How can I get the body of request on rasa

I have the same trouble. but how, can you help me?

Can I get my messages in my action

There are some messages in my request from SocketIOInput.handle_message such as user name, message, username, userid. But how to translate to action. Because I need the message to do some of my job. That all, thank you.

Cluster deployment Rasa, but something I can't understand

我用redis 单机，我遇到的问题是集群模式下某台宕机重连有点长，不过不是这个框架问题就是了

This is my deploy photo. Client uses rasa-voice-interface with socket.io to connect to nginx. Then nginx proxies to nlu cluster, finally nlu connects to action cluster.
Main nginx conf is:

upstream nlu {
    hash $remote_addr consistent;
    server 127.0.0.1:5005;
    server 192.168.254.18:5005;
}

Introduce yourself!

I am wupj from China. A common programmer. But I am not an AI worker. So I think I will have more trouble in using Rasa. My company wants to use something framework like Rasa. In my country, companies like Baidu or Alibaba have something frameworks similar to Rasa but need much money. So I suggested my boss try to use Rasa.

It is too slow to reply when I run in local PC

Ok no problem, I will send my project to you in my free time. If there are something wrong or unreasonable please help me point out. It’s my 'hello world’ with Rasa. Thank you very much.

I have my actions but I print the time and it only costs less than 0.5s.

Thank you for your answer. My Rasa version is 1.1.8 and my model (core+nlu) only 2.1M.

Object of type 'MaxHistoryTrackerFeaturizer' is not JSON serializable

I have the same question. Are you able to solve the problem now?

This is my first question; maybe I don’t say it good, but it will be better. OK now I will say my question. When I run my project on my notebook computer (CPU I7 8750H, GTX 1060, RAM 32G), if the answer needs to predict it will be slow in action. I found the same question