Skip to content
View Yamini26284's full-sized avatar
🎯
Focusing
🎯
Focusing
2 followers · 0 following

Block or report Yamini26284

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Yamini26284/README.md

Hi, I'm Yamini 👋

I build production ready LLM applications and agentic AI systems.

What I'm working on

  • 🤖 Real-time AI agents with multimodal capabilities
  • 🔍 RAG pipelines and context engineering
  • ⚡ Production-ready AI backends with FastAPI

Projects

Project What it does
Vision Agent Real-time AI interviewer with body language detection
RAG - LangGraph A RAG backend built to never bluff, every answer traced to a real source, or refused outright
Context Excavator Reduces LLM token usage 40-50% via semantic code filtering
Cross Lens Adverserial RAG system
Coffee Barista Agent AI assistant recommending personalized coffee orders using RAG, deployed on Cloud Run
Coffee-shop-agent AI agent that can analyze coffee shop data writes staffing recommendations, with human-in-the-loop approval
bigQuery-data-agent AI agent built with ADK + Gemini that answers business questions using BigQuery data via MCP server, deployed on Cloud Run

Stack

Python · LLMs (OpenAI, Anthropic, Groq, Gemini) · LangChain · LangGraph · RAG Systems · Agentic AI · Vector Databases (Pinecone, ChromaDB, FAISS) · FastAPI · Streamlit · Docker · YOLO · Git · PostgreSQL

📫 yamini26284@gmail.com Linkedin : https://www.linkedin.com/in/yamini26284/

Pinned Loading

  1. Context-Excavator Context-Excavator Public

    Context Excavator solves a real problem: when you paste large codebases into ChatGPT, the AI gets lost in noise. You're feeding it 500 lines of code when only 20 lines actually matter. The LLM can'…

    Python 4

  2. Vision-Agent Vision-Agent Public

    Vision Agent is a real-time AI interview coach that gives you instant feedback on your performance based on posture, clarity, confidence, everything

    Python

  3. cross_lens cross_lens Public

    Advanced RAG system that verifies claims by finding evidence on both sides of any document.

    Python

  4. coffee-barista-agent coffee-barista-agent Public

    AI coffee shop assistant using Google ADK, Gemini, and RAG deployed on Cloud Run

    Python

  5. rag-langGraph rag-langGraph Public

    A RAG backend that answers questions from documents, with real citations and honest refusals, built with LangGraph, Pinecone, and FastAPI.

    Python

  6. cinema-ticketing-fullstack-webapp cinema-ticketing-fullstack-webapp Public

    Full-stack cinema seat-booking system with live seat maps, time-limited holds, and concurrency-safe payment transitions. Built with Hono, React, PostgreSQL, and Drizzle ORM.

    TypeScript