# Understanding rasa stories format

**URL:** <https://forum.rasa.com/t/understanding-rasa-stories-format/55054>\
**Category:** Rasa Open Source\
**Created:** [August 29, 2022, 11:35am UTC](https://forum.rasa.com/t/understanding-rasa-stories-format/55054 "2022-08-29T11:35:37Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Rafal](https://avatars.discourse-cdn.com/v4/letter/r/ac91a4/32.png) [@Rafal](https://forum.rasa.com/u/Rafal)\
**Post date:** [August 29, 2022, 11:35am UTC](https://forum.rasa.com/t/understanding-rasa-stories-format/55054/1 "2022-08-29T11:35:37Z")

</div>

In the [documentation](https://rasa.com/docs/rasa/stories/) we have the following example

```auto
stories:
- story: collect restaurant booking info # name of the story - just for debugging
  steps:
  - intent: greet # user message with no entities
  - action: utter_ask_howcanhelp
  - intent: inform # user message with entities
    entities:
    - location: "rome"
    - price: "cheap"
  - action: utter_on_it # action that the bot should execute
  - action: utter_ask_cuisine
  - intent: inform
    entities:
    - cuisine: "spanish"
  - action: utter_ask_num_people

```

My question is simple. Does “rome”, “cheap” and “spanish” - the values for the entities ‘location’ ‘price’ and ‘cuisine’ written in the file `stories.yml` during training are added to the training examples from the `nlu.yml` file as new lines in format `- <value>` at the end of the list of examples:

```auto
foo/nlu.yml

version: "3.1"
nlu:
-intent: "inform"
  examples: |
    - [bar](cuisine)
    - [xyz](price)
# added:
    - [rome](location)
    - [cheap](price)
    - [spanish](location)
    .....

```

OR are matched as regexes during predictions and are not used for training?

I can’t find any meaningful explanation for that in the docks.

Cheers

---

<div class="post-metadata">

**Author:** ![stephens](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/stephens/32/1632_2.png) [@stephens](https://forum.rasa.com/u/stephens)\
**Post date:** [August 31, 2022, 11:39pm UTC](https://forum.rasa.com/t/understanding-rasa-stories-format/55054/2 "2022-08-31T23:39:44Z")

</div>

> … added … to the `nlu.yml` file as new lines

No

> are matched as regexes

Not unless you’ve added them in a lookup table or regex

---

<div class="post-metadata">

**Author:** ![Rafal](https://avatars.discourse-cdn.com/v4/letter/r/ac91a4/32.png) [@Rafal](https://forum.rasa.com/u/Rafal)\
**Post date:** [September 1, 2022, 10:14am UTC](https://forum.rasa.com/t/understanding-rasa-stories-format/55054/3 "2022-09-01T10:14:45Z")

</div>

So why do we write it if they are not doing anything?

---

<div class="post-metadata">

**Author:** ![stephens](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/stephens/32/1632_2.png) [@stephens](https://forum.rasa.com/u/stephens)\
**Post date:** [September 1, 2022, 5:54pm UTC](https://forum.rasa.com/t/understanding-rasa-stories-format/55054/4 "2022-09-01T17:54:36Z")

</div>

stories & rules control the dialog, the nlu.yml is input to the nlu intent and entity recognition. Two separate functions.