> For the complete documentation index, see [llms.txt](https://docs.ccv.brown.edu/ai-tools/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ccv.brown.edu/ai-tools/services/librechat/advanced-usage.md).
# Advanced Usage
Configuring prompts and model settings
## **Model Configurations**
You can personalize how the AI behaves by accessing the control panel. To open it, click the control icon located in the left panel.
Here are the key settings you can adjust:
### 1. Parameters - Temperature (Creativity)
The **Temperature** setting controls how "creative" or "random" the AI's responses are.
* **Lower values (e.g., 0 - 0.5):** The model becomes more focused, precise, and deterministic. Use this for coding, data analysis, or factual answers.
* **Higher values (e.g., 0.8 - 1.0):** The model becomes more creative and unpredictable. Use this for brainstorming, storytelling, or generating varied ideas.
### Creating and Using Prompts
1. **Create a Prompt:**
* Select the **Prompts** tab.
* Click the **Add Prompt** button (+)
* Give a name and a the prompt in the text area
* Press the **Create Prompt button**
2. **Use a Prompt:**
* Select the model you want to use
* Click on your desired prompt from the list in the **Prompts** tab.
* This will automatically apply the prompt to your chat input. The AI will now follow these instructions for the rest of the conversation.
Take into account that prompts use additional tokens/credits per message. Your credit per month limit can be affected by this.
### 3. Manage Uploaded Files
In this section, you can review and manage the documents or images you have attached to the current and previous conversations.
* Click on the **Attached Files** section to view a list of your uploaded files, including their names and upload dates. Below this list.
* Click the **Manage Files** button to manually select and delete any files you no longer need.
## **Configure Speech-to-Text and Text-to-Speech**
LibreChat offers audio capabilities that allow you to listen to responses and dictate your messages.
### Text-to-Speech (Read Aloud)
You can have LibreChat read responses aloud by clicking the **speaker icon** (Read Aloud) located at the bottom of any message.
### Speech-to-Text (Voice Typing)
Instead of typing, you can use your microphone to dictate questions. simply click the **microphone icon** located within the chat input box to start recording.
### Changing the Voice
To customize the voice used for reading responses:
1. Click on your **Profile** icon in the bottom-left corner.
2. Select **Settings**.
3. Navigate to the **Speech** tab.
4. Under the **Text to Speech** section, choose your preferred voice from the dropdown menu.
### Using Dual Conversation (Compare Mode)
LibreChat allows you to send the same message to two different models simultaneously, making it easy to compare their responses.
1. **Select the First Model**: Choose your primary model from the model dropdown list at the top of the chat.
2. **Add a Second Model**: Click the **plus (+)** button located immediately to the right of the model dropdown.
3. **Select the Second Model**: A new dropdown will appear. Choose the second model you wish to compare.
4. **Start Chatting**: Type your message in the chatbox and press **Enter**. Both models will generate responses side-by-side in the chat window.
Take into account that some models have different response times.
## How to build and agent
For detailed instructions, please refer to the official [LibreChat documentation website](https://www.librechat.ai/docs/features/agents).
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.ccv.brown.edu/ai-tools/services/librechat/advanced-usage.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
located in the left panel.
