# LibreChat

LibreChat is an Open Source web application that allows you to interact with multiple Large Language Models (LLMs) in a single, unified workspace. It provides advanced capabilities such as multi-language support, the ability to use documents and images in your prompts, personalized model settings, and custom presets.

We have deployed this application for Brown’s use within our infrastructure, providing access to state of the art models with Enterprise-level privacy guarantees. Each user is given a certain amount of free credits per month. To learn more about your free-credits, please visit our [Cost and Limits page](https://docs.ccv.brown.edu/ai-tools/costs-and-limits).

## Getting started

### Logging In

To start using LibreChat, simply log in using your university credentials.

1. Navigate to [librechat.ccv.brown.edu](http://librechat.ccv.brown.edu).
2. Select the **Log in** button.
3. Enter your **Brown credentials**.
4. If this is your first time logging in, complete the two-factor authentication (2FA) prompt to create your account.

Once authenticated, you will be redirected to the main chat interface.

### Starting a New Chat

To begin a conversation:

1. Click the **+ New Chat** button in the top-left corner.
2. Select your desired model from the endpoint selector (e.g., GPT-5, Claude4, etc.) located at the top of the chat window.
3. Type your message in the input box at the bottom and press **Enter**.

<figure><img src="https://3357215318-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FXaSdR1JjDGbvccnFNb3t%2Fuploads%2FrM0pWHSjVAQlEL8UFDEp%2Flibrechat-new-chat.gif?alt=media&#x26;token=0f685eba-b212-4c88-8897-5b82087bc857" alt="Starts a new chat"><figcaption></figcaption></figure>

### Switching Models

LibreChat allows you to switch between different AI models easily:

* Click the model name at the top of the current chat.
* Select a different provider or specific model version from the dropdown menu to see which one works best for your specific task.

<figure><img src="https://3357215318-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FXaSdR1JjDGbvccnFNb3t%2Fuploads%2FWhmbfrBxkDsKNQSMz19S%2Flibrechat-select-ai.gif?alt=media&#x26;token=0120b6bc-9026-4f09-b5fe-bd921d1322a4" alt="Shows how to select different AI models for the chat"><figcaption></figcaption></figure>

### Model Availability

We select models based on their **performance, cost-efficiency, and strong commitment to privacy**. Generally, you can expect access to the two most recent versions of state-of-the-art models that meet our required security practices.

### Using Attachments (Files & Images)

You can upload documents or images to provide context to the AI:

1. Click the **paperclip icon** or **image icon** next to the chat input bar.
2. Select the files from your computer.
3. Once uploaded, type your prompt (e.g., "Summarize this PDF" or "Describe this image") and send the message.

<figure><img src="https://3357215318-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FXaSdR1JjDGbvccnFNb3t%2Fuploads%2F0IVbwm5kDsYtCeu1BSlp%2Flibrechat-upload-image.gif?alt=media&#x26;token=3644f692-91f5-439e-a9e6-7d01a8e5adbc" alt="Shows how to upload an image to the chat interface"><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.ccv.brown.edu/ai-tools/services/librechat.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.