基於rasa構建faq

faq(frequency asked question), 常問問題，這類FAQ問題機器人，經過收集常見問題，以交互式方式實現人機問答。

rasa應用中涉及的文件有：config.yml, nlu.md, stories.md, domain.yml。新增常見問題回答文件reponses.md

1. config.yml

    實現faq, 要有ResponseSelector, 它是一個監督式的檢索模型，當用戶的意圖識別爲faq意圖後，經過responseSelector從預先定義的回覆文本中檢索生成回覆，回覆發送給respond_faq. 

# Configuration for Rasa NLU.
# https://rasa.com/docs/rasa/nlu/components/
language: en
pipeline:
  - name: WhitespaceTokenizer
  - name: RegexFeaturizer
  - name: LexicalSyntacticFeaturizer
  - name: CountVectorsFeaturizer
  - name: CountVectorsFeaturizer
    analyzer: "char_wb"
    min_ngram: 1
    max_ngram: 4
  - name: DIETClassifier
    epochs: 100
  - name: EntitySynonymMapper
  - name: ResponseSelector
    epochs: 100

# Configuration for Rasa Core.
# https://rasa.com/docs/rasa/core/policies/
policies:
  - name: MemoizationPolicy
  - name: TEDPolicy
    max_history: 5
    epochs: 100
  - name: MappingPolicy

2. nlu.md

    在greet和goodbye意圖基礎上，添加faq意圖，也可只保留faq

## intent:greet
- hey
- hello
- hi
- good morning
- good evening
- hey there

## intent:goodbye
- bye
- goodbye
- see you around
- see you later

## intent:faq/ask_channels
- what channels of communication does rasa support?
- what channel do you support
- what chat channels does rasa uses

## intent:faq/ask_languages
- what language does rasa support?
- which language do you support
- which language supports rasa
- languages supported

3.  stories.md

    增長faq

## happy path
* greet
  - utter_greet

## say goodbye
* goodbye
  - utter_goodbye

## some questions from faq
* faq
  - respond_faq

4. domain.yml

    intents, actions中需添加faq

intents:
  - greet
  - goodbye
  - faq

actions:
  - respond_faq

responses:
  utter_greet:
  - text: "Hey! How are you?"

  utter_goodbye:
  - text: "bye"

session_config:
  session_expiration_time: 60
  carry_over_slots_to_new_session: true

5. responses.md

    實現channel和language的回答

## ask channels
* faq/ask_channels
  - we have a comprehensive from ask_channels
  
## ask languages
* faq/ask_languages
  - you can use rasa to build assistants from ask_language

完整代碼請走：https://github.com/hugLiu/rasa-faq/tree/main