Custom Pilot FAQs
Custom Pilot is a Visual Studio Code extension framework that allows you to easily integrate your custom code completion model into VS Code. Learn more on the project's homepage.
FAQs of Custom Pilot
What is Custom Pilot?
Custom Pilot is a Visual Studio Code extension that lets you integrate your own custom code completion models into your development workflow.
How do I use Custom Pilot?
You can use Custom Pilot with LM Studio, which is a separate tool for building and training custom language models. Once you have a trained model, you can use Custom Pilot to load it into VS Code and start using it for code completion.
How does Custom Pilot work?
Custom Pilot works by connecting to LM Studio, which provides the trained language model. When you type code, Custom Pilot sends the current context to LM Studio, which generates suggestions based on the model's understanding of the code.
What are the benefits of using Custom Pilot?
Custom Pilot allows you to leverage the power of custom language models to improve your coding experience. This can lead to faster and more efficient development, as well as better code quality.
How does Custom Pilot compare to other code completion extensions?
Custom Pilot is unique in that it allows you to use your own custom models. This gives you more control over the code completion experience and allows you to tailor it to your specific needs. Many other code completion extensions are based on pre-trained models, which may not be as effective for specialized coding tasks.
How to use Custom Pilot
Custom Pilot enables integrating custom code completion models within Visual Studio Code. This tool leverages OpenAI's API format for seamless code completion in any programming language. It also integrates with LM Studio for offline LLM usage.
- Begin by installing the Custom Pilot extension through VS Code's Quick Open (
Ctrl+P) using the provided command. - Configure the extension by setting the API server URL in the Sidebar panel. This points to your custom completion model server.
- Choose an inference model from the dropdown menu. This selection determines the model used for code completions.
- Provide your API key, if required by your API server, for authentication. This ensures secure communication with your model.
- Optionally, adjust advanced settings to fine-tune the completion behavior. This allows customization based on user preference.
- To use with LM Studio, run a local webserver following their guide. Then, set the API server URL to your LM Studio instance.
- The selected model will then provide code completion suggestions. These suggestions are based on your custom model's output.
- Evaluate and utilize the code suggestions generated. This helps in improving coding efficiency and reducing manual coding effort.
