I don't understand what the use case is here at all. It saves prompt parameters as JSON? Is that it?
If you enjoy the OpenAI's playground, this looks pretty much like that but you can use other LLMs.
AIConfig Extension for VS Code
11–17 of 17 posts
Re: AIConfig Extension for VS Code
#12I don't understand what the use case is here at all. It saves prompt parameters as JSON? Is that it?
It seems to be a config file format, library for loading it, interactive editor for it, and playground that uses it.
Re: AIConfig Extension for VS Code
#13I don't understand what the use case is here at all. It saves prompt parameters as JSON? Is that it?
I thought it supported a few use cases:
* Testing prompt behavior across various LLMs * Sharing those prompts across multiple applications
We currently use a jupyter notebook to iterate, test, and validate prompts. Then move those prompts to our production app written in C#. If there were a C# SDK, I could use this tool to create a prompts config file and share it between the jupyter notebook and the C# app. The config file could also be added to version control.
Having said that, I don't understand why it saves the output of the LLM so maybe I'm missing something.
Re: AIConfig Extension for VS Code
#14It contains telemetry but it's not clear whether it collects your prompts or not
Re: AIConfig Extension for VS Code
#15It contains telemetry but it's not clear whether it collects your prompts or not
doesn't collect prompts and there's a way to disable telemetry as well - https://github.com/lastmile-ai/aiconfig/blob/8a5a59d47cef474...
Re: AIConfig Extension for VS Code
#16VSCode is a good target for single-player editing, and I can see something like this being helpful, but what does a collaborative experience look like, eg if you have a team of folks all working on the same prompts?
Isn't that what Git is for? Or do you mean lot's of people editing the same prompt at the same moment, a la google docs? That sounds... hectic.
Re: AIConfig Extension for VS Code
#17Alternative extension to do something similar, but using VSCode's native notebooks: https://marketplace.visualstudio.com/items?itemName=jaaxxx.l.... It's more tailored to crafting long-form few-shot prompts, rather than a single text box. Think ChatGPT playground but with a text editor interface that isn't absolutely terrible.
Nice part about that one is no separate server, no telemetry, and the backing file format is simple JSON you can directly import from your production application. However the range of supported models is smaller (basically only LLaMa-style and OpenAI-style interfaces are supported).