> ## Documentation Index
> Fetch the complete documentation index at: https://docs.embedchain.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Streamlit.io

> Deploy your RAG application to streamlit.io platform

Embedchain offers a Streamlit template to facilitate the development of RAG chatbot applications in just three easy steps.

Follow the instructions given below to deploy your first application quickly:

## Step-1: Create RAG app

We provide a command line utility called `ec` in embedchain that inherits the template for `streamlit.io` platform and help you deploy the app. Follow the instructions to create a streamlit.io app using the template provided:

```bash Install embedchain theme={null}
pip install embedchain
```

```bash Create application theme={null}
mkdir my-rag-app
ec create --template=streamlit.io
```

This will generate a directory structure like this:

```bash theme={null}
├── .streamlit
│   └── secrets.toml
├── app.py
├── embedchain.json
└── requirements.txt
```

Feel free to edit the files as required.

* `app.py`: Contains API app code
* `.streamlit/secrets.toml`: Contains secrets for your application
* `embedchain.json`: Contains embedchain specific configuration for deployment (you don't need to configure this)
* `requirements.txt`: Contains python dependencies for your application

Add your `OPENAI_API_KEY` in `.streamlit/secrets.toml` file to run and deploy the app.

## Step-2: Test app locally

You can run the app locally by simply doing:

```bash Run locally theme={null}
pip install -r requirements.txt
ec dev
```

## Step-3: Deploy to streamlit.io

![Streamlit App deploy button](https://github.com/embedchain/embedchain/assets/73601258/90658e28-29e5-4ceb-9659-37ff8b861a29)

Use the deploy button from the streamlit website to deploy your app.

You can refer this [guide](https://docs.streamlit.io/streamlit-community-cloud/deploy-your-app) if you run into any problems.

## Seeking help?

If you run into issues with deployment, please feel free to reach out to us via any of the following methods:

<Snippet file="get-help.mdx" />