OpenAI integrations
⤓ Install on the Alfred Gallery
- Create an OpenAI account and log in.
- On the API keys page, click
+ Create new secret key. - Name your new secret key and click
Create secret key. - Copy your secret key and add it to the Workflow’s Configuration.
Query ChatGPT via the chatgpt keyword, the Universal Action, or the Fallback Search.
<kbd>↩︎</kbd>Ask a new question.<kbd>⌘</kbd><kbd>↩︎</kbd>Clear and start new chat.<kbd>⌥</kbd><kbd>↩︎</kbd>Copy last answer.<kbd>⌃</kbd><kbd>↩︎</kbd>Copy full chat.<kbd>⇧</kbd><kbd>↩︎</kbd>Stop generating answer.
View Chat History with ⌥↩︎ in the chatgpt keyword. Each result shows the first question as the title and the last as the subtitle.
<kbd>↩︎</kbd> to archive the current chat and load the selected one. Older chats can be trashed with the Delete Universal Action. Select multiple chats with the File Buffer.
Query DALL·E via the dalle keyword.
<kbd>↩︎</kbd>Send a new prompt.<kbd>⌘</kbd><kbd>↩︎</kbd>Archive images.<kbd>⌥</kbd><kbd>↩︎</kbd>Reveal last image in the Finder.
This fork comes with a fastapi server that converts incoming request in openai format (generated by this workflow) to format accepted by POE, the collection of chatbots.
To configure this server, you should reference .env-example and put up your own api keys.
To start this manually, you can run the script start_server.zsh which host an api server locally at port 3700. Alternatively, you can use the keyword startpoe2gpt in Alfred to start this server.