Skip to content

Add PosterLens to Perplexity Cookbook showcase #38

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

nickjlamb
Copy link

Description

Adding PosterLens to the showcase — an iOS app that transforms static scientific posters into interactive insights using OCR and Perplexity’s Sonar Pro API.

Type of Contribution

  • Showcase Project

Checklist

  • My code follows the cookbook's style guidelines
  • I have included comprehensive documentation
  • I have tested my code and it works as expected
  • I have included all necessary dependencies and setup instructions
  • My MDX file includes proper frontmatter (title, description, keywords)
  • I have linked to any external repositories or live demos

Project Details

What problem does this solve?
Scientific posters are often packed with dense information, small fonts, and minimal context. PosterLens solves this by letting users scan a poster and explore it interactively using natural language — extracting meaning and surfacing related studies instantly.

What makes this contribution valuable to other developers?
PosterLens is a real-world example of combining OCR, LLMs, and Perplexity's Sonar Pro to improve how scientific content is explored. It shows how to create a seamless, on-device experience backed by powerful APIs.

External Links (if applicable):

Testing

Tested on iPhone running iOS 17, with working API key setup and demo use cases during Perplexity Hackathon 2025.

Screenshots (if applicable)

PosterLens Screenshot

Additional Notes

Uses:

  • Apple Vision for OCR
  • GPT-3.5 for natural-language Q&A
  • Perplexity Sonar Pro for semantic search and context
  • PubMed for citation validation

Thanks for reviewing!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant