Skip to content

Latest commit

 

History

History
54 lines (31 loc) · 3.48 KB

FAQ.md

File metadata and controls

54 lines (31 loc) · 3.48 KB
Raw

Frequently Asked Questions (FAQ)

How do I set up an alternative AI model?

The workflow offers the ability to change the API end points and override model names in the Workflow Environment Variables. This requires advanced configuration and is not something we can provide support for, but our community are doing it with great success and can help you.

How do I access the service behind a proxy?

Add a new https_proxy key in Workflow Environment Variables. Or configure the proxy for all workflows under Alfred Preferences → Advanced → Network.

Why can’t I use the workflow with a ChatGPT Plus subscription?

The ChatGPT API and ChatGPT Plus subscription are billed separately.

How can I reuse pre-made prompts?

Make a new workflow with a Keyword Input and connect it to an Arg and Vars Utility with your custom prompt text plus {query}, which will be replaced with new input from the Keyword. Then connect it to a Call External Trigger Output set to open continue_chat from this workflow.

Is there a video which shows how to use the workflow?

Yes.

Why does nothing happen when I run the workflow?

Something always happens, so check the debugger. Ensure you installed the Automation Tasks.

How do I report an issue?

Accurate and thorough information is crucial for a proper diagnosis. When reporting issues, please include your exact installed versions of:

  • The Workflow.
  • Alfred.
  • macOS.

In addition to:

  • The debugger output. Perform the failing action and click Copy on the top right.
  • Details on what you did, what happened, and what you expected to happen. A short video of the steps with the debugger open may help to find the problem faster.

Why do I keep getting Quota exceeded?

You need API credits to use the workflow. You can view your remaining credits and top up your account on the OpenAI website.

Why do I keep getting [Connection Stalled]?

This happens when the workflow takes too long to receive a reply from the API. It indicates a problem either with your connection or OpenAI’s service.

Open a terminal and run the following (replace YOUR_API_KEY within the quotes with your API key):

openai_key="YOUR_API_KEY"
time /usr/bin/curl "https://api.openai.com/v1/chat/completions" --header "Authorization: Bearer ${openai_key}" --header "Content-Type: application/json" --data '{ "model": "gpt-3.5-turbo", "messages": [{ "role": "user", "content": "What is red?" }], "stream": true }'

It should provide a clue as to what is happening. Include the result in your report.