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

# Quickstart

> Get started with Xyne Locally

### Guides :

<CardGroup>
  <Card title="Step 1 : Quickstart the application." icon="rocket" href="/quickstart">
    Use quickstart to reach the login screen.
  </Card>

  <Card title="Step 2 : Generate Google Credentials And Add Scopes." icon="lock-open" href="/authentication/get-credentials">
    Set-up your google credentials and add scopes.
  </Card>

  <Card title="Step 3 : Add AI provider" icon="comment-code" href="/apikeys/apikeys">
    Add AI Provider of your choice to use Chat.
  </Card>

  <Card title="Step 4 : Ingest Your Data" icon="rotate" href="/ingestion/ingestion">
    Ingest your Data into the Xyne App.
  </Card>
</CardGroup>

If you want to deploy Xyne using your local machine, this document will give you a detailed guide to do so.
Follow the steps listed below to get started :

## Install the required dependencies :

Deployment of Xyne requires you to only install Docker and Docker Compose:

* [Docker](https://docs.docker.com/engine/install/)
* [Docker Compose](https://docs.docker.com/compose/install/)

Once you have installed the dependencies, you can use the following steps to set up the app.

## Clone the repository :

Use the following git command to clone the xyne repository.

```javascript theme={null}
git clone https://github.com/xynehq/xyne.git
```

## Deploy Xyne with Docker  :

<Tip> Remember to ensure that your Docker service is running. Incase you're using Docker Desktop, ensure that is running too </Tip>

<Tip> If you have postgres running, we suggest you kill the process before starting docker </Tip>

Run the application with the following command from the `xyne` folder:

```javascript theme={null}
docker-compose -f deployment/docker-compose.yml up
```

And that is all 🎉 ! The app will now be available in port `3001`.  [Go to xyne](http://localhost:3001/)

<Note> Since the size of the downloading models can be quite large, wait for the application to start running, this can take around 10 - 15 minutes,
depending on your internet connection. </Note>

<Tip> You can also choose to follow the [Step guide](https://docs.xynehq.com/quickstart#guides) mentioned above</Tip>

### Post Execution Setup \[Environment Variables]:

To unlock the full potential of the Xyne app, you need to enable Google Authentication. This requires setting up your Google credentials first.

#### Taking down docker-compose

First, bring down the Docker Compose setup using:

```javascript theme={null}
docker-compose -f deployment/docker-compose.yml down
```

#### Getting Google Credentials

Then proceed to obtain your `GOOGLE_CLIENT_ID` and `GOOGLE_SECRET` by following this guide:

<Card title="Setup Google Credentials" icon="google" href="/authentication/get-credentials">
  Setup your Google Credentials for the application.
</Card>

#### Setting the environment variables:

Inside the `server` folder of the `xyne` folder, you will find a `.env.default` file, this is the environment file that our docker uses.
For the moment you will find some default generated environment variables that we've set up for the app to work.

<Warning> We strictly recommend generating your own ***ENCRYPTION\_KEY, SERVICE\_ACCOUNT\_ENCRYPTION\_KEY and JWT\_SECRET*** values for security.</Warning>

<Tip>Due to our agentic RAG implementation, the maximum TPM limit exceeds for Open AI's gpt4o model.
For the ***best experience***, we recommend using ***AWS Bedrock or Claude***, as it enhances performance and accuracy. </Tip>

In the `.env.default` file, you can modify the following and replace the missing values with your own :

```javascript .env.default file theme={null}
ENCRYPTION_KEY=<YOUR_ENCRYPTION_KEY>
SERVICE_ACCOUNT_ENCRYPTION_KEY=<YOUR_SERVICE_ACCOUNT_ENCRYPTION_KEY> 
  

GOOGLE_CLIENT_ID=<YOUR_GOOGLE_CLIENT_ID>
GOOGLE_CLIENT_SECRET=<YOUR_GOOGLE_CLIENT_SECRET>
GOOGLE_REDIRECT_URI=http://localhost:3000/v1/auth/callback
GOOGLE_PROD_REDIRECT_URI=http://localhost:3001/v1/auth/callback


JWT_SECRET=<YOUR_JWT_SECRET>


DATABASE_HOST=xyne-db
VESPA_HOST=vespa

## If using AWS Bedrock
AWS_ACCESS_KEY=<YOUR_AWS_ACCESS_KEY>
AWS_SECRET_KEY=<YOUR_AWS_ACCESS_SECRET>
AWS_REGION=<YOUR_AWS_REGION>
  
## OR [ If using Open AI ]
OPENAI_API_KEY=<YOUR_OPEN_API_KEY>

## OR [ If using Ollama ] 
OLLAMA_MODEL=<YOUR_OLLAMA_MODEL_NAME> 

## OR  [ If using Together AI ] 
TOGETHER_API_KEY=<YOUR_TOGETHER_API_KEY>
TOGETHER_MODEL=<YOUR_TOGETHER_MODEL>
TOGETHER_FAST_MODEL=<YOUR_TOGETHER_FAST_MODEL>

## OR  [ If using Fireworks AI ] 
FIREWORKS_API_KEY=<YOUR_FIREWORKS_API_KEY>
FIREWORKS_MODEL=<YOUR_FIREWORKS_MODEL>
FIREWORKS_FAST_MODEL=<YOUR_FIREWORKS_FAST_MODEL>

## OR [If using Google AI]
GEMINI_API_KEY=<YOUR_GEMINI_API_KEY> 
GEMINI_MODEL=<YOUR_GEMINI_MODEL_NAME>  

## If you are using custom OpenAI or Together AI endpoints
BASE_URL=<YOUR_BASE_URL>

HOST=http://localhost:3001
```

<Tip>To use the chat feature of Xyne, you need any one AI provider (AWS, Ollama, OpenAI Together AI or Fireworks AI). Missing keys will disable chat functionality.</Tip>

You can checkout the AI Providers section for better clarity :

<Card title="Setup AI Providers for Xyne" icon="key" href="/apikeys/apikeys">
  Setup your AI Provider.
</Card>

<Warning> Chat will be unavailable without a Service Account or OAuth Account connection. </Warning>

And build the container again from the `xyne` folder using :

```javascript theme={null}
docker-compose -f deployment/docker-compose.yml up 
```

<Note> Currently the client side has .env variables that refer to port 3001, if you've changed the port number ensure to change the values in the .env as well. </Note>

## Ingesting data

Follow the guide below to learn more about ingesting data into xyne app:

<Card title="Ingest data in Xyne app" icon="inbox-in" href="/ingestion/ingestion">
  Ingest data into Xyne app.
</Card>