You are viewing documentation for our open source project which is maintained by the community. If you want to get started building assistants with Rasa please check out our latest [documentation here](/content/docs/index.html).

Let's get started with migrating your application from LUIS to Rasa:

## Step 1: Export your Training Data from LUIS [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migrate-from/microsoft-luis-to-rasa/#step-1-export-your-training-data-from-luis "Direct link to heading")

Go to your list of [LUIS conversation apps](https://www.luis.ai/conversations/applications) and select the application you want to export.

Select 'Export' > 'Export as JSON'. This will download a file with a `.json` extension that can be imported directly into Rasa.

## Step 2: Create a Rasa Project [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migrate-from/microsoft-luis-to-rasa/#step-2-create-a-rasa-project "Direct link to heading")

To create a Rasa project, run:

```bash
rasa init
```

This will create a directory called `data`. Remove the files in this directory and move your json file into this directory.

```bash
rm -r data/*

mv /path/to/file.json data/
```

## Step 3: Train your NLU model [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migrate-from/microsoft-luis-to-rasa/#step-3-train-your-nlu-model "Direct link to heading")

To train a model using your LUIS data, run:

```bash
rasa train nlu
```

## Step 4: Test your NLU model [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migrate-from/microsoft-luis-to-rasa/#step-4-test-your-nlu-model "Direct link to heading")

Let's see how your NLU model will interpret some test messages. To start a testing session, run:

```bash
rasa shell nlu
```

This will prompt your for input. Type a test message and press 'Enter'. The output of your NLU model will be printed to the screen. You can keep entering messages and test as many as you like. Press 'control + C' to quit.

## Step 5: Start a Server with your NLU Model [\#](https://legacy-docs-oss.rasa.com/docs/rasa/migrate-from/microsoft-luis-to-rasa/#step-5-start-a-server-with-your-nlu-model "Direct link to heading")

To start a server with your NLU model, run:

```bash
rasa run
```

This will start a server listening on port 5005. To send a request to the server, run:

```bash
curl 'localhost:5005/model/parse?emulation_mode=luis' -d '{"text": "hello"}'
```

The `emulation_mode` parameter tells Rasa that you want your json response to have the same format as you would get from LUIS. You can also leave it out to get the result in the usual Rasa format.

## Terminology:

The words `intent`, `entity`, `role`, and `utterance` have the same meaning in Rasa as they do in LUIS.

LUIS's `patterns` feature is very similar to Rasa NLU's [regex features](./training-data-format.mdx#regular-expressions)

LUIS's `phrase lists` feature does not currently have an equivalent in Rasa NLU.

Join the [Rasa Community Forum](https://forum.rasa.com/) and let us know how your migration went!