## [Deprecated] Rasa X Community Edition  
May 22, 2019  
You are right, I commented it out and I am still getting a 404 error in the browser visiting the url that is spits out.  
The server is running at [http://localhost:5002/login?username=me&password=ekpKs7OPGNa4](http://localhost:5002/login?username=me&password=ekpKs7OPGNa4)

## [Deprecated] Rasa X Community Edition  
May 21, 2019  
Running Rasa X inside of the moodbot example gives me this stacktrace.  
Process SpawnProcess-1:  
Traceback (most recent call last):  
File "/usr/local/Cellar/python/3.6.5_1/Frameworks/Python.framework/Versions/3.6/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap  
self.run()  
Fil…

## One Conversation Multiple Agents and Routing  
January 16, 2019  
Let me know if this helps you.

## Specify ONE response per intent  
January 15, 2019  
When the bot gets an intent, it runs it through the model and the model returns the action or utter that it predicted. There are a list of actions and utters that it takes into consideration when it makes that prediction.  
Is there a way, outside of a lot of training examples and using the memoization...

## How to switch between models in rasa core  
January 8, 2019  
You can create different agents and specify which agent you want to send it to, but you need to create your own server and load a different agent per route.  
```  
http://localhost:5003/parse?q=hi&agent=resturant&version=1  
http://localhost:5003/parse?q=hi&agent=resturant&version=2  
```

## Embedding Policy Results  
January 7, 2019  
That is exactly what I have already, could I see what the output would look like?

## What is the best method for entity extraction for names?  
January 6, 2019  
I would like to get the name from a user. For example, “Hello my name is Adrian.” or just “Adrian”. What is the best way to extract this entity?  
For example, should I just add a lot more training examples, or is there a custom pipeline that helps extract names?

## Checkpoint Example  
December 10, 2018  
Could someone please provide me with an example of how to use checkpoints?  
I am confused as to where we define the actual checkpoint. For example in:  
```  
## first story  
hello  
action_ask_user_question  
check_asked_question  
```

## Where is the best place to store models in Kubernates Cluster  
December 5, 2018  
Seems like the method load_from_server will do the job. Looks like I can create my own endpoint that will return a gzipped directory of the model. And this returns the agent with that loaded model.

## FormAction Stuck in Loop  
September 17, 2018  
This is the story that breaks the form action. If however the last action is like  
```  
* inform  
- action_personal_loan_form  
- slot{"caller_ssn": "13434"}  
- slot{"application_finished": true}  
- utter_form_complete  
```

## Getting error during Action implementation  
September 11, 2018  
You must add 'action_purchase" to you domain file under actions:  
Then you must retrain the dialogue model and you should be good to go.

## Multiple agents on the rasa core  
September 11, 2018  
Yes, create your own server, and load different agents from different directories. Then create a custom tracker store. You can look at these on the github:  
[https://github.com/RasaHQ/rasa_core/blob/master/rasa_core/tracker_store.py](https://github.com/RasaHQ/rasa_core/blob/master/rasa_core/tracker_store.py)

## Importing FormAction from Rasa Core sdk throws an error  
importing FormAction from Rasa Core sdk throws an error.  
```  
from rasa_core_sdk.forms import FormAction  
```  
Gives me the error stack of:  
Traceback (most recent call last):  
"..."

## Rasa_core run doesn't take --interactive argument  
September 9, 2018  
So first you need to have a trained dialogue model and a trained nlu model. This runs the rasa_core run script. It passes it the online flag. The -d is the path to your domain file...

## Trackers are Different in Rasa Core SDK  
September 9, 2018  
The answer was to save the tracker after updating it.

## One Conversation Multiple Agents and Routing  
August 30, 2018  
So in theory I could do this. Create a tracker with a sender_id. Save that tracker in the database. Create two agents. Instantiate those two agents with the same tracker...