Contra - A professional network for the jobs and skills of the future

Contra - A professional network for the jobs and skills of the futureA realtor or a business in need of python and LLM AI document processing? Here are some recaps of...

The network for creativity

Join 1.25M professional creatives like you

Connect with clients, get discovered, and run your business 100% commission-free

Creatives on Contra have earned over $150M and we are just getting started

Back to feedPost

Kyle Parsotan

• 2d

A realtor or a business in need of python and LLM AI document processing? Here are some recaps of my previous internship I did.

Just completed some advanced level python and LLM from extern for a mortgage company.

Check out some of the project I've worked on

Engineered AI-powered document processing pipelines for 200+ page mortgage files using OCR technologies including Tesseract OCR, PaddleOCR, and PyMuPDF, enabling scalable document extraction and parsing.

Developed a Retrieval-Augmented Generation (RAG) system using LlamaIndex for intelligent document search, classification, and contextual retrieval workflows.

Improved retrieval accuracy and system performance through embedding optimization, chunking strategies, vector search tuning, and intelligent routing logic.

Delivered technical documentation, demo UI, and evaluation reports validating OCR accuracy, retrieval precision, and system readiness for production deployment.

Github: https://github.com/Kyl67899/Outamation_Externship_internship

github.com

GitHub - Kyl67899/Outamation_Externship_internship

Contribute to Kyl67899/Outamation_Externship_internship development by creating an account on GitHub.

Maty Sandoval

max

• 2d

The OCR plus RAG pipeline for 200-page mortgage files sounds like a serious test of retrieval quality. Which document type caused the toughest extraction or chunking issue?

Luiz Cipriano

• Jul 16

Launch site for a sustainable luxury planned neighborhood in Bento Gonçalves, Brazil five towers, a hotel and retail in one concept. Interactive structure selector and WhatsApp-first lead capture.

AI Development Frontend Development Web Design GSAP JavaScript Laravel

Arafat Rahman

• Jul 16

Amazing Work!

Diya Garg

• Jul 16

I am a Computer Science and AI student offering affordable AI project development. I can build chatbots, dashboards, fraud detection models, and recommendation systems with clean, optimized code. If you want a reliable AI project at low cost, let’s connect and collaborate.

Subhash Gowtham Veer Turugopu

• 12h

Hii Divya,looking forward to connect with you 😊

Gabriele Mannino

• Jul 16

Vedetta AI: Autonomous Lead Prospecting Agent The Problem: B2B agencies spend countless hours manually searching platforms for leads and filtering out low-budget opportunities. The Solution: I built a custom Node.js autonomous agent that works 24/7. It continuously monitors data sources, parses unstructured text, and passes it through a strict Claude/Gemini scoring model to determine real commercial intent. It then drafts a highly personalized outreach message and pushes it to a Telegram channel for a 1-click human approval. It entirely automates the top of the sales funnel. Tech Stack (Skills da taggare): Node.js, TypeScript, AI Agents, Prompt Engineering, API Integration.