Quickstart
To quickly get started, follow the steps below:
Step 1: Install Jan Desktop
Before using Jan, you need to install Jan. Jan can be installed through:
Step 2: Download a Model
Jan provides a variety of local AI models tailored to different needs and is ready for download. These models are installed and run directly on the user's device.
- Go to the Hub.
- Select the models that you would like to install. To see model details, click the dropdown button.
- Or you can also paste the Hugging Face model's ID or URL in the search bar.
Ensure you select the appropriate model size by balancing performance, cost, and resource considerations in line with your task's specific requirements and hardware specifications.
- Click the Download button.
Step 3: Configure the Model
After downloading, configure the model to fit your requirements and hardware specs by following these steps:
- Go to the Thread tab.
- Click the Model dropdown button.
- Choose the downloaded model, either Local or Remote.
- Adjust the configurations as needed.
Please see Using Models for detailed model configuration.
Step 4: Start the Model
After downloading and configuring your model, you can chat with the model.
Step 5: Connect to ChatGPT (Optional)
Jan also provides access to remote models hosted on external servers, requiring an API key for connectivity. For example, to use the ChatGPT model with Jan, you must input your API key by following these steps:
- Go to the Thread tab.
- Under the Model dropdown menu, select the ChatGPT model.
- Fill in your ChatGPT API Key that you can get in your OpenAI platform (opens in a new tab).
Best Practices
Optimize your experience with Jan by implementing these best practices, designed for developers, analysts, and AI enthusiasts. These guidelines will enhance the performance of AI models on your local machine.
Quickstart Guide
Refer to the quickstart guide to set up Jan efficiently. It provides straightforward instructions that help you start quickly, even if you're new to AI.
Selecting the Right Models
Choose from Jan's pre-configured AI models to match your needs. Consider the model's capabilities, accuracy, and processing speed.
Remember, your choice may also depend on your hardware specs (see the Hardware Requirements section).
Setting Up Jan
Get familiar with Jan's application and its advanced settings to fine-tune AI performance. Refer to the Settings for configuration details.
Integrations
Understand the integration capabilities and limitations when connecting Jan with other systems or open-source LLM providers.
Mastering Prompt Engineering
Enhancing AI responses involves skilled, prompt engineering. Here are key tips:
- Adopt a specific persona for the model.
- Provide detailed prompts for precise responses.
- Start with context or examples.
- Use clear, concise language and specific keywords.
Pre-configured Models
For a complete list of available AI models, visit our official GitHub (opens in a new tab).