to another intent resolving
GOTO_WAIT: fallback waiting for user action, signal or empty message, but do not consume the message
GOTO_BACK: fallback leading to already visited node
EXTRACT
Check if node can be accessed by calling existing_function_name_X. If node is selected by IntentResolver as the best candidate and at the same time, return value of call existing_function_name_X is not None (null), assign value to variable var2fill_no_X.
NODE_NAME:
EXTRACT:
- "var2fill_no_1": existing_function_name_1
- "var2fill_no_2": existing_function_name_2
# ...
- "var2fill_no_N": existing_function_name_N
# or more informative text:
- "var2fill_no_a": [existing_function_name_1, {'par1': 'val1'}]
- "var2fill_no_b": [existing_function_name_2, {}]
# ...
- "var2fill_no_z": [existing_function_name_N, {'url': 'xyz', 'timeout': 20}]EXTRACT Roles
Extract attributes will be always designed by BornDigital team.
If EXTRACT attribute is added to YAML by BornDigital, all visual tools should be able to display it and preserve the information
EXTRACT Visualization example
╔═════════════════════════════════════════════════╗
║ NODE_NAME ║
╟─────────────────────────────────────────────────╢
║ E: var2fill_no_1: existing_function_name_1 ║
║ E: var2fill_no_2: existing_function_name_2 ║
║ E: var2fill_no_N: existing_function_name_N ║
║ E: var2fill_no_a: existing_function_name_1... ║
║ E: var2fill_no_b: existing_function_name_2... ║
║ E: var2fill_no_z: existing_function_name_N... ║
╚═════════════════════════════════════════════════╝CALL
Call some function from interface agreement (existing_function_name_X). Set the response to variable (var2fill_no_X).
NODE_NAME:
CALL:
- "var2fill_no_1": existing_function_name_1
- "var2fill_no_2": existing_function_name_2
# ...
- "var2fill_no_N": existing_function_name_N
# or more informative text:
- "var2fill_no_a": [existing_function_name_1, {'par1': 'val1'}]
- "var2fill_no_b": [existing_function_name_2, {}]
# ...
- "var2fill_no_z": [existing_function_name_N, {'url': 'xyz', 'timeout': 20}]CALL Roles
Not displayed in visualization or displayed for business users.
Will be added to YAML using interface agreement markdown.
CALL Visualization example
╔═════════════════════════════════════════════════╗
║ NODE_NAME ║
╟─────────────────────────────────────────────────╢
║ C: var2fill_no_1: existing_function_name_1 ║
║ C: var2fill_no_2: existing_function_name_2 ║
║ C: var2fill_no_N: existing_function_name_N ║
║ C: var2fill_no_a: existing_function_name_1... ║
║ C: var2fill_no_b: existing_function_name_2... ║
║ C: var2fill_no_z: existing_function_name_N... ║
╚═════════════════════════════════════════════════╝Extensions documentation
SET
Set system, local and other variables for current conversation_id (session id). To write
NODE_NAME:
SET:
- "simple_string": "'simple text'"
# 'simple text'
- "longer_string": "'Very long text:\n...with new lines\nanother line\n...etc.'"
# 'Very long text:
# ...with new lines
# another line\n...etc.'
- "int_number": "23"
# 23
- "float_number": "0.53"
# 0.53
- "float_number_with_python": "round(0.59, 1)"
# 0.6
- "lists_with_mixed_content": "[1, '2', '...']"
# [1, "2", "..."]
- "dicts_with_mixed_content": "{1: 'int', '2': 'str'}"
# {1: "int", "2": "str"}
- "reuse_variable": "int_number + 2"
# 25
- "another_reuse": "str(reuse_variable) + 'hello'"
# '25hello'
- "python_tricks": "1 if int_number > 10 else 2"
# 2
- "access_structure": "lists_with_mixed_content[1] + dicts_with_mixed_content['2']"
# "2str"SET Roles
All sets should be present in logic.
SET Visualization example
╔═════════════════════════════════════════════════╗
║ NODE_NAME ║
╟─────────────────────────────────────────────────╢
║ S: simple_string="'simple text'" ║
║ S: longer_string="'Very long text:\n...[cut] ║
║ S: int_number="23" ║
║ ... ║
╚═════════════════════════════════════════════════╝RESET
Remove content of some variable, usually some help variable. Also used when skipping to another part of logic.
Remove content of variables a, b and c:
NODE_NAME_A:
RESET:
- "a"
- "b"
- "c"Delete all variables:
NODE_NAME_B:
RESET:
- "all"Delete all variables except a and b and c:
NODE_NAME_C:
RESET:
- "a"
- "b"
- "c"
- "except"Approaches above cannot be combined.
RESET Roles
All resets should be present in logic.
RESET Visualization examples
╔═════════════════════════════════════════════════╗
║ NODE_NAME_A ║
╟─────────────────────────────────────────────────╢
║ R: [a, b, c] ║
╚═════════════════════════════════════════════════╝
╔═════════════════════════════════════════════════╗
║ NODE_NAME_B ║
╟─────────────────────────────────────────────────╢
║ R: [all] ║
╚═════════════════════════════════════════════════╝
╔═════════════════════════════════════════════════╗
║ NODE_NAME_C ║
╟─────────────────────────────────────────────────╢
║ R: [a, b, c, except] ║
╚═════════════════════════════════════════════════╝1, 2, 3, …
Produces outputs.
Text output:
NODE_NAME:
1:
MARKDOWN: "Simple text"
2:
MARKDOWN: "Another bubble"╔═════════════════════════════════════════════════╗
║ NODE_NAME ║
╟─────────────────────────────────────────────────╢
║ OT: Simple text ║
║ OT: Another bubble ║
╚═════════════════════════════════════════════════╝Speech output:
NODE_NAME:
1:
SPEECH: "Simple speech. Speech can be present in one tag, bubbles do not have sense."╔═════════════════════════════════════════════════╗
║ NODE_NAME ║
╟─────────────────────────────────────────────────╢
║ OS: Simple speech. Speech can be present in ║
║ one tag, bubbles do not have sense. ║
╚═════════════════════════════════════════════════╝Mixed channels:
NODE_NAME:
1:
MARKDOWN: "Simple speech"
SPEECH: "Simple speech. Speech can be present
in one tag, bubbles do not have sense."
2:
MARKDOWN: "Text has more tags than speech."╔═════════════════════════════════════════════════╗
║ NODE_NAME ║
╟─────────────────────────────────────────────────╢
║ OS: Simple speech. Speech can be present in ║
║ one tag, bubbles do not have sense. ║
║ OT: Simple text ║
║ OT: Text has more tags than speech. ║
╚═════════════════════════════════════════════════╝Extra data for frontend and/or widgets:
NODE_NAME:
1:
# https://trello.com/c/AJnPxOEi/114-widget-pro-konfigurovatelný-carousel
WIDGET: carousel
DATA:
widget: [
{"title": "1. Hello, swipe right", "image_url": "https://example.com/images/1.svg"},
{"title": "2. I have description", "description": "This text will below the image", "image_url": "https://example.com/images/2.svg"},
{"title": "3. I am always right", "image_url": "https://example.com/images/3.svg"},
]
2:
MARKDOWN: "Please wait, loading."
NODE_NAME_2:
1:
# https://trello.com/c/Ur8blaSi/437-basic-list-widget-done
WIDGET: listWithAutocomplete
DATA:
widget:
title: 'Please select our open hours:'
list:
- city: Dumaguete
openingHours: 9am - 1pm
- city: Dubai
openingHours: 6am - 1pm
- city: Dauin
openingHours: 8am - 1pm
- city: DumaGetMe
openingHours: 7am - 1pm
- city: Manila
openingHours: 8am - 4pm
- city: Cagayan de Oro
openingHours: 9am - 3pm
- city: Praha
openingHours: '08:00 - 17:00'
- city: Brno
openingHours: closed
NODE_NAME_3:
1:
# https://trello.com/c/GF3gw9Yc/123-upravit-widget-recognizednumber-abychom-mohli-měnit-v-logice-text-ve-widgetu-a-validaci-nebo-vytvořit-nový
WIDGET: 'Recognized_Number'
DATA:
widget:
text: 'string'
field_recognized_number:
visibility: 'boolean'
label: 'string'
placeholder: 'string'
validation:
input_type: 'string / integer'
length_min: 'absolute integer'
length_max: 'absolute integer'
start_with: 'abcd...0123456789'
end_with: 'abcd...0123456789'
field_phone_number:
visibility: 'boolean'
label: 'string'
placeholder: 'string'
validation:
input_type: 'string / integer'
length_min: 'absolute integer'
length_max: 'absolute integer'
start_with: 'abcd...0123456789'
end_with: 'abcd...0123456789'╔═════════════════════════════════════════════════╗
║ NODE_NAME ║
╟─────────────────────────────────────────────────╢
║ OD: CHANGE_BACKGROUND_COLOR ║
║ OW: PLAY_MUSIC ║
║ OT: Please wait, loading. ║
╚═════════════════════════════════════════════════╝We can use placeholders to add variables:
NODE_NAME:
1:
MARKDOWN: "**Bold speech {abc}.**"
SPEECH: "Simple speech. {record_name}."
2:
MARKDOWN: "[alt text]: http://web/image.png 'Title'"╔═════════════════════════════════════════════════╗
║ NODE_NAME ║
╟─────────────────────────────────────────────────╢
║ OS: Simple speech. {record_name}. ║
║ OT: **Bold speech {abc}.** ║
║ OT: [alt text]: http://web/image.png 'Title' ║
╚═════════════════════════════════════════════════╝1, 2, 3, … Roles
Defined in logic.
ACTIONS
Wait in the node until user produces next utterance (speech or text). After utterance is received, process it by IntentResolver. If some available intent matches the utterance, the state changes from current NODE_NAME_X to new NODE_NAME_Y.
NODE_NAME:
ACTIONS:
NODE_NAME_A:
- "some sentence example 1"
- "some sentence example 2"
- "another word sequence exemplar n"
NODE_NAME_B:
- "intent description 1"
- "new intent description 2"
- "intent definition N"
NODE_NAME_C:
- "weather"
- "sunny"
- "raining... "ACTIONS Roles
All actions should be present in logic.
ACTIONS Visualization example
╔═══════════╗
║ NODE_NAME ║ ╔═════════════╗
╟───────────╢═════════════════════════════> ║ NODE_NAME_A ║
║ ║ some sentence example 1 ╚═════════════╝
╚═══════════╝
║ ╔═════════════╗
╠══════════════════════════════════> ║ NODE_NAME_B ║
║ intent description 1 ╚═════════════╝
║
║ ╔═════════════╗
╚══════════════════════════════════> ║ NODE_NAME_C ║
weather ╚═════════════╝ACTIONS_SIGNALS
Signal can be sent in special cases like too much noise in the voice channel to inform the customer that he/she should repeat the sentence in the more calm environment. After the signal is received the state changes from current NODE_NAME to new NODE_NAME_A.
NODE_NAME:
ACTIONS_SIGNALS:
no_input: NODE_NAME_A
no_match: NODE_NAME_B
call_end_customer_hangup: NODE_NAME_CACTIONS_SIGNALS Roles
All signal nodes should be present in logic.
no_input: Customer is silent (his/her microphone is not catching any sound). The recommended reaction is to check whether is customer still listening and ready to continue current conversation.
no_match: Customer speech is unintelligible (too much noise in the background; speaker is cold; speaker is foreigner with bad pronunciation; bad articulation). The recommended reaction is to ask customer to rephrase his utterance slowly and intelligibly.
call_end_customer_hangup: Customer ended conversation prematurely. After this, the data storage should be cleaned and extra follow-up actions planned.
ACTIONS_SIGNALS Visualization example
Generic intents documentation
CONDITIONS
Try conditions from top to bottom, the first fulfilled condition is activated and the state is changed to the node assigned to the condition. The last condition can be True which replaces GOTO fallback.
NODE_NAME:
CONDITIONS:
- "some_variable == 'hello'": NODE_NAME_A
- "another_variable == 23": NODE_NAME_B
- "True": NODE_NAME_CVersion with fallback:
NODE_NAME_2:
CONDITIONS:
- "some_variable == 'hello'": NODE_NAME_A2
- "another_variable == 23": NODE_NAME_B2
GOTO: NODE_NAME_C3CONDITIONS Roles
All conditions should be present in logic.
CONDITIONS Visualization example
╔═══════════╗
║ NODE_NAME ║
╟───────────╢
║ ║
╚═══════════╝
║
some_variable == 'hello' ╔═════════════╗
╠═True═══════════════════> ║ NODE_NAME_A ║
False ╚═════════════╝
║
another_variable == 23 ╔═════════════╗
╠═True═══════════════════> ║ NODE_NAME_B ║
False ╚═════════════╝
║
True ╔═════════════╗
╚═True═══════════════════> ║ NODE_NAME_C ║
╚═════════════╝Version with fallback:
╔═════════════╗
║ NODE_NAME_2 ║
╟─────────────╢
║ ║
╚═════════════╝
║
another_variable == 23 ╔═════════════╗
╠═True═══════════════════> ║ NODE_NAME_B ║
False ╚═════════════╝
║
True ╔═════════════╗
╠═True═══════════════════> ║ NODE_NAME_C ║
║ ╚═════════════╝
║
\ /
╔══════════════╗
║ NODE_NAME_C2 ║
╚══════════════╝GOTO
Fallback, if there is no other option, travel from current node to GOTO destination.
NODE_NAME:
GOTO: DESTINATION_NODEGOTO Roles
All gotos should be present in logic.
GOTO Visualization example
╔══════════════════╗
║ NODE_NAME ║
╟──────────────────╢
║ ║
╚══════════════════╝
║
║
\ /
╔══════════════════╗
║ DESTINATION_NODE ║
╚══════════════════╝GOTO_REUSE_UTTERANCE
Fallback, if there is no other option, travel from current node to GOTO_REUSE_UTTERANCE destination. Also, the utterance written/said by user can be modified reused later. Please be mindful of the fact that input utterance is also processed. That means corrector and transformer changes are reapplied to it.
NODE_NAME:
GOTO_REUSE_UTTERANCE: [DESTINATION_NODE, 'Python code']GOTO_REUSE_UTTERANCE Python code
It can operate with one variable original_utterance and can use regex Python library re. It must have non-empty value (empty value would make GOTO_REUSE_UTTERANCE same as GOTO), it can use newlines (the return value will be used from last line).
GOTO_REUSE_UTTERANCE Roles
All tags should be present in logic.
GOTO_REUSE_UTTERANCE Visualization example
GOTO_WAIT
Fallback, wait here until next API call. The API call can contain user utterance, signal or be empty.
Can be used for situations we:
need to ignore user input (user is waiting, music is playing; waiting for backend call response; etc.):
flow: PAUSE_NODE: GOTO_WAIT: PAUSE_NODEwant to use only regular expressions and variables for routing and need to turn intents off for this decision:
flow: QUESTION: 1: MARKDOWN: "What product do you have?" GOTO_WAIT: DETECT DETECT: CALL: - product: utterance CONDITIONS: - "'O1' in product": "MOBILE_01" - "'O2' in product or 'beta' in product": "MOBILE_02" - "'O3' in product or 'prime' in product": "MOBILE_03" - "True": NOT_UNDERSTOOD
GOTO_STOP
Fallback, stops user and sends response from interaction with preset timeout variable set to 0.
Can be used identically to GOTO_WAIT above, however when working in tandem with voice server a new interaction is initiated due to timeout value.
Interaction with GOTO_REUSE_UTTERANCE
GOTO_WAITis activated by utterance,GOTO_REUSE_UTTERANCEkeeps that utterance
GOTO_WAITis activated by signal or empty message,GOTO_REUSE_UTTERANCEkeeps utterance empty (None)
GOTO_WAIT Visualization example
Clever fallback for I_DONT_UNDERSTAND and ERROR
To modify your flow to support fallbacks, several changes need to be implemented. Firstly, you need to find all nodes needing fallbacks:
“I do not understand” fallbacks should be present for every node that: : 1. Contains property ACTIONS and do not contain property GOTO 2. Contains property ACTIONS and contains property GOTO
“Error” fallback should be present for every node that: : 1. Contains property CONDITIONS and do not contain property GOTO
Examples of situations and solutions:
flow:
NODE_XYZ:
ACTIONS:
intent_abc:
- some word
intent_xyz:
- other tokensis transformed to:
flow:
NODE_XYZ:
ACTIONS:
intent_abc:
- some word
intent_xyz:
- other tokens
NODE_XYZ_I_DONT_UNDERSTAND:
- bla bla
- some nonsense
GOTO: NODE_XYZ_I_DONT_UNDERSTANDflow:
NODE_XYZ:
ACTIONS:
intent_abc:
- some word
intent_xyz:
- other tokens
GOTO: intent_abcis transformed to:
flow:
NODE_XYZ:
ACTIONS:
intent_abc:
- some word
intent_xyz:
- other tokens
NODE_XYZ_I_DONT_UNDERSTAND:
- bla bla
- some nonsense
GOTO: intent_abcflow:
NODE_XYZ:
CONDITIONS:
- "a < 2": intent_abc
- "a >= 2": intent_xyzis transformed to:
flow:
NODE_XYZ:
CONDITIONS:
- "a < 2": intent_abc
- "a >= 2": intent_xyz
GOTO: NODE_XYZ_ERRORNow we need to add newly mentioned nodes:
For actions (we will use extractor counter which automatically increment variable by one each time we enter the node):
flow:
NODE_XYZ:
ACTIONS:
intent_abc:
- some word
intent_xyz:
- other tokens
NODE_XYZ_I_DONT_UNDERSTAND:
- bla bla
- some nonsense
GOTO: intent_abc
NODE_XYZ_I_DONT_UNDERSTAND:
1:
MARKDOWN: "Je nám líto, nerozuměla jsem vám. Mohli byste to zopakovat jinými slovy? Děkuji"
SPEECH: "Je nám líto, nerozuměla jsem vám. Mohli byste to zopakovat jinými slovy? Děkuji"
CALL:
- _temp_counter_: counter
CONDITIONS:
- "_temp_counter_ < 2": NODE_XYZ
- "True": SESSION_ENDFor conditions:
flow:
NODE_XYZ:
CONDITIONS:
- "a < 2": intent_abc
- "a >= 2": intent_xyz
GOTO: NODE_XYZ_ERROR
NODE_XYZ_ERROR:
1:
MARKDOWN: "Je nám líto, nastala chyba a musíme spojení ukončit."
SPEECH: "Je nám líto, nastala chyba a musíme spojení ukončit."
GOTO: SESSION_ENDHandling meaningless inputs with signals
In some conversations, GoodBot can receive a short meaningless inputs. Commonly a speech engine catches noises in the background (music, car engine, other people are talking) or user writes a typo (a cat walks over the keyboard, children seize the phone, etc.). In such cases, the GoodBot receives input such as pp, hjk or mm.
This feature allows to recognize such noises and replace them by a signal defined in the configuration yaml in the section:
configuration: replace_noise_by_signal: SIGNAL_NAME
To turn off this feature, set
falseornullin the configuration section:
configuration: replace_noise_by_signal: null
Of course, it is necessary to have signals set up in GoodBot. Let’s have look at an example of a node named ARE_YOU_CONTENT with a definition for the signal catching meaningless inputs:
flow: ARE_YOU_CONTENT: ACTIONS_SIGNALS: no_match: ARE_YOU_CONTENT_NO_INPUT ACTIONS: YES: *yes NO: *no
ARE_YOU_CONTENT_NO_INPUT: 1: SPEECH: "Sorry, I didn't get it. Can you repeat it, please?" GOTO: ARE_YOU_CONTENT
And example of a node in which the feature won’t work:
flow: ARE_YOU_HAPPY: ACTIONS: YES: *yes NO: *no
Last updated
Was this helpful?