Document AI
PDF parsing, OCR, RAG pipelines, document QA, and provenance tools
11 explainers
Document AI
production-agentic-rag-course: The RAG Course That Treats Search Like a System, Not a Demo
A production-first curriculum for building an arXiv research assistant with BM25, hybrid retrieval, LangGraph feedback loops, Airflow ingestion, and local model infrastructure.
Document AI
NiubiGEO: The Audit Trail for How LLMs See Your Brand
A TypeScript GEO tool that treats AI visibility like forensic evidence, preserving raw model responses, citations, and analysis history instead of hiding behind a proprietary score.
Document AI
TL-DR: How a Local LLM Turns Chaotic WhatsApp Chats Into Reliable Events
A privacy-first Python pipeline uses windowing, fuzzy matching, and anchor-based date resolution to extract deadlines from messy Hinglish group chats without sending data to the cloud.
Document AI
resume-book: ACM@UIUC Resume Book: The Campus Recruiting System That Turns PDFs Into Searchable Talent
A dual-auth, AI-assisted platform for students and recruiters, built like a real product rather than a form stack.
Document AI
ai-powered-aptitude-learning-app: QuizMania: The Adaptive Quiz Engine That Turns Wrong Answers Into the Next Lesson
A full-stack learning platform that combines spaced repetition, AI feedback, and weighted question selection to steer students toward what they actually need to study.
Document AI
Employee_Feedback_Analyzer: The HR AI Stack That Fits in One Monolith
A Java 21 and SQLite system that turns raw employee complaints into structured signals, then grounds HR answers in policy text without needing a vector database.
Document AI
employee_feedback_AI: The AI HR Tool That Refuses to Depend on One Model
A FastAPI and React app that combines offline sentiment rules, structured LLM output, and lightweight RAG to turn raw employee feedback into something HR can actually use.
Document AI
loansight: LoanLens AI: The Lending Pipeline That Treats Documents Like Evidence
A tri-service React, Node, and Python system that extracts financial data, cross-checks claims, caches expensive AI work, and turns loan review into an explainable workflow.
Document AI
ckd-detection: NephroScan, the CKD detector that tries to behave like a clinical tool, not a notebook
A Flask and React pipeline turns an imbalanced kidney dataset into risk scores, stage estimates, and a visual fingerprint of renal health.
Document AI
Maharashtra_Climate_Change: How One Dashboard Turns 51 Years of Monsoon Data into a Readable Regional Story
A Power BI and Python pipeline converts IMD gridded climate records into district-level trends, seasonal comparisons, and deviation analysis for Maharashtra.
Document AI
BananaCare-AI-Plant-Disease-Detection: BananaCare AI: The Leaf Scanner That Turns a Model Into a Farm System
A Spring Boot backend, a FastAPI inference service, and plantation history tracking show how one disease classifier becomes an operational tool for growers.