A chat tool that integrates multiple popular large language model (LLM) services, including OpenAI, Anthropic, Gemini, etc. Currently supports:
- OpenAI
- Anthropic
- Gemini
- Qwen
With the release of Alfred version 5.5, Alfred officially provided the ChatGPT Workflow, but it only supports OpenAI integration. When I installed and used it, my OpenAI API Key happened to be banned. Moreover, the ChatGPT Workflow is mainly based on JXA (JavaScript for Automation), which is difficult to extend. Therefore, I rewrote it in Python and extended support for other LLM services such as Anthropic and Gemini. Now, introducing support for a new LLM service is very easy.
- You need to choose an LLM service, register an account on its official website, and obtain an API Key.
- Install python3, ensuring that
/usr/bin/env python3 -c "import sys; print(sys.executable)"prints the correct path to your python3.
Here is how to get those api-keys:
- OpenAI: https://platform.openai.com/api-keys
- Anthropic: https://console.anthropic.com/settings/keys
- Gemini: https://ai.google.dev/gemini-api/docs/api-key
- (Qwen)通义千问: https://help.aliyun.com/zh/dashscope/developer-reference/activate-dashscope-and-create-an-api-key
- Install the workflow. Typically, you just need to download the latest version from the release page and click to install it.
- Perform basic configuration. You need to select a provider, and set the corresponding Api Key, Model. If necessary, set a proxy.
- Make sure the endpoint is correct.
- Enjoy.
Tip: Enhance your user experience by adding hotkey triggers. After installation, the workflow's hotkey triggers are initially unset. We recommend using Ctrl + Shift + Z to open chat history and Ctrl + Shift + X to start a new chat, but feel free to customize these to your liking.
