These docs are for version 1.x of Rasa Open Source.

### User Guide

- [Installation](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/installation/)
- [Tutorial: Rasa Basics](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/rasa-tutorial/)
- [Tutorial: Building Assistants](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/building-assistants/)
- [Command Line Interface](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/command-line-interface/)
- [Architecture](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/architecture/)
- [Messaging and Voice Channels](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/messaging-and-voice-channels/)
- [Testing Your Assistant](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/testing-your-assistant/)
- [Setting up CI/CD](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/setting-up-ci-cd/)
- [Validate Data](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/validate-files/)
- [Configuring the HTTP API](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/configuring-http-api/)
- [Deploying Your Rasa Assistant](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/how-to-deploy/)
- [Cloud Storage](https://legacy-docs-v1.rasa.com/1.10.9/user-guide/cloud-storage/)

### NLU

- [About](https://legacy-docs-v1.rasa.com/1.10.9/nlu/about/)
- [Using NLU Only](https://legacy-docs-v1.rasa.com/1.10.9/nlu/using-nlu-only/)
- [Training Data Format](https://legacy-docs-v1.rasa.com/1.10.9/nlu/training-data-format/)
- [Language Support](https://legacy-docs-v1.rasa.com/1.10.9/nlu/language-support/)
- [Choosing a Pipeline](https://legacy-docs-v1.rasa.com/1.10.9/nlu/choosing-a-pipeline/)
- [Components](https://legacy-docs-v1.rasa.com/1.10.9/nlu/components/)
- [Entity Extraction](https://legacy-docs-v1.rasa.com/1.10.9/nlu/entity-extraction/)

### Core

- [About](https://legacy-docs-v1.rasa.com/1.10.9/core/about/)
- [Stories](https://legacy-docs-v1.rasa.com/1.10.9/core/stories/)
- [Domains](https://legacy-docs-v1.rasa.com/1.10.9/core/domains/)
- [Responses](https://legacy-docs-v1.rasa.com/1.10.9/core/responses/)
- [Actions](https://legacy-docs-v1.rasa.com/1.10.9/core/actions/)
- [Reminders and External Events](https://legacy-docs-v1.rasa.com/1.10.9/core/reminders-and-external-events/)
- [Policies](https://legacy-docs-v1.rasa.com/1.10.9/core/policies/#)
- [Slots](https://legacy-docs-v1.rasa.com/1.10.9/core/slots/)
- [Forms](https://legacy-docs-v1.rasa.com/1.10.9/core/forms/)
- [Retrieval Actions](https://legacy-docs-v1.rasa.com/1.10.9/core/retrieval-actions/)
- [Interactive Learning](https://legacy-docs-v1.rasa.com/1.10.9/core/interactive-learning/)
- [Fallback Actions](https://legacy-docs-v1.rasa.com/1.10.9/core/fallback-actions/)
- [Knowledge Base Actions](https://legacy-docs-v1.rasa.com/1.10.9/core/knowledge-bases/)

### Policies

The `rasa.core.policies.Policy` class decides which action to take at every step in the conversation.

#### Configuring Policies

- **Max History:** This controls how much dialogue history the model looks at to decide which action to take next.
- **Action Selection:** At every turn, each policy in your configuration will predict a next action with confidence. The bot’s next action is decided by the policy that predicts with the highest confidence.

##### Keras Policy

The `KerasPolicy` uses a neural network implemented in [Keras](http://keras.io/) to select the next action.

```python
def model_architecture(...):
    ...
```

##### Fallback Policy

The `FallbackPolicy` invokes a fallback action if the intent recognition has a confidence below `nlu_threshold`.

| Parameter               | Description                                        |
|-------------------------|----------------------------------------------------|
| `nlu_threshold`         | Min confidence needed to accept an NLU prediction. |
| `core_threshold`        | Min confidence needed to accept an action prediction from Rasa Core. |
| `fallback_action_name`  | Name of the fallback action to be called.         |

### Form Policy

The `FormPolicy` is an extension that handles the filling of forms. Once a `FormAction` is called, the `FormPolicy` will continually predict the `FormAction` until all required slots in the form are filled.