Tony Sellprano

Our Sales AI Agent

Back to all case studies
ViewAI: Native Mac App for Scientific Paper Chat

RAG, Embeddings & macOS

ViewAI: Native Mac App for Scientific Paper Chat

Project by Kryštof Mitka

Pioneering Local-First AI for Research

Developed a native macOS app for PDF chat using a custom RAG pipeline with GPT-4, *before* mainstream tools offered similar local-first capabilities.

Advanced Scientific Paper Processing

Engineered robust PDF parsing (Nougat & LaTeX) for accurate vector embeddings and RAG, handling complex scientific notation and structure.

Native macOS AI Experience

Crafted a high-performance, Swift-based native app, showcasing seamless AI integration within the Apple ecosystem for an optimal user experience.

Context

Before it became possible to casually chat with PDFs inside ChatGPT, there was a gap for people who wanted a fast, local, native experience to deeply interact with research papers. ViewAI was built to fill that need.

What It Was

ViewAI was a native macOS app designed by Kryštof Mitka. It let users open any scientific paper (PDF), view it cleanly in a two-panel layout, and instantly ask questions about the content using a GPT-4-powered retrieval-augmented generation (RAG) stack.

It was built during a time when no easy, off-the-shelf tools existed to achieve this with speed, quality, and local control. Everything from parsing to vector search had to be custom built.

Features

  • Local parsing of PDFs using Nougat for structure extraction
  • LaTeX math rendering support
  • Embedded vector search on-device using scientific text chunks
  • GPT-4 used for answering questions via RAG architecture
  • Clean native UI/UX in Swift, focused on speed and simplicity

Tech Stack

  • Swift (native macOS)
  • Nougat (for PDF to structured data)
  • LaTeX rendering engine
  • GPT-4 API
  • Custom vector embedding store

Outcome

ViewAI served as an early glimpse into what user-friendly, AI-native interfaces could look like for academic work. It helped validate the demand for structured, smart interactions with scientific content—long before the mainstream tooling caught up.

This was a small but sharp experiment that Kryštof led and executed, showing what was possible with the right combination of AI infrastructure and product intuition.

Ready to work together?

Let's discuss your project.

Contact Us