social-ai VS TypeChat

I wrote some code to annotate the image with the text of the prompt. I couldn't find a convenient way to do it in EXIF.

For Midjourney: https://github.com/ernop/social-ai/tree/main/SocialAI

Yeah, it's really strange how hard they make it to manage, download, and get full prompts for your images on all these platforms. I made this discord bot for midjourney which with some easy configuration can download and annotate all your images, including as much info as I could grab about version, etc. https://github.com/ernop/social-ai/tree/main/SocialAI

Even then it's not perfect since I'm getting info off of the command you send, which may have fallen into whatever the defaults were at the time, and so when interpreted today, not easily possible to reconstruct the version/seed/etc. from that point in the past, if you didn't include it in the prompt. But still, I just like having a folder of 30k images that I can never lose, with at least the prompt, so I can go through and re-run them later (even manually) to get comparisons over time.

Repo for my C# bot which you can use to download (and annotate) all your creations. https://github.com/ernop/social-ai/

Not sure it's related to function calling. GPT4 can do function calling without using the specific function-calling API just by injecting the schema you want into the prompt with directions and asking it to return JSON. It works like >99% of the time. Same with 3.5-turbo.

The problem is these libraries convert pydantic models into json schemas and inject them into the prompt, which uses up like 80% more tokens than just describing the schema using typescript type syntax for example. See https://microsoft.github.io/TypeChat/, where they prompt using typescript type descriptions to get json data from LLMs. It's similar to what we built but with more boilerplate.

Semantic Memory (renamed to Kernel Memory - https://github.com/microsoft/kernel-memory) complements SK. Guidance's features are being absorbed into SK, following the departure of that team from Microsoft. Additionally, we have TypeChat (https://github.com/microsoft/TypeChat), which aims to ensure type-safe responses from LLMs. Most features of Autogen are also being integrated into SK, along with Assistants. SK serves as the orchestration engine powering Microsoft Copilots.

I tried TypeChat for my use case and ended up defining functions as typescript data types. This approach sounds much better, and leverages the newer OpenAI function calling, which should be more reliable I would think. Thanks for creating+sharing.

https://microsoft.github.io/TypeChat/

That re-prompting error on is what this new Microsoft library does, too: https://github.com/microsoft/TypeChat

Here's their prompt for that: https://github.com/microsoft/TypeChat/blob/c45460f4030938da3...

I think the approach using grammars (seen here, but also in things like https://github.com/ggerganov/llama.cpp/pull/1773 ) is a much more elegant solution.

I'm very surprised that they're not using `guidance` [0] here.

It not only would allow them to suggest that required fields be completed (avoiding the need for validation [1]) and probably save them GPU time in the end.

There must be a reason and I'm dying to know what it is! :)

[0] https://github.com/microsoft/guidance

[1] https://github.com/microsoft/TypeChat/blob/main/src/typechat...