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

# Quickstart

> Start managing prompts in under 5 minutes.

## Running LangBear application

The LangBear app is a web application for prompt management. Users can create
and update prompt templates on-the-fly, track versions, and monitor prompt
ratings with it.

Step 1. Create and configure a new LangBear app with Supabase.

```bash theme={null}
$ npx create-langbear-app my-app --database supabase
```

Step 2. Start your app with `npm run dev`.

```bash theme={null}
$ npm run dev
```

The LangBear application is now available at `http://localhost:3030`. Check
out the [Application](/application) page for more details.

## Setting up your development

The LangBear library allows you to manage LangChain prompts from the LangBear
web application, accomplished with just a few lines of code.

Step 1. Add LangBear dependency to your project:

<CodeGroup>
  ```bash pip theme={null}
  pip install langbear
  ```

  ```bash npm theme={null}
  npm install -S langbear
  ```

  ```bash yarn theme={null}
  yarn add langbear
  ```

  ```bash pnpm theme={null}
  pnpm add langbear
  ```
</CodeGroup>

Step 2. Initialize LangBear client:

<CodeGroup>
  ```python python theme={null}
  from langbear import LangBear

  lb = LangBear(end_point="http://localhost:3030")
  ```

  ```typescript typescript theme={null}
  TBD;
  ```
</CodeGroup>

Step 2. Add LangBear callback handler to your LangChain callbacks:

<CodeGroup>
  ```python python theme={null}
  from langchain.llms import OpenAI

  llm = OpenAI(temperature=0.5, callbacks=[lb.callback_handler])
  ```

  ```typescript typescript theme={null}
  TBD;
  ```
</CodeGroup>

Step 3. Get a prompt template from LangBear:

<CodeGroup>
  ```python python theme={null}
  prompt = lb.prompts.get("company-name-generation")
  prompt.format(product="colorful socks")
  ```

  ```typescript typescript theme={null}
  TBD;
  ```
</CodeGroup>

You are now ready to manage prompts using LangBear. Check out the
[Development](/development) page for more details.