寻星SeekStar-互联网探索引擎 寻星 是一种面向未来的浏览器 / 搜索引擎形态构想。通过AI驱动的3D 语义望远镜：把互联网万物折叠成可漫游的星空。输入关键词 → 进入三维语义空间 → 调焦、闲逛、跃迁，发现列表页永远到不了的冷门站点、商品与视频。支持 Web/VR 双模式，开源全流程。 它不再以传统的关键词匹配和线性列表作为信息探索的入口，而是以地图化 / 星图化的方式，展现知识的关联、创作者的聚集，以及那些尚未被命名的领域。 在“寻星”中， 你看到的，不是结果的排序， 而是信息的引力场； 不是冷静的检索， 而是温柔的靠近。

A Java implementation of HNSW with multi-vector search support

A Streamlit-based platform offering Ayurvedic remedies. Users can ask queries and complete a questionnaire to discover their dosha (body constitution).

A universal AI and MCP-powered plugin for Logitech's Actions Ring that adapts to the user's workflow.

A project that uses Large Language Models (LLMs) to assist users with legal inquiries, particularly based on the Indian Penal Code (IPC). LegalMind provides case summarization, user-specific legal guidance, and recommendations from past case data.

vectorizing data from mysql database to vector so it can be used by LLM in Dify workflow orchestration

Open Source Hybrid AI Search Application Based OpenAI, Serp, SearXNG, LanceDB...

Multi Modal Agent using Deepgram and Groq LPU's and Sentence Transformers for Vector Embeddings, ChromaDB for persistent vector db storage and BM25 with ColBERT reranking for hybrid search for RAG context management

Retrieval-Augmented Generation chatbot built with Next.js 15, Groq AI, HuggingFace embeddings, Clerk auth, and Neon PostgreSQL. Chat with your PDFs intelligently.

Developed an intelligent cologne recommendation platform that uses semantic search and natural language processing (NLP) to match users with fragrances. Users can describe their scent preferences in everyday language (e.g., “I’m looking for something sweet but masculine”).

Lightweight RAG system using OpenAI embeddings and ChromaDB for local document search and retrieval.

A prototype for the SIH 2024 Police Department, where users can speak about a crime scenario and receive relevant IPC sections that apply to the situation.

A test project integrating FAISS vector embeddings with Gemini, deployed on Streamlit Cloud.

The Personal Portfolio RAG Agent is a live, production-ready demonstration of end-to-end AI system engineering. More than a Q&A bot, it acts as a knowledge-grounded expert on my professional profile.

A Semantic Search Engine that solves the "Vocabulary Mismatch" problem. Uses Transformers (BERT) to match User Intent rather than Keywords. Features an AI Happiness Score for quality-first ranking.

An AI-based tool that allows users to upload documents and receive concise summaries and Question-Answering on that Document. The system utilizes vector embeddings to capture key details from the content, enabling quick and accurate response on prompt.

I post my practices in this repository.

RAG chatbot using car manual data to answer MG ZS warnings via GPT-4o and LangChain.