LLM

View Code Overview TokenSmith is a retrieval-augmented QA pipeline for technical textbooks, designed to reduce “semantic miss” failures by combining sparse keyword matching with dense embedding retrieval, then re-ranking candidates with an ensemble ranker. Key Achievements Hybrid retrieval (dense + sparse) to improve coverage on exact terminology and equations-heavy text. EnsembleRanker supports Reciprocal Rank Fusion (RRF) and weighted score fusion for configurable ranking behavior. Stable evaluation harness with structured logging to debug retrieval failures and measure end-to-end answer quality. Technical Implementation Retrieval: FAISS for dense similarity + BM25 for keyword recall, merged via fusion strategies. Ranking: Config-driven EnsembleRanker stage to combine multiple retrievers and optionally add lightweight feature-based scoring. Inference: Pluggable LLM backend (local or hosted), with chunking and provenance attached to retrieved passages. Inference: Support for llama.cpp inference and document chunking Impact This RAG pipeline enables efficient querying of large document collections, making educational content more accessible and searchable through natural language interfaces. ...

View Project Report | View Code Overview A cross-platform mobile application that provides real-time lecture transcription, AI-powered summaries, and intelligent Q&A to enhance learning efficiency. Key Achievements 30% improvement in lecture review efficiency during pilot tests with 50+ students 41% higher engagement and 2× faster response times through A/B testing on note layouts and Q&A interface Fault-tolerant Whisper + LLM pipeline for reliable real-time processing Technical Implementation Architecture Frontend: React Native for cross-platform compatibility Backend: Flask with Python Celery for distributed task processing AI Pipeline: Whisper for speech-to-text, LLM for summarization and Q&A Infrastructure: Azure cloud services for scalability Design: Figma for UI/UX design and prototyping Key Features Real-time transcription using advanced speech recognition AI-generated summaries with key points and concepts Intelligent Q&A system for lecture content A/B testing framework for continuous improvement Fault-tolerant processing for reliable performance Results 30% efficiency gain in lecture review during pilot tests 41% higher engagement through optimized user interface 2× faster response times for Q&A interactions Positive feedback from 50+ beta users across multiple institutions View on GitHub →