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 (usually found near the model selector or on the right side of the header).

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.

2. System Prompts (User Prompts)

This allows you to give the AI a "persona" or a set of specific instructions to follow for the entire conversation.

• Example: "You are an expert Python tutor. Explain concepts simply for a beginner."

• Usage: Instead of repeating instructions in every message, set a system prompt once, and the model will adhere to it throughout the chat.

Creating and Using Prompts

1. Create a Prompt:

   • Select the Prompts tab.

   • Click the Create Prompt button.

   • In the modal window, give your prompt a name and enter the specific instructions or behavior you want the AI to adopt in the text field.

2. Use a Prompt:

   • 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.