ulidabess

Awesome, thanks!

Awesome project. I was looking through the Github and if I understand correctly, then it's plugged in to the OpenAI API by default?

Is there an option for using other LLMs with it?

An experiment comparing information retrieval performance between Open AI's Assistants API's RAG, GPT-4 Turbo (with context window stuffing) and Llama Index with GPT4.

Pretty striking results, especially when it comes to how the Assistants API beats Llama Index and how useless context-window stuffing is.

ShowHN: CopilotKit is an open-source library for embedding an AI-Copilot into any react app within ~1hr.

How it works: Wrap your app in CopilotProvider. Use useMakeCopilotReadable(...) to share nuanced app state with Copilot.

Leverage useMakeCopilotActionable(...) to let Copilot perform tasks like form submissions. Get a live Copilot within an hour, and embedded deeply.

An Open-source stack that makes it easy to integrate POWERFUL Plug and play copilot features to react applications:

1. Copilot <textarea>: drop-in replacement for any <textarea> complete with AI autocomplete (like Github copilot) and insertions.

2. Copilot Portal: a 'chatGPT inside your app'. Reads your app state, answers questions and takes actions based on prompts.

The post-AI way to engage with the podcast ecosystem. The AI listens to every episode the comes out, finds the best coherent segments for every user (based on their textual self description, and soon Twitter graph as well).

It sends these segments to any podcast app via a personalized RSS feed.

The podcast episodes become the source material for a newsfeed of personalized segments. Means you can get value of pod episodes without having to listen to the full thing.

Segments also jump to the point, skipping long intros, ads & chit-chat which we somehow tolerate in pods (but you'd never watch a YouTube video that took 15 mins to start).

Looks awesome dude. Might experiment with integrating this over the weekend.