diff --git a/docs/docs/how-to-deploy.mdx b/docs/docs/how-to-deploy.mdx index afeb705e7fa5..c514f1ae016e 100644 --- a/docs/docs/how-to-deploy.mdx +++ b/docs/docs/how-to-deploy.mdx @@ -69,7 +69,7 @@ for doing so, as well as manual instructions for any custom setups. It is also possible to deploy a Rasa assistant without Rasa X using Docker Compose. To do so, you can build your Rasa Assistant locally or in Docker. Then you can deploy your model in Docker Compose. -* [Building a Rasa Assistant Locally](./prototype-an-assistant.mdx) +* [Building a Rasa Assistant Locally](./playground.mdx) * [Building a Rasa Assistant in Docker](./docker/building-in-docker.mdx) diff --git a/docs/docs/installation.mdx b/docs/docs/installation.mdx index 0cc1f52426cd..ce18ec6d3349 100644 --- a/docs/docs/installation.mdx +++ b/docs/docs/installation.mdx @@ -24,10 +24,10 @@ rasa init ``` :::note Want to explore first? -You can explore Rasa Open Source online using our prototyper without any installation. +You can explore Rasa Open Source online using the Rasa Playground even before you install. At the end of the tutorial you can download the resulting assistant, install Rasa on your machine and continue development locally. -Prototype an Assistant +Rasa Playground ::: ## Step-by-step Installation Guide @@ -175,10 +175,10 @@ You can read more about how that data is pulled out and what it is used for in t **Congratulations! You have successfully installed Rasa Open Source!** -Next step: Start prototyping your first assistant online and download it afterwards +Next step: Use the Rasa Playground to prototype your first assistant in the browser and download it afterwards - + ## Building from Source diff --git a/docs/docs/introduction.mdx b/docs/docs/introduction.mdx index 0e3ddaed6fd5..c9460c39d7a8 100644 --- a/docs/docs/introduction.mdx +++ b/docs/docs/introduction.mdx @@ -10,7 +10,7 @@ import useBaseUrl from '@docusaurus/useBaseUrl'; ## Prototype an Assistant -Try out Rasa Open Source before you install by [prototyping an assistant](prototype-an-assistant.mdx)! +Try out Rasa Open Source before you install by prototyping in the [Rasa Playground](playground.mdx)! ## Quick Install diff --git a/docs/docs/prototype-an-assistant.mdx b/docs/docs/playground.mdx similarity index 92% rename from docs/docs/prototype-an-assistant.mdx rename to docs/docs/playground.mdx index bcd75f01bbbb..860388b1bfa5 100644 --- a/docs/docs/prototype-an-assistant.mdx +++ b/docs/docs/playground.mdx @@ -1,5 +1,5 @@ --- -id: prototype-an-assistant +id: playground sidebar_label: 'Rasa Playground' title: 'Rasa Playground' abstract: Learn the basics of building an assistant with Rasa Open Source with this interactive guide. You will be able to customize the assistant, talk to it and download the project so you can continue to build. @@ -36,10 +36,10 @@ What are the various things people might say to an assistant that can help them For an assistant to recognize what a user is saying no matter how the user phrases their message, we need to provide example messages the assistant can learn from. We group these examples according to the idea or the goal the message is expressing, which is also called the intent. -In the code block below, we have added an intent called greet, which contains example +In the code block on the right, we have added an intent called greet, which contains example messages like “Hi”, “Hey”, and “good morning”. -Intents and training examples make up the assistant’s NLU data, which is used to train the NLU model. +Intents and their examples are used as training data for the assistant's Natural Language Understanding (NLU) model. [Learn more about NLU data and its format](./training-data-format.mdx) @@ -81,7 +81,7 @@ Now that the assistant understands a few messages users might say, it needs resp “Hello, how can I help you?” and “what’s your email address?” are some of the responses our assistant will use. You’ll see how to connect user messages and responses in the next steps. In the code block below, we have listed some responses and added one or more text -options for each of them. If a response has multiple text options, one of them will be chosen at random whenever that response is predicted. +options for each of them. If a response has multiple text options, one of these options will be chosen at random whenever that response is predicted. [Learn more about responses](./responses.mdx) @@ -116,7 +116,7 @@ The story format shows the intent of the user message followed by the assistant Your first story should show a conversation flow where the assistant helps the user accomplish their goal in a straightforward way. Later, you can add stories for situations where the user doesn't want to provide their information or switches to another topic. -In the code block below, we have added a simple story where the user and assistant exchange greetings, the user asks to subscribe to the newsletter, and then the user provides their email address in response to the newsletter_form. +In the code block below, we have added a story where the user and assistant exchange greetings, the user asks to subscribe to the newsletter, and the assistant starts collecting the information it needs through the newsletter_form. You will learn about forms in the next step. [Learn more about stories](./writing-stories.mdx) @@ -176,6 +176,8 @@ it is no longer active (`active_loop: null`), the form is complete. [Learn more about rules and how to write them.](./rules.mdx) +Now that you've gone through all the steps, scroll down to talk to your assistant. + diff --git a/docs/sidebars.js b/docs/sidebars.js index 6aac61e9cdb2..aa8a8f38fefb 100644 --- a/docs/sidebars.js +++ b/docs/sidebars.js @@ -1,7 +1,7 @@ module.exports = { default: [ 'introduction', - 'prototype-an-assistant', + 'playground', { type: 'category', label: 'Building Assistants',