rasa 介绍文档

responses:   
  utter_greet:   
  - text: "今天天气怎么样"                       #添加文字
    image: "https://i.imgur.com/nGF1K8f.jpg"        #添加图像

responses:   
  utter_ask_name_spelled_correctly:
  - buttons:
    - payload: /affirm
      title: Yes
    - payload: /deny
      title: No
    text: Is {first_name} spelled correctly?

stories: 
- story: happy path   
  steps:   
  - intent: greet   
  - action: utter_greet       
  - intent: mood_great   
  - action: utter_happy

rasa init         # 使用自带的样例数据生成一个新的 project
rasa train        # 训练模型
rasa test         # 测试训练好的 rasa 模型 (默认使用最新的)
rasa interactive  # 和 bot 进行交互，创建新的训练数据 
rasa shell        # 加载模型 (默认使用最新的)，在命令行和 bot 对话 
rasa run          # 使用训练好的模型，启动 server，包括 NLU 和 DM 
rasa run actions  # 使用 rasa SDK，启动 action server 

nlu: 
- regex: car_type   
  examples: |   
  - ^[a-zA-Z][0-9]$ 

- intent: 手机产品介绍   
  examples: |     
    - 这款手机[续航](property)怎么样呀？

{   "entities": [{         
    "value": "续航",         
    "start": 20,         
    "end": 33,         
    "confidence": 0.812631,         
    "entity": "property",         
    "extractor": "DIETClassifier"     
    }] 
} 

nlu: 
- intent: 手机产品介绍   
examples: |     
 - 我想要对比一下[Mi11]{“entity”: “type”, “role”: “xiaomi”}和[iPhone11]{“entity”: “type”, “role”: “apple”} 

nlu: 
- intent: 手机产品介绍   
    examples: |     
    - 我想要对比一下[Mi10]{“entity”: “type”, “group”: “1”}, 
    [Mi11]{“entity”: “type”, “group”: “1”}
    和[iPhone11]{“entity”: “type”, “group”: “2”} 

nlu:  
- intent: 手机产品介绍   
  examples: |     
    - 我想看看[Mi11](type)  
- synonym: P7     
    examples: |     
    - 小米11      
    - xiaomi11

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

pip install rasa_chinese
pip install rasa_chinese_service

  - name: "rasa_chinese.nlu.tokenizers.lm_tokenizer.LanguageModelTokenizer"
    tokenizer_url: "http://127.0.0.1:8000/"

 - name: LanguageModelFeaturizer
    model_name: bert
    model_weights: /path/to/offline_model

pipeline:
- name: "rasa.nlu.components.MyComponent"

import typing
from typing import Any, Optional, Text, Dict, List, Type

from rasa.nlu.components import Component
from rasa.nlu.config import RasaNLUModelConfig
from rasa.shared.nlu.training_data.training_data import TrainingData
from rasa.shared.nlu.training_data.message import Message

if typing.TYPE_CHECKING:
    from rasa.nlu.model import Metadata


class MyComponent(Component):
    """A new component"""

    # Which components are required by this component.
    # Listed components should appear before the component itself in the pipeline.
    @classmethod
    def required_components(cls) -> List[Type[Component]]:
        """Specify which components need to be present in the pipeline."""

        return []

    # Defines the default configuration parameters of a component
    # these values can be overwritten in the pipeline configuration
    # of the model. The component should choose sensible defaults
    # and should be able to create reasonable results with the defaults.
    defaults = {}

    # Defines what language(s) this component can handle.
    # This attribute is designed for instance method: `can_handle_language`.
    # Default value is None which means it can handle all languages.
    # This is an important feature for backwards compatibility of components.
    supported_language_list = None

    # Defines what language(s) this component can NOT handle.
    # This attribute is designed for instance method: `can_handle_language`.
    # Default value is None which means it can handle all languages.
    # This is an important feature for backwards compatibility of components.
    not_supported_language_list = None

    def __init__(self, component_config: Optional[Dict[Text, Any]] = None) -> None:
        super().__init__(component_config)

    def train(
        self,
        training_data: TrainingData,
        config: Optional[RasaNLUModelConfig] = None,
        **kwargs: Any,
    ) -> None:
        """Train this component.

        This is the components chance to train itself provided
        with the training data. The component can rely on
        any context attribute to be present, that gets created
        by a call to :meth:`components.Component.pipeline_init`
        of ANY component and
        on any context attributes created by a call to
        :meth:`components.Component.train`
        of components previous to this one."""
        pass

    def process(self, message: Message, **kwargs: Any) -> None:
        """Process an incoming message.

        This is the components chance to process an incoming
        message. The component can rely on
        any context attribute to be present, that gets created
        by a call to :meth:`components.Component.pipeline_init`
        of ANY component and
        on any context attributes created by a call to
        :meth:`components.Component.process`
        of components previous to this one."""
        pass

    def persist(self, file_name: Text, model_dir: Text) -> Optional[Dict[Text, Any]]:
        """Persist this component to disk for future loading."""

        pass

    @classmethod
    def load(
        cls,
        meta: Dict[Text, Any],
        model_dir: Text,
        model_metadata: Optional["Metadata"] = None,
        cached_component: Optional["Component"] = None,
        **kwargs: Any,
    ) -> "Component":
        """Load this component from file."""

        if cached_component:
            return cached_component
        else:
            return cls(meta)

class MyTokenizer(Tokenizer):

    language_list = ["zh"]
    def __init__(self, component_config: Dict[Text, Any] = None) -> None:
        """Construct a new Tokenizer."""
        super().__init__(component_config)

    @classmethod
    def required_packages(cls) -> List[Text]:
        return []

    def tokenize(self, message: Message, attribute: Text) -> List[Token]:
        """Construct a new Tokenizer."""
        return tokens

policies:
 - name: "RulePolicy"
   core_fallback_threshold: 0.3    # 当 policies不能预测出下一个action时，回退的action
   core_fallback_action_name: action_default_fallback
   enable_fallback_prediction: true
   restrict_rules: true
   check_for_contradictions: true  # 训练前检查 slots和 active loops在rules中的一致性

policies:
 - name: "MemoizationPolicy"
   max_history: 7

policies: (自定义 policy)
 - name: "path.to.your.policy.class"
   arg1: "……"

class TEDPolicy(Policy): 
    def __init__(
        self,
        featurizer: Optional[TrackerFeaturizer] = None,
        priority: int = DEFAULT_POLICY_PRIORITY, 
        max_history: Optional[int] = None, 
        model: Optional[RasaModel] = None,
        fake_features: Optional[Dict[Text, List["Features"]]] = None, 
        ) -> None:

responses:
 utter_ask_type:
 - text: 请问您是咨询哪款机型？
 utter_greet:
 - text: 你好, {name}. 最近怎样?
 utter_cheer_up:
 - text: 这儿有一些有趣的照片。
   image: "https://i.imgur.com/nGF1K8f.jpg"

forms:
  type_form:  型号表单
    required_slots:
      car_type:
      - type: from_entity

rules: (激活表单)
 - rule: Activate form
   steps:
   - intent: request_car_type
   - action: type_form       # 开始运行表单
   - active_loop: car_form  # 激活表单

rules: 
 - rule: (停用并提交表单)
   condition:
   - active_loop: type_form    # 满足表单激活的状态
   steps:
   - action: type_form
   - active_loop: null             # 停用该表单
   - slot_was_set:
     - requested_slot: null        # 不再请求slot
   - action: utter_submit          # 提交表单
 - rule: (用户中途切换话题)
   condition:
   - active_loop: type_form
   steps:
   - intent: chitchat              # 用户中途开始闲聊
   - action: utter_chitchat         # 回应闲聊
   - action: type_form
   - active_loop: type_form

class Action:
  def name(self) -> Text:
    raise NotImplementedError("An action must implement a name")
  async def run(
    self,
    dispatcher: "CollectingDispatcher",
    tracker: Tracker,
    domain: "DomainDict", 
    ) -> List[Dict[Text, Any]]: 

rules:
 - rule: 当置信度低于阈值时，要求用户重新表述
   steps:
   - intent: nlu_fallback
   - action: utter_please_rephrase

rules:
 - rule: 只有当用户提供姓名后才回复问好
   condition:
   - slot_was_set:
     - user_provided_name: true
   steps:
   - intent: greet
   - action: utter_greet

? Next user input:  hello
? Is the NLU classification for 'hello' with intent 'hello' correct?  Yes
------
Chat History
 #    Bot                        You
────────────────────────────────────────────
 1    action_listen
────────────────────────────────────────────
 2                                    hello
                         intent: hello 1.00
------
? The bot wants to run 'utter_greet', correct?  (Y/n)