Skip to content

Latest commit

 

History

History
102 lines (76 loc) · 4.68 KB

README.md

File metadata and controls

102 lines (76 loc) · 4.68 KB


An VS Code ChatGPT Copilot Extension

The most loved opensourced ChatGPT extension for VS Code

The project is built on the most loved ChatGPT extension gencay/vscode-chatgpt, which has downloaded by ~500,000 developers.

But unfortunately, the original author has decided to stop maintaining the project, and the new recommended Genie AI extension on the original project is not opensourced. So I decided to fork it and continue the development.

Features

  • ➕ Use GPT-4, GPT-3.5, Claude 3 or OpenAI compatible local models with your API Key from OpenAI, Azure OpenAI Service or Anthropic.
  • 📃 Get streaming answers to your prompts in sidebar conversation window
  • 🔥 Stop the responses to save your tokens.
  • 📝 Create files or fix your code with one click or with keyboard shortcuts.
  • ➡️ Export all your conversation history at once in Markdown format.
  • Automatic partial code response detection. Continues and combines automatically, when response is cut off.
  • Ad-hoc prompt prefixes for you to customize what you are asking ChatGPT
  • Edit and resend a previous prompt
  • Copy, insert or create new file from the code, ChatGPT is suggesting right into your editor.

Configurations

Configuration Description
chatgpt.gpt3.apiKey Required, please get from OpenAI, Azure OpenAI or Anthropic.
chatgpt.gpt3.apiBaseUrl Optional, default to "https://api.openai.com/v1".
For Azure OpenAI Service, it should be set to "https://[YOUR-ENDPOINT-NAME].openai.azure.com/openai/deployments/[YOUR-DEPLOYMENT-NAME]".
chatgpt.gpt3.model Optional, default to "gpt-3.5-turbo".

Refer following sections for more details of how to configure various openai services.

OpenAI

    "chatgpt.gpt3.apiKey": "<api-key>",
    "chatgpt.gpt3.apiBaseUrl": "https://api.openai.com/v1", // Optional

Azure OpenAI Service

    "chatgpt.gpt3.apiKey": "<api-key>",
    "chatgpt.gpt3.model": "gpt-3.5-turbo",
    "chatgpt.gpt3.apiBaseUrl": "https://<endpoint-name>.openai.azure.com/openai/deployments/<deployment-name>", // Required

Anthropic Claude 3

    "chatgpt.gpt3.model": "claude-3-sonnet-20240229",
    "chatgpt.gpt3.apiKey": "<api-key>",
    "chatgpt.gpt3.apiBaseUrl": "https://api.anthropic.com/v1", // Optional

Local or self-hosted LLM compatible with OpenAI

    "chatgpt.gpt3.apiKey": "<api-key>",
    "chatgpt.gpt3.apiBaseUrl": "<base-url>",

Configuring Custom Model Names

To use a custom model name for local or self-hosted LLMs compatible with OpenAI, set the chatgpt.gpt3.model configuration to "custom" and specify your custom model name in the chatgpt.gpt3.customModel configuration.

Example configuration for a custom model name with groq:

    "chatgpt.gpt3.model": "custom",
    "chatgpt.gpt3.apiKey": "<your-custom-key>",
    "chatgpt.gpt3.customModel":  "mixtral-8x7b-32768",
    "chatgpt.gpt3.apiBaseUrl": "https://api.groq.com/openai/v1",

How to install locally

  • Install vsce if you don't have it on your machine (The Visual Studio Code Extension Manager)
    • npm install --global vsce
  • Run vsce package
  • Follow the instructions and install manually.
npm run build
npm run package
code --uninstall-extension jeanibarz.chatgpt-copilot
code --install-extension chatgpt-copilot-*.vsix

License

This project is released under ISC License - See LICENSE for details. Copyright notice and the respective permission notices must appear in all copies.