ChefMate is an AI-driven recipe assistant that uses Retrieval-Augmented Generation and a local LLM to provide context-aware cooking suggestions. It supports ingredient queries, recipe generation, and dietary filters through semantic search and real-time chat.

Retrieval-Augmented Generation (RAG) MCP server written in Go that runs locally in your machine

CoreML conversion of all-MiniLM-L6-v2 with a full SwiftUI demo, tokenizer implementation, model resources, and conversion script for easy on-device text embeddings.

A comprehensive comparative analysis system that implements and evaluates two approaches for answering questions based on company financial statements

A minimalistic Android app showcasing semantic search using ObjectBox and Lucene KNN, leveraging the MiniLM-L6-V2 embedding model and bert_vocab.txt for efficient retrieval.

VALORA AI is a Multimodal Pricing Prediction Model that uses textual and visual data to make precise predictions on product prices

Chat with your PDFs using FastAPI, LangChain, Qdrant, and Gemini — an async RAG pipeline built with love

The Sankalpiq Foundation AI Automation Suite is a comprehensive microservices-based Multiagent designed to automate critical NGO operations through intelligent micro agents. The solution addresses operational bottlenecks by implementing specialized micro-agents that handle specific organizational functions while maintaining seamless integration.

SemEval 2026 Task 8: Multi-Turn Retrieval-Augmented Generation (MT-RAG) - Implementations for Subtasks A, B, and C using Milvus, pgvector, MiniLM, Qwen models, and cross-encoder reranking.

Detect and analyze resource leaks in Android apps using method signature matching and NLP-based similarity detection.

A financial GenAI assistant that combines LLMs, RAG, AI agents, and SQL querying to allow users to interact with financial data, documents, and APIs using natural language.

Fully local and open-source AI study companion for lecture PDFs - with slide summarization, smart Q&A, and flashcard creation using LangChain and Hugging Face Transformers.

Improving retrieval quality for trading documents using all-MiniLM-L6-v2

POC RAG system using faiss-cpu, sqlite and gemini

Phishing URL detection using ML & LLM models