学习笔记（10）- 智能会话框架rasa

https://rasa.com/

阿里用过这个，贝壳也在用这个。

• 优点：

1. 有中文版本（https://github.com/crownpku/rasa_nlu_chi）；
2. 2018年发布，文档多，业界应用多；
3. 使用简单，pipline方式定义会话流程，“讲故事”stories.md
4. 有数据标注工具rasa_nlu_trainer；
5. 可以使用语义理解word2vec；
6. 部署简单，支持docker；

• 缺点：
  端到端的实现较弱；

创建一个虚拟环境，然后这两句话就可以创建智能会话的工程

python3 -m venv env
source env/bin/activate
pip install rasa-x --extra-index-url https://pypi.rasa.com/simple
rasa init

使用的命令：

$ rasa 
usage: rasa [-h] [--version]
            {init,run,shell,train,interactive,test,visualize,data,x} ...

Rasa command line interface. Rasa allows you to build your own conversational
assistants 🤖. The 'rasa' command allows you to easily run most common commands
like creating a new bot, training or evaluating models.

positional arguments:
  {init,run,shell,train,interactive,test,visualize,data,x}
                        Rasa commands
    init                Creates a new project, with example training data,
                        actions, and config files.
    run                 Starts a Rasa server with your trained model.
    shell               Loads your trained model and lets you talk to your
                        assistant on the command line.
    train               Trains a Rasa model using your NLU data and stories.
    interactive         Starts an interactive learning session to create new
                        training data for a Rasa model by chatting.
    test                Tests Rasa models using your test NLU data and
                        stories.
    visualize           Visualize stories.
    data                Utils for the Rasa training files.

组成部分：

基本流程：

目录结构是这样的：

自然语言理解NLU

多轮会话(控制器)

交互图