智能交互助手 - 运行篇

启动

在上述所有都训练完成后，需要启动的内容包括：

bert classifier (通过bert-as-service)，这个可以用macanv重新封装过的
bert ner(通过bert-as-service)，这个也是用macanv的
rasa actions，用来处理自定义动作
rasa ，这个是所有处理的入口，rasa本身提供http的接口

官方的介绍是这样的：

rasa http

Rasa启动后的提示，包括了可以调用的各个HTTP请求

/conversations/<conversation_id>/messages          POST                           add_message
/conversations/<conversation_id>/tracker/events    POST                           append_events
/webhooks/rest                                     GET                            custom_webhook_RestInput.health
/webhooks/rest/webhook                             POST                           custom_webhook_RestInput.receive
/model/test/intents                                POST                           evaluate_intents
/model/test/stories                                POST                           evaluate_stories
/conversations/<conversation_id>/execute           POST                           execute_action
/domain                                            GET                            get_domain
/                                                  GET                            hello
/model                                             PUT                            load_model
/model/parse                                       POST                           parse
/conversations/<conversation_id>/predict           POST                           predict
/conversations/<conversation_id>/tracker/events    PUT                            replace_events
/conversations/<conversation_id>/story             GET                            retrieve_story
/conversations/<conversation_id>/tracker           GET                            retrieve_tracker
/status                                            GET                            status
/model/predict                                     POST                           tracker_predict
/model/train                                       POST                           train
/conversations/<conversation_id>/trigger_intent    POST                           trigger_intent
/model                                             DELETE                         unload_model
/version                                           GET                            version

我们主要用到的入口就是/webhooks/rest/webhook，默认的端口是5005

HTTP请求的调用格式：

headers = {'Content-Type':'application/json'}
payload = {
   "sender": "whatisyourname",
   "message": "whateveryouwanttosendtoyourrobot"
}
resp = >requests.post(url='http://localhost:5005/webhooks/rest/webhook',json=payload,headers=headers)