Source attribution with direct links to exact timestamps is truly unique when it comes to A/V RAG solutions.

Hey everyone,

I recently published a blog about data segmentation in Retrieval Augmented Generation (RAG) applications. It talks about the benefits of data separation as it applies to security, retrieval quality and control.

I'd love to hear what you think.

Thanks for posting the link!

CEO of Ragie here. Check out http://jfk-files.ai/ and let me know what you think. It's fun to play with and I've gotten pretty positive feedback so far.

A TypeScript first AI framework is something that has been missing. How do you work with AI SDK?

idk man

https://js.langchain.com/docs/introduction/

https://www.vellum.ai/products/workflows-sdk

https://github.com/transitive-bullshit/agentic

which is not to say any of them got it right or wrong, but it is by no means "missing". the big question w all of them is do they deliver enough value to last. kudos to those who at least try, of course

We originally were wrapping AI SDK, but that confused people who wanted to use both, so we decided to make the API more explicit, eg:

import { Agent } from "@mastra/core/agent"; import { openai } from "@ai-sdk/openai";

export const myAgent = new Agent({ name: "My Agent", instructions: "You are a helpful assistant.", model: openai("gpt-4o-mini"), });

Mine is written in TypeScript and I still think it's more ergonomic than anything else I'm seeing in the wild. Maybe there's finally an appetite for this stuff and I should release it. The Mastra dashboard looks pretty nice, might take some notes from it.

https://typedai.dev is another full-featured one I've built, with a web UI, multi-user support, code editing agents, CodeAct autonomous agent