CopilotKit VS TypeChat

CopilotKit is an incredible tool that allows you to add AI Copilots to your products within minutes. Whether you're interested in AI chatbots and assistants or automating complex tasks, CopilotKit makes it easy.

Designed to alleviate exactly the pain points in the article.

Devs define simple Copilot entrypoints into state (frontend + backend + 3rd party), action, purpose-specific LLM chains, etc. And the CopilotKit engine takes care of the rest.

https://github.com/CopilotKit/CopilotKit

Star ⭐️

A drop-in replacement for any with the features of Github CopilotX (autocomplete, insertions, prompting). Context aware.

Everything is open-source and fully customizable. It is plugged in to OpenAI by default but you can literally run everything locally, including the LLM. It's built to be deeply customized and still work.

https://preview.redd.it/20rrkws3mp4c1.png?width=3071&format=png&auto=webp&s=90072ad62138ef1f251c248074ac1e7ce588f8c3

Please check it out and let us know what you think. If you like it, give us a star🌟 while you're there :)

Come join our journey 🗺️

---

Discord:

https://discord.gg/6dffbvGU3D

Github:

https://github.com/CopilotKit/CopilotKit

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...