image

Tracker和Event

在Rasa Core中Tracker負(fù)責(zé)記錄整個對話的流程较沪，而Tracker中數(shù)據(jù)的新增鳞绕、編輯和刪除是通過Event進(jìn)行管理的。

Policy

Policy是負(fù)責(zé)決策Action的調(diào)用在Tracker的狀態(tài)發(fā)生變更之后尸曼，Policy來決定下一步的Action们何。

Action

Action是對用戶輸入的一種回應(yīng):

Actions are the things your bot runs in response to user input. There are three kinds of actions in Rasa Core:

1. default actions (action_listen, action_restart, action_default_fallback)
2. utter actions, starting with utter_, which just sends a message to the user.
3. custom actions - any other action, these actions can run arbitrary code

Action的自定義比較簡單，只需要繼承Action并提供對應(yīng)方法即可骡苞。普通的Action是通過run方法來實現(xiàn)功能垂蜗，例如講一個笑話：

from rasa_core_sdk import Action

class ActionJoke(Action):
    def name(self):
        # define the name of the action which can then be included in training stories
        return "action_joke"

    def run(self, dispatcher, tracker, domain):
        # what your action should do
        request = requests.get('http://api.icndb.com/jokes/random').json() #make an apie call
        joke = request['value']['joke'] #extract a joke from returned json response
        dispatcher.utter_message(joke) #send the message back to the user
        return []

另一種常用的Action是FromAction楷扬，這種Action會進(jìn)行表單校驗，要求用戶提供指定的slots：

class UserInfoForm(FormAction):
   """Example of a custom form action"""

   def name(self):
       # type: () -> Text
       """Unique identifier of the form"""

       return "userinfo_form"

   @staticmethod
   def required_slots(tracker):
       # type: () -> List[Text]
       """A list of required slots that the form has to fill"""

       return ["user_name"]

   def submit(self, dispatcher, tracker, domain):
       # type: (CollectingDispatcher, Tracker, Dict[Text, Any]) -> List[Dict]
       """Define what the form has to do
           after all required slots are filled"""

       # utter submit template
       # dispatcher.utter_template('utter_info_basic', tracker)
       response = {
               "intent": "user_info_basic",
               "slots":[
                   tracker.get_slot("user_name")
                   ]
               }
       dispatcher.utter_message(json.dumps(response))
       # dispatcher.utter_attachment(*elements)
       return []

在Action定義完成后需要在domain中添加贴见，并且需要ActionServer來調(diào)用這些Action提供服務(wù)烘苹。

Agent

Agent將Rasa Core的功能通過API開放出來，像模型訓(xùn)練片部，對話處理等都可以通過Agent完成镣衡，一個模型訓(xùn)練的例子：

import sys
from rasa_core.policies.keras_policy import KerasPolicy
from rasa_core.agent import Agent

if len(sys.argv) < 3:
    print("請指定數(shù)據(jù)路徑和模型的存儲名稱")
    exit()

domain = "{}/domain.yml".format(sys.argv[1])
stories = "{}/data/stories.md".format(sys.argv[1])
dialogue = "{}/models/{}".format(sys.argv[1], sys.argv[2])

agent = Agent(domain, policies=[KerasPolicy(validation_split=0.0,epochs=400)])
training_data = agent.load_data(stories)
agent.train(training_data)
agent.persist(dialogue)

Agent可以作為Rasa Core服務(wù)的入口，通過Agent來訪問Rasa Core提供的功能档悠。