## Overview Rasa uses [YAML](https://yaml.org/spec/1.2/spec.html) as a unified and extendable way to manage all training data, including NLU data, stories and rules. You can split the training data over any number of YAML files, and each file can contain any combination of NLU data, stories, and rules. The training data parser determines the training data type using top level keys. The [domain](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#domain) uses the same YAML format as the training data and can also be split across multiple files or combined in one file. The domain includes the definitions for [responses](https://legacy-docs-oss.rasa.com/docs/rasa/next/responses) and [forms](https://legacy-docs-oss.rasa.com/docs/rasa/next/forms). See the [documentation for the domain](https://legacy-docs-oss.rasa.com/docs/rasa/next/domain) for information on how to format your domain file. ##### Legacy Formats Looking for Markdown data format? It's removed in Rasa 3.0, but you can still find the documentation for [markdown NLU data](https://legacy-docs-v1.rasa.com/nlu/training-data-format/) and [markdown stories](https://legacy-docs-v1.rasa.com/core/stories/). If you still have your training data in Markdown format then the recommended approach is to use Rasa 2.x to convert your data from Markdown to YAML. [The migration guide](https://legacy-docs-oss.rasa.com/docs/rasa/next/migration-guide#training-data-files) explains how to do this. ### High-Level Structure Each file can contain one or more **keys** with corresponding training data. One file can contain multiple keys, but each key can only appear once in a single file. The available keys are: - `version` - `nlu` - `stories` - `rules` You should specify the `version` key in all YAML training data files. If you don't specify a version key in your training data file, Rasa will assume you are using the latest training data format specification supported by the version of Rasa you have installed. Training data files with a Rasa version greater than the version you have installed on your machine will be skipped. Currently, the latest training data format specification for Rasa 3.x is 3.1. ### Example Here's a short example which keeps all training data in a single file: ```yaml version: "3.1" nlu: - intent: greet examples: | - Hey - Hi - hey there [Sara](name) - intent: faq/language examples: | - What language do you speak? - Do you only handle english? stories: - story: greet and faq steps: - intent: greet - action: utter_greet - intent: faq - action: utter_faq rules: - rule: Greet user steps: - intent: greet - action: utter_greet ``` To specify your test stories, you need to put them into a separate file: ``` tests/test_stories.yml ``` ```yaml stories: - story: greet and ask language steps: - user: | hey intent: greet - action: utter_greet - user: | what language do you speak intent: faq/language - action: utter_faq ``` [Test stories](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#test-stories) use the same format as the story training data and should be placed in a separate file with the prefix `test_`. ##### The `|` symbol As shown in the above examples, the `user` and `examples` keys are followed by `|` (pipe) symbol. In YAML `|` identifies multi-line strings with preserved indentation. This helps to keep special symbols like `"`, `'` and others still available in the training examples. ## NLU Training Data [NLU](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#nlu) training data consists of example user utterances categorized by [intent](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#intent). Training examples can also include [entities](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#entity). Entities are structured pieces of information that can be extracted from a user's message. You can also add extra information such as regular expressions and lookup tables to your training data to help the model identify intents and entities correctly. NLU training data is defined under the `nlu` key. Items that can be added under this key are: - [Training examples](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#training-examples) grouped by user intent e.g. optionally with annotated [entities](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#entities) ```yaml nlu: - intent: check_balance examples: | - What's my [credit](account) balance? - What's the balance on my [credit card account]{"entity":"account","value":"credit"} ``` - [Synonyms](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#synonyms) ```yaml nlu: - synonym: credit examples: | - credit card account - credit account ``` - [Regular expressions](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#regular-expressions) ```yaml nlu: - regex: account_number examples: | - \d{10,12} ``` - [Lookup tables](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#lookup-tables) ```yaml nlu: - lookup: banks examples: | - JPMC - Comerica - Bank of America ``` ### Training Examples Training examples are grouped by [intent](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#intent) and listed under the `examples` key. Usually, you'll list one example per line as follows: ```yaml nlu: - intent: greet examples: | - hey - hi - whats up ``` However, it's also possible to use an extended format if you have a custom NLU component and need metadata for your examples: ```yaml nlu: - intent: greet examples: - text: | hi metadata: sentiment: neutral - text: | hey there! ``` The `metadata` key can contain arbitrary key-value data that is tied to an example and accessible by the components in the NLU pipeline. In the example above, the sentiment metadata could be used by a custom component in the pipeline for sentiment analysis. You can also specify this metadata at the intent level: ```yaml nlu: - intent: greet metadata: sentiment: neutral examples: - text: | hi - text: | hey there! ``` In this case, the content of the `metadata` key is passed to every intent example. If you want to specify [retrieval intents](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#retrieval-intent), then your NLU examples will look as follows: ```yaml nlu: - intent: chitchat/ask_name examples: | - What is your name? - May I know your name? - What do people call you? - Do you have a name for yourself? - intent: chitchat/ask_weather examples: | - What's the weather like today? - Does it look sunny outside today? - Oh, do you mind checking the weather for me please? - I like sunny days in Berlin. ``` All retrieval intents have a suffix added to them which identifies a particular response key for your assistant. In the above example, `ask_name` and `ask_weather` are the suffixes. The suffix is separated from the retrieval intent name by a `/` delimiter. ##### Special meaning of `/` As shown in the above examples, the `/` symbol is reserved as a delimiter to separate retrieval intents from their associated response keys. Make sure not to use it in the name of your intents. ### Entities [Entities](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#entity) are structured pieces of information that can be extracted from a user's message. Entities are annotated in training examples with the entity's name. In addition to the entity name, you can annotate an entity with [synonyms](https://legacy-docs-oss.rasa.com/docs/rasa/next/nlu-training-data#synonyms), [roles, or groups](https://legacy-docs-oss.rasa.com/docs/rasa/next/nlu-training-data#entities-roles-and-groups). In training examples, entity annotation would look like this: ```yaml nlu: - intent: check_balance examples: | - how much do I have on my [savings](account) account - how much money is in my [checking]{"entity": "account"} account - What's the balance on my [credit card account]{"entity":"account","value":"credit"} ``` The full possible syntax for annotating an entity is: ```text []{"entity": "", "role": "", "group": "", "value": ""} ``` The keywords `role`, `group`, and `value` are optional in this notation. The `value` field refers to synonyms. To understand what the labels `role` and `group` are for, see the section on [entity roles and groups](https://legacy-docs-oss.rasa.com/docs/rasa/next/nlu-training-data#entities-roles-and-groups). ### Synonyms Synonyms normalize your training data by mapping an extracted entity to a value other than the literal text extracted. You can define synonyms using the format: ```yaml nlu: - synonym: credit examples: | - credit card account - credit account ``` You can also define synonyms in-line in your training examples by specifying the `value` of the entity: ```yaml nlu: - intent: check_balance examples: | - how much do I have on my [credit card account]{"entity": "account", "value": "credit"} - how much do I owe on my [credit account]{"entity": "account", "value": "credit"} ``` Read more about synonyms on the [NLU Training Data page](https://legacy-docs-oss.rasa.com/docs/rasa/next/nlu-training-data#synonyms). ### Regular Expressions You can use regular expressions to improve intent classification and entity extraction using the [`RegexFeaturizer`](https://legacy-docs-oss.rasa.com/docs/rasa/next/components#regexfeaturizer) and [`RegexEntityExtractor`](https://legacy-docs-oss.rasa.com/docs/rasa/next/components#regexentityextractor) components. The format for defining a regular expression is as follows: ```yaml nlu: - regex: account_number examples: | - \d{10,12} ``` Here `account_number` is the name of the regular expression. When used as features for the `RegexFeaturizer` the name of the regular expression does not matter. When using the `RegexEntityExtractor`, the name of the regular expression should match the name of the entity you want to extract. Read more about when and how to use regular expressions with each component on the [NLU Training Data page](https://legacy-docs-oss.rasa.com/docs/rasa/next/nlu-training-data#regular-expressions). ### Lookup Tables Lookup tables are lists of words used to generate case-insensitive regular expression patterns. The format is as follows: ```yaml nlu: - lookup: banks examples: | - JPMC - Bank of America ``` When you supply a lookup table in your training data, the contents of that table are combined into one large regular expression. This regex is used to check each training example to see if it contains matches for entries in the lookup table. Lookup table regexes are processed identically to the regular expressions directly specified in the training data and can be used either with the [RegexFeaturizer](https://legacy-docs-oss.rasa.com/docs/rasa/next/components#regexfeaturizer) or with the [RegexEntityExtractor](https://legacy-docs-oss.rasa.com/docs/rasa/next/components#regexentityextractor). The name of the lookup table is subject to the same constraints as the name of a regex feature. Read more about using lookup tables on the [NLU Training Data page](https://legacy-docs-oss.rasa.com/docs/rasa/next/nlu-training-data#lookup-tables). ## Conversation Training Data Stories and rules are both representations of conversations between a user and a conversational assistant. They are used to train the dialogue management model. [Stories](https://legacy-docs-oss.rasa.com/docs/rasa/next/stories) are used to train a machine learning model to identify patterns in conversations and generalize to unseen conversation paths. [Rules](https://legacy-docs-oss.rasa.com/docs/rasa/next/rules) describe small pieces of conversations that should always follow the same path and are used to train the [RulePolicy](https://legacy-docs-oss.rasa.com/docs/rasa/next/policies#rule-policy). ### Stories Stories are composed of: - `story`: The story's name. The name is arbitrary and not used in training; you can use it as a human-readable reference for the story. - `metadata`: arbitrary and optional, not used in training, you can use it to store relevant information about the story like e.g. the author - a list of `steps`: The user messages and actions that make up the story For example: ```yaml stories: - story: Greet the user metadata: author: Somebody key: value steps: - intent: greet - action: utter_greet ``` Each step can be one of the following: - A [user message](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#user-messages), represented by **intent** and **entities**. - An [or statement](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#or-statement), which includes two or more user messages under it. - A bot [action](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#actions). - A [form](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#forms). - A [slot was set](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#slots) event. - A [checkpoint](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#checkpoints), which connects the story to another story. #### User Messages All user messages are specified with the `intent:` key and an optional `entities:` key. While writing stories, you do not have to deal with the specific contents of the messages that the users send. Instead, you can take advantage of the output from the NLU pipeline, which uses a combination of an intent and entities to refer to all possible messages the users can send with the same meaning. User messages follow the format: ```yaml stories: - story: user message structure steps: - intent: intent_name # Required entities: # Optional - entity_name: entity_value - action: action_name ``` For example, to represent the sentence `I want to check my credit balance`, where `credit` is an entity: ```yaml stories: - story: story with entities steps: - intent: account_balance entities: - account_type: credit - action: action_credit_account_balance ``` It is important to include the entities here as well because the policies learn to predict the next action based on a _combination_ of both the intent and entities (you can, however, change this behavior using the [`use_entities`](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#entities) attribute). #### Actions All actions executed by the bot are specified with the `action:` key followed by the name of the action. While writing stories, you will encounter two types of actions: 1. [Responses](https://legacy-docs-oss.rasa.com/docs/rasa/next/domain#responses): start with `utter_` and send a specific message to the user. e.g. ```yaml stories: - story: story with a response steps: - intent: greet - action: utter_greet ``` 2. [Custom actions](https://legacy-docs-oss.rasa.com/docs/rasa/next/custom-actions): start with `action_`, run arbitrary code and send any number of messages (or none). ```yaml stories: - story: story with a custom action steps: - intent: feedback - action: action_store_feedback ``` #### Forms A [form](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#form) is a specific kind of custom action that contains the logic to loop over a set of required slots and ask the user for this information. You [define a form](https://legacy-docs-oss.rasa.com/docs/rasa/next/forms#defining-a-form) in the `forms` section in your domain. Once defined, you should specify the [happy path](https://legacy-docs-oss.rasa.com/docs/rasa/next/glossary#happy--unhappy-paths) for a form as a [rule](https://legacy-docs-oss.rasa.com/docs/rasa/next/forms). You should include interruptions of forms or other "unhappy paths" in stories so that the model can generalize to unseen conversation sequences. As a step in a story, a form takes the following format: ```yaml stories: - story: story with a form steps: - intent: find_restaurant - action: restaurant_form # Activate the form - active_loop: restaurant_form # This form is currently active - active_loop: null # Form complete, no form is active - action: utter_restaurant_found ``` The `action` step activates the form and begins looping over the required slots. The `active_loop: restaurant_form` step indicates that there is a currently active form. Much like a `slot_was_set` step, a `form` step doesn't **set** a form to active but indicates that it should already be activated. In the same way, the `active_loop: null` step indicates that no form should be active before the subsequent steps are taken. A form can be interrupted and remain active; in this case the interruption should come after the `action:
` step and be followed by the `active_loop: ` step. An interruption of a form could look like this: ```yaml stories: - story: interrupted food steps: - intent: request_restaurant - action: restaurant_form - intent: chitchat - action: utter_chitchat - active_loop: restaurant_form - active_loop: null - action: utter_slots_values ``` #### Slots A slot event is specified under the key `slot_was_set:` with the slot name and optionally the slot's value. **[Slots](https://legacy-docs-oss.rasa.com/docs/rasa/next/domain#slots)** act as the bots memory. Slots are **set** by either the default action [`action_extract_slots`](https://legacy-docs-oss.rasa.com/docs/rasa/next/default-actions#action_extract_slots) according to the [slot mappings](https://legacy-docs-oss.rasa.com/docs/rasa/next/domain#slot-mappings) specified in the domain, or by custom actions. They are **referenced** by stories in `slot_was_set` steps. For example: ```yaml stories: - story: story with a slot steps: - intent: celebrate_bot - slot_was_set: feedback_value: positive - action: utter_yay ``` This means the story requires that the current value for the `feedback_value` slot be `positive` for the conversation to continue as specified. Whether or not you need to include the slot's value depends on the [slot type](https://legacy-docs-oss.rasa.com/docs/rasa/next/domain#slot-types) and whether the value can or should influence the dialogue. If the value doesn't matter, as is the case for e.g. `text` slots, you can list only the slot's name: ```yaml stories: - story: story with a slot steps: - intent: greet - slot_was_set: - name - action: utter_greet_user_by_name ``` The initial value for any slot by default is `null`, and you can use it to check if the slot was not set: ```yaml stories: - story: French cuisine steps: - intent: inform - slot_was_set: - cuisine: null ``` ##### How slots work Stories do not **set** slots. The slot must be set by the default action `action_extract_slots` if a slot mapping applies, or custom action **before** the `slot_was_set` step. #### Checkpoints Checkpoints are specified with the `checkpoint:` key, either at the beginning or the end of a story. Checkpoints are ways to connect stories together. They can be either the first or the last step in a story. If they are the last step in a story, that story will be connected to each other story that starts with the checkpoint of the same name when the model is trained. Here is an example of a story that ends with a checkpoint, and one that starts with the same checkpoint: ```yaml stories: - story: story_with_a_checkpoint_1 steps: - intent: greet - action: utter_greet - checkpoint: greet_checkpoint - story: story_with_a_checkpoint_2 steps: - checkpoint: greet_checkpoint - intent: book_flight - action: action_book_flight ``` Checkpoints at the beginning of stories can also be conditional on slots being set, for example: ```yaml stories: - story: story_with_a_conditional_checkpoint steps: - checkpoint: greet_checkpoint # This checkpoint should only apply if slots are set to the specified value slot_was_set: - context_scenario: holiday - holiday_name: thanksgiving - intent: greet - action: utter_greet_thanksgiving ``` Checkpoints can help simplify your training data and reduce redundancy in it, but **do not overuse them**. Using lots of checkpoints can quickly make your stories hard to understand. It makes sense to use them if a sequence of steps is repeated often in different stories, but stories without checkpoints are easier to read and write. #### OR statement `or` steps are ways to handle multiple intents or slot events the same way, without writing a separate story for each intent. For example, if you ask the user to confirm something, you might want to treat the `affirm` and `thankyou` intents in the same way. Stories with `or` steps will be converted into multiple separate stories at training time. For example, the following story would be converted to two stories at training time: ```yaml stories: - story: story with OR steps: - intent: signup_newsletter - action: utter_ask_confirm - or: - intent: affirm - intent: thanks - action: action_signup_newsletter ``` You can also use `or` statements with slot events. The following means the story requires that the current value for the `name` slot is set and is either `joe` or `bob`. This story would be converted to two stories at training time. ```yaml stories: - story: steps: - intent: greet - action: utter_greet - intent: tell_name - or: - slot_was_set: name: joe - slot_was_set: name: bob # ... next actions ``` Just like checkpoints, OR statements can be useful, but if you are using a lot of them, it is probably better to restructure your domain and/or intents. ##### Don't overuse Overusing these features (both checkpoints and OR statements) will slow down training. ### Rules Rules are listed under the `rules` key and look similar to stories. A rule also has a `steps` key, which contains a list of the same steps as stories do. Rules can additionally contain the `conversation_started` and `conditions` keys. These are used to specify conditions under which the rule should apply. A rule that with a condition looks like this: ```yaml rules: - rule: Only say `hey` when the user provided a name condition: slot_was_set: user_provided_name: true steps: - intent: greet - action: utter_greet ``` For more information about writing rules, see [Rules](https://legacy-docs-oss.rasa.com/docs/rasa/next/rules#writing-a-rule). ## Test Stories Test stories check if a message is classified correctly as well as the action predictions. Test stories use the same format as [stories](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format/#stories), except that user message steps can include a `user` to specify the actual text and entity annotations of the user message. Here's an example of a test story: ```yaml stories: - story: A basic end-to-end test steps: - user: | hey intent: greet - action: utter_ask_howcanhelp - user: | show me [chinese]{"entity": "cuisine"} restaurants intent: inform - action: utter_ask_location - user: | in [Paris]{"entity": "location"} intent: inform - action: utter_ask_price ``` You can run the tests using the following command: ``` rasa test ``` If you want to know more about testing head over to [Testing Your Assistant](https://legacy-docs-oss.rasa.com/docs/rasa/next/testing-your-assistant). ## End-to-end Training ##### New in 2.2 End-to-end training is an experimental feature. We introduce experimental features to get feedback from our community, so we encourage you to try it out! However, the functionality might be changed or removed in the future. If you have feedback (positive or negative) please share it with us on the [Rasa Forum](https://forum.rasa.com/). With [end-to-end training](https://legacy-docs-oss.rasa.com/docs/rasa/next/stories#end-to-end-training), you do not have to deal with the specific intents of the messages that are extracted by the NLU pipeline. Instead, you can put the text of the user message directly in the stories, by using `user` key. These end-to-end user messages follow the format: ```yaml stories: - story: user message structure steps: - user: the actual text of the user message - action: action_name ``` In addition, you can add entity tags that can be extracted by the [TED Policy](https://legacy-docs-oss.rasa.com/docs/rasa/next/policies#ted-policy). The syntax for entity tags is the same as in [the NLU training data](https://legacy-docs-oss.rasa.com/docs/rasa/next/training-data-format#entities). For example, the following story contains the user utterance ` I can always go for sushi`. By using the syntax from the NLU training data `[sushi](cuisine)`, you can mark `sushi` as an entity of type `cuisine`. ```yaml stories: - story: story with entities steps: - user: I can always go for [sushi](cuisine) - action: utter_suggest_cuisine ``` Similarly, you can put bot utterances directly in the stories, by using the `bot` key followed by the text that you want your bot to say. A story with only a bot utterance might look like this: ```yaml stories: - story: story with an end-to-end response steps: - intent: greet entities: - name: Ivan - bot: Hello, a person with a name! ``` You can also have a mixed end-to-end story: ```yaml stories: - story: full end-to-end story steps: - intent: greet entities: - name: Ivan - bot: Hello, a person with a name! - intent: search_restaurant - action: utter_suggest_cuisine - user: I can always go for [sushi](cuisine) - bot: Personally, I prefer pizza, but sure let's search sushi restaurants - action: utter_suggest_cuisine - user: Have a beautiful day! - action: utter_goodbye ```