# From

**URL:** <https://forum.rasa.com/t/from/20672>\
**Category:** Rasa Open Source\
**Created:** [October 31, 2019, 1:38am UTC](https://forum.rasa.com/t/from/20672 "2019-10-31T01:38:20Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![m.khalilishoja](https://avatars.discourse-cdn.com/v4/letter/m/d2c977/32.png) [@m.khalilishoja](https://forum.rasa.com/u/m.khalilishoja)\
**Post date:** [October 31, 2019, 1:38am UTC](https://forum.rasa.com/t/from/20672/1 "2019-10-31T01:38:20Z")

</div>

Hi All, I would like to test ‘formbot’ example in Jupyter Notebook provided by RASA in the following link;

> **[GitHub - RasaHQ/rasa-workshop-pydata-dc: This repository contains the code of...](https://github.com/RasaHQ/rasa-workshop-pydata-dc)**
>
> This repository contains the code of the Rasa workshop at PyData DC 2018 - GitHub - RasaHQ/rasa-workshop-pydata-dc: This repository contains the code of the Rasa workshop at PyData DC 2018

When I run the cell related to “Training your Dialogue Model”, I got an error. The cell is

```auto
from rasa_core.policies import KerasPolicy, MemoizationPolicy
from rasa_core.agent import Agent
# there is a threshold for the NLU predictions as well as the action predictions
agent = Agent('domain.yml', policies=[MemoizationPolicy(), KerasPolicy()])

# loading our neatly defined training dialogues
training_data = agent.load_data('stories.md')

agent.train(
    training_data,
    validation_split=0.0,
    epochs=10
)

agent.persist('models/dialogue')

```

and the error is ;

TypeError: **init** () got an unexpected keyword argument ‘auto\_fill’

I think I have to add FormPolicy in this snippet somewhere but I dont know. Could you please help me to fix it?

---

<div class="post-metadata">

**Author:** ![JiteshGaikwad](https://avatars.discourse-cdn.com/v4/letter/j/77aa72/32.png) [@JiteshGaikwad](https://forum.rasa.com/u/JiteshGaikwad)\
**Post date:** [October 31, 2019, 3:30am UTC](https://forum.rasa.com/t/from/20672/2 "2019-10-31T03:30:51Z")

</div>

hey @m.khalilishoja, the code you are trying to run is for the older version of rasa. check this out, it may help you:

> **[Jupyter Notebooks](https://rasa.com/docs/rasa/jupyter-notebooks/)**
>
> Learn how to integrate open source chatbot platform Rasa into Jupyter notebooks, alongside all your machine learning code.

---

<div class="post-metadata">

**Author:** ![m.khalilishoja](https://avatars.discourse-cdn.com/v4/letter/m/d2c977/32.png) [@m.khalilishoja](https://forum.rasa.com/u/m.khalilishoja)\
**Post date:** [October 31, 2019, 5:22am UTC](https://forum.rasa.com/t/from/20672/3 "2019-10-31T05:22:52Z")

</div>

Thanks @JiteshGaikwad, let me test it.

---

<div class="post-metadata">

**Author:** ![m.khalilishoja](https://avatars.discourse-cdn.com/v4/letter/m/d2c977/32.png) [@m.khalilishoja](https://forum.rasa.com/u/m.khalilishoja)\
**Post date:** [October 31, 2019, 6:13pm UTC](https://forum.rasa.com/t/from/20672/4 "2019-10-31T18:13:22Z")

</div>

Hi @JiteshGaikwad,

I got this error

```auto
ERROR:rasa.core.actions.action:The model predicted the custom action 'restaurant_form', but you didn't configure an endpoint to run this custom action. Please take a look at the docs and set an endpoint configuration via the --endpoints flag. https://rasa.com/docs/rasa/core/actions
ERROR:rasa.core.processor:Encountered an exception while running action 'restaurant_form'. Bot will continue, but the actions events are lost. Please check the logs of your action server for more information.

```

when I ran the

```auto
from rasa.jupyter import chat
chat(model_path)

```

and entered the following message;

```auto
id like a restaurant

```

---

<div class="post-metadata">

**Author:** ![JiteshGaikwad](https://avatars.discourse-cdn.com/v4/letter/j/77aa72/32.png) [@JiteshGaikwad](https://forum.rasa.com/u/JiteshGaikwad)\
**Post date:** [November 1, 2019, 2:44am UTC](https://forum.rasa.com/t/from/20672/5 "2019-11-01T02:44:09Z")

</div>

Hey @m.khalilishoja, make sure you have mentioned the Rasa actions endpoint in endpoints.yml file and your custom action server is running