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

- [Docs for the new version 2.0 can be found here.](/content/docs/rasa/index.html)

## User Guide

- [Installation](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/installation/)
- [Rasa Tutorial](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/rasa-tutorial/)
- [Command Line Interface](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/command-line-interface/)
- [Architecture](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/architecture/)
- [Messaging and Voice Channels](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/messaging-and-voice-channels/)
- [Evaluating Models](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/evaluating-models/)
- [Validate Data](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/validate-files/)
- [Running the Server](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/running-the-server/)
- [Running Rasa with Docker](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/running-rasa-with-docker/)
- [Cloud Storage](https://legacy-docs-v1.rasa.com/1.3.10/user-guide/cloud-storage/)

## NLU

- [About](https://legacy-docs-v1.rasa.com/1.3.10/nlu/about/)
- [Using NLU Only](https://legacy-docs-v1.rasa.com/1.3.10/nlu/using-nlu-only/#)
- [Training Data Format](https://legacy-docs-v1.rasa.com/1.3.10/nlu/training-data-format/)
- [Choosing a Pipeline](https://legacy-docs-v1.rasa.com/1.3.10/nlu/choosing-a-pipeline/)
- [Language Support](https://legacy-docs-v1.rasa.com/1.3.10/nlu/language-support/)
- [Entity Extraction](https://legacy-docs-v1.rasa.com/1.3.10/nlu/entity-extraction/)
- [Components](https://legacy-docs-v1.rasa.com/1.3.10/nlu/components/)

## Core

- [About](https://legacy-docs-v1.rasa.com/1.3.10/core/about/)
- [Stories](https://legacy-docs-v1.rasa.com/1.3.10/core/stories/)
- [Domains](https://legacy-docs-v1.rasa.com/1.3.10/core/domains/)
- [Responses](https://legacy-docs-v1.rasa.com/1.3.10/core/responses/)
- [Actions](https://legacy-docs-v1.rasa.com/1.3.10/core/actions/)
- [Policies](https://legacy-docs-v1.rasa.com/1.3.10/core/policies/)
- [Slots](https://legacy-docs-v1.rasa.com/1.3.10/core/slots/)
- [Forms](https://legacy-docs-v1.rasa.com/1.3.10/core/forms/)
- [Retrieval Actions](https://legacy-docs-v1.rasa.com/1.3.10/core/retrieval-actions/)
- [Interactive Learning](https://legacy-docs-v1.rasa.com/1.3.10/core/interactive-learning/)
- [Fallback Actions](https://legacy-docs-v1.rasa.com/1.3.10/core/fallback-actions/)
- [Knowledge Base Actions](https://legacy-docs-v1.rasa.com/1.3.10/core/knowledge-bases/)

## Conversation Design

- [Dialogue Elements](https://legacy-docs-v1.rasa.com/1.3.10/dialogue-elements/dialogue-elements/)
- [Small Talk](https://legacy-docs-v1.rasa.com/1.3.10/dialogue-elements/small-talk/)
- [Completing Tasks](https://legacy-docs-v1.rasa.com/1.3.10/dialogue-elements/completing-tasks/)
- [Guiding Users](https://legacy-docs-v1.rasa.com/1.3.10/dialogue-elements/guiding-users/)

## API Reference

- [Action Server](https://legacy-docs-v1.rasa.com/1.3.10/api/action-server/)
- [HTTP API](https://legacy-docs-v1.rasa.com/1.3.10/api/http-api/)
- [Jupyter Notebooks](https://legacy-docs-v1.rasa.com/1.3.10/api/jupyter-notebooks/)
- [Agent](https://legacy-docs-v1.rasa.com/1.3.10/api/agent/)
- [Custom NLU Components](https://legacy-docs-v1.rasa.com/1.3.10/api/custom-nlu-components/)
- [Events](https://legacy-docs-v1.rasa.com/1.3.10/api/events/)
- [Tracker](https://legacy-docs-v1.rasa.com/1.3.10/api/tracker/)
- [Tracker Stores](https://legacy-docs-v1.rasa.com/1.3.10/api/tracker-stores/)
- [Event Brokers](https://legacy-docs-v1.rasa.com/1.3.10/api/event-brokers/)
- [Lock Stores](https://legacy-docs-v1.rasa.com/1.3.10/api/lock-stores/)
- [Training Data Importers](https://legacy-docs-v1.rasa.com/1.3.10/api/training-data-importers/)
- [Featurization](https://legacy-docs-v1.rasa.com/1.3.10/api/featurization/)
- [Migration Guide](https://legacy-docs-v1.rasa.com/1.3.10/migration-guide/)
- [Rasa Change Log](https://legacy-docs-v1.rasa.com/1.3.10/changelog/)

## Migrate from (beta)

- [Dialogflow](https://legacy-docs-v1.rasa.com/1.3.10/migrate-from/google-dialogflow-to-rasa/)
- [Wit.ai](https://legacy-docs-v1.rasa.com/1.3.10/migrate-from/facebook-wit-ai-to-rasa/)
- [LUIS](https://legacy-docs-v1.rasa.com/1.3.10/migrate-from/microsoft-luis-to-rasa/)
- [IBM Watson](https://legacy-docs-v1.rasa.com/1.3.10/migrate-from/ibm-watson-to-rasa/)

## Reference

- [Glossary](https://legacy-docs-v1.rasa.com/1.3.10/glossary/)

## Versions

viewing: 1.3.10

## tags

[1.10.26](https://legacy-docs-v1.rasa.com/1.10.26/nlu/using-nlu-only/) [1.10.25](https://legacy-docs-v1.rasa.com/1.10.25/nlu/using-nlu-only/) [1.10.24](https://legacy-docs-v1.rasa.com/1.10.24/nlu/using-nlu-only/) [1.10.23](https://legacy-docs-v1.rasa.com/1.10.23/nlu/using-nlu-only/) [1.10.22](https://legacy-docs-v1.rasa.com/1.10.22/nlu/using-nlu-only/) [1.10.21](https://legacy-docs-v1.rasa.com/1.10.21/nlu/using-nlu-only/) [1.10.20](https://legacy-docs-v1.rasa.com/1.10.20/nlu/using-nlu-only/) [1.10.19](https://legacy-docs-v1.rasa.com/1.10.19/nlu/using-nlu-only/) [1.10.18](https://legacy-docs-v1.rasa.com/1.10.18/nlu/using-nlu-only/) [1.10.17](https://legacy-docs-v1.rasa.com/1.10.17/nlu/using-nlu-only/) [1.10.16](https://legacy-docs-v1.rasa.com/1.10.16/nlu/using-nlu-only/) [1.10.15](https://legacy-docs-v1.rasa.com/1.10.15/nlu/using-nlu-only/) [1.10.14](https://legacy-docs-v1.rasa.com/1.10.14/nlu/using-nlu-only/) [1.10.13](https://legacy-docs-v1.rasa.com/1.10.13/nlu/using-nlu-only/) [1.10.12](https://legacy-docs-v1.rasa.com/1.10.12/nlu/using-nlu-only/) [1.10.11](https://legacy-docs-v1.rasa.com/1.10.11/nlu/using-nlu-only/) [1.10.10](https://legacy-docs-v1.rasa.com/1.10.10/nlu/using-nlu-only/) [1.10.9](https://legacy-docs-v1.rasa.com/1.10.9/nlu/using-nlu-only/) [1.10.8](https://legacy-docs-v1.rasa.com/1.10.8/nlu/using-nlu-only/) [1.10.7](https://legacy-docs-v1.rasa.com/1.10.7/nlu/using-nlu-only/) [1.10.6](https://legacy-docs-v1.rasa.com/1.10.6/nlu/using-nlu-only/) [1.10.5](https://legacy-docs-v1.rasa.com/1.10.5/nlu/using-nlu-only/) [1.10.4](https://legacy-docs-v1.rasa.com/1.10.4/nlu/using-nlu-only/) [1.10.3](https://legacy-docs-v1.rasa.com/1.10.3/nlu/using-nlu-only/) [1.10.2](https://legacy-docs-v1.rasa.com/1.10.2/nlu/using-nlu-only/) [1.10.1](https://legacy-docs-v1.rasa.com/1.10.1/nlu/using-nlu-only/) [1.10.0](https://legacy-docs-v1.rasa.com/1.10.0/nlu/using-nlu-only/) [1.9.7](https://legacy-docs-v1.rasa.com/1.9.7/nlu/using-nlu-only/) [1.9.6](https://legacy-docs-v1.rasa.com/1.9.6/nlu/using-nlu-only/) [1.9.5](https://legacy-docs-v1.rasa.com/1.9.5/nlu/using-nlu-only/) [1.9.4](https://legacy-docs-v1.rasa.com/1.9.4/nlu/using-nlu-only/) [1.9.3](https://legacy-docs-v1.rasa.com/1.9.3/nlu/using-nlu-only/) [1.9.2](https://legacy-docs-v1.rasa.com/1.9.2/nlu/using-nlu-only/) [1.9.1](https://legacy-docs-v1.rasa.com/1.9.1/nlu/using-nlu-only/) [1.9.0](https://legacy-docs-v1.rasa.com/1.9.0/nlu/using-nlu-only/) [1.8.3](https://legacy-docs-v1.rasa.com/1.8.3/nlu/using-nlu-only/) [1.8.2](https://legacy-docs-v1.rasa.com/1.8.2/nlu/using-nlu-only/) [1.8.1](https://legacy-docs-v1.rasa.com/1.8.1/nlu/using-nlu-only/) [1.8.0](https://legacy-docs-v1.rasa.com/1.8.0/nlu/using-nlu-only/) [1.7.4](https://legacy-docs-v1.rasa.com/1.7.4/nlu/using-nlu-only/) [1.7.3](https://legacy-docs-v1.rasa.com/1.7.3/nlu/using-nlu-only/) [1.7.2](https://legacy-docs-v1.rasa.com/1.7.2/nlu/using-nlu-only/) [1.7.1](https://legacy-docs-v1.rasa.com/1.7.1/nlu/using-nlu-only/) [1.7.0](https://legacy-docs-v1.rasa.com/1.7.0/nlu/using-nlu-only/) [1.6.2](https://legacy-docs-v1.rasa.com/1.6.2/nlu/using-nlu-only/) [1.5.3](https://legacy-docs-v1.rasa.com/1.5.3/nlu/using-nlu-only/) [1.4.6](https://legacy-docs-v1.rasa.com/1.4.6/nlu/using-nlu-only/) [1.3.10](https://legacy-docs-v1.rasa.com/1.3.10/nlu/using-nlu-only/) [1.2.9](https://legacy-docs-v1.rasa.com/1.2.9/nlu/using-nlu-only/)

## Using NLU Only

If you want to use Rasa only as an NLU component, you can!

### Training NLU-only models

To train an NLU model only, run:

```
    rasa train nlu
```

This will look for NLU training data files in the `data/` directory and saves a trained model in the `models/` directory. The name of the model will start with `nlu-`.

### Testing your NLU model on the command line

To try out your NLU model on the command line, use the `rasa shell nlu` command:

```
    rasa shell nlu
```

This will start the rasa shell and ask you to type in a message to test. You can keep typing in as many messages as you like.

Alternatively, you can leave out the `nlu` argument and pass in an nlu-only model directly:

```
    rasa shell -m models/nlu-20190515-144445.tar.gz
```

### Running an NLU server

To start a server with your NLU model, pass in the model name at runtime:

```
    rasa run --enable-api -m models/nlu-20190515-144445.tar.gz
```

You can then request predictions from your model using the `/model/parse` endpoint. To do this, run:

```
    curl localhost:5005/model/parse -d '{"text":"hello"}'
```