> ## Documentation Index
> Fetch the complete documentation index at: https://openchat-not-gen-ui.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> OpenCopilot is a free and open-source tool that allows you to create AI copilots for your SaaS product. The copilot can communicate with your underlying APIs and execute calls as needed. We are open-source under MIT license and also support OpenAPI standards.

## Getting started

<CardGroup cols={2}>
  <Card title="What are copilots? (start from here)" icon="question" href="ai-copilots">
    Introduction to OpenCopilot. **start from here** for step-by-step guide
  </Card>

  <Card title="Setting up" icon="palette" href="#setting-up">
    Install the project locally and make it yours
  </Card>

  <Card title="Create copilots" icon="code" href="api-reference/endpoint/get">
    Create copilots programmatically (APIs, SDKs) or using the dashboard
  </Card>

  <Card title="Authentications and Authorization" icon="screwdriver-wrench" href="authorization">
    Handle Authentications and Authorization to your backend
  </Card>

  <Card title="Embedding copilots on your app" icon="lightbulb" href="widget/embed">
    How to use OpenCopilot widget and embed it on your web app
  </Card>

  <Card title="Creating complex flows" icon="rectangle-code" href="flows">
    Learn how to use OpenCopilot flows definition
  </Card>

  <Card title="Roadmap" icon="stars" href="https://opencopilot.so/roadmap">
    See what's coming next.
  </Card>
</CardGroup>

## Setting up

You can self-host OpenCopilot in a relatively easy way, please make sure you have the following requirements:

* Docker engine and docker compose installed
* Clone the repository

```bash
git clone https://github.com/openchatai/opencopilot.git
```

* Update your llm-server/.env with your OPENAI\_API\_KEY

```dotenv
OPENAI_API_KEY=YOUR_KEY_GOES_HERE
```

* Run the installation script

```bash
make install
```

Then your OpenCopilot dashboard will be accessible at [http://localhost:8888](http://localhost:8888)

***

You also can see the complete list of commands using `make help`

```
➜  OpenCopilot git:(main) make help
Usage: make [target]

Available Targets:

  install            - Install and set up the Docker environment
  db-setup           - Set up the database (fresh migration with seeding)
  down               - Stop and remove all containers
  exec-backend      - Access the backend container's shell
  exec-dashboard    - Access the dashboard container's shell
  exec-llm-server   - Access the llm-server container's shell
  restart            - Restart all containers
  logs               - Show container logs

  help               - Display this help message
```

## Crawling Web Pages

By default, when passing in a URL to create a new DataSource for a Copilot, 15 pages will be indexed. The configuration for this is located in the `opencopilot/llm-server/utils/llm_consts.py` file:

```python
max_pages_to_crawl = int(os.getenv("MAX_PAGES_TO_CRAWL", "15"))
```

To increase the max pages to crawl, you can change the configuration file. However, this will create uncommitted changes in your working copy which you will need to stash in order to `git pull` for future updates. Another way to increase the max pages to crawl is to set an environment variable:

```bash
export MAX_PAGES_TO_CRAWL="50"
```

***

Complete list of links:

* [http://localhost:8888/backend](http://localhost:8888/backend) -> backend APIs (create, update, delete and validate copilots)
* [http://localhost:8888](http://localhost:8888) or [http://localhost:8888/dashbaord](http://localhost:8888/dashbaord) -> dashboard (UI to do the same)