> PROJECTS.DB // FEATURED

KEY PROJECTS

● ACTIVE

YouTube AI Helper

LLM-based system that converts long-form YouTube videos and playlists into structured notes, flashcards, and a queryable interface.

// Modular pipeline: transcript extraction → summarization → Q&A with multi-video context

// Explored limits of full-context prompting; working toward retrieval-based approaches

LLMsRAG (in progress)StreamlitPythonAgentic Workflows

> PROJECTS.DB // ALL

OTHER WORK

○ ARCHIVED

Content Recommendation Pipeline

Two-stage recommendation system: embedding-based retrieval + local LLM reranking.

// Cosine similarity retrieval paired with Llama 3B reranker on RTX 3090

// Designed a category-overlap evaluation metric — then mathematically invalidated it upon finding structural embedding space boundaries

Recommendation SystemsEmbeddingsLLM RerankingEvaluationPython
○ ARCHIVED

Vision-to-Text SOC

Vision-to-text pipeline for extracting structured information from image-heavy inputs.

// Combined OCR and NLP to convert visual data into usable text representations

// Focused on making extracted data structured and actionable rather than raw output

OCR PipelinesDocument UnderstandingNLPPython
○ ARCHIVED

WIDS 2025 Agentic AI

Agentic AI system exploring multi-step reasoning and tool-based workflows.

// Modular agents for task decomposition, routing, and response generation

// Explored limits of agent reliability, control flow, and hallucination handling

Agent SystemsLLMsTool UsePrompt Orchestration