Skip to content
View KalyaniHari's full-sized avatar
1 follower · 2 following

Block or report KalyaniHari

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.

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
KalyaniHari/README.md

Hi, I'm Kalyani

AI Engineer focused on LLMs, Retrieval-Augmented Generation (RAG), and applied machine learning — building systems that put models into real, useful applications, from document Q&A assistants to healthcare fraud detection.

What I work on

  • LLM & RAG apps: retrieval pipelines, agents/tool use, conversational memory
  • Applied ML: classification, anomaly detection, model evaluation
  • Serving & data: FastAPI model APIs, PySpark data pipelines, vector stores

Tech

  • AI/ML: LangChain, OpenAI, RAG, ChromaDB, scikit-learn, XGBoost, PySpark
  • Serving / Backend: FastAPI, Node.js/Express
  • Languages: Python, SQL, JavaScript/TypeScript, Java, C#
  • Data & Cloud: MongoDB, MySQL, SQL Server, AWS S3, Power BI

Featured AI Projects

Project What it demonstrates
agentic-rag-knowledge-app RAG chatbot over your documents — LangChain + OpenAI + ChromaDB, with conversational memory
clinical-notes-ai-demo Applied ML: medication extraction + readmission prediction, served via FastAPI (XGBoost)
medclaim-guard-fraud-detection Data engineering at scale: PySpark ETL over 10M+ Medicare rows + anomaly detection
rag-document-qa FastAPI document Q&A assistant with retrieval and tool use
course-registration-system End-to-end full-stack delivery (React + Express + MongoDB)

📫 Connect

Pinned Loading

  1. agentic-rag-knowledge-app agentic-rag-knowledge-app Public

    RAG chatbot that answers questions from your documents (LangChain, OpenAI, ChromaDB).

    Python

  2. clinical-notes-ai-demo clinical-notes-ai-demo Public

    Medication extraction and 30-day readmission prediction, served as a FastAPI ML API (XGBoost).

    Python

  3. medclaim-guard-fraud-detection medclaim-guard-fraud-detection Public

    Medicare claims fraud detection and analytics with PySpark and Power BI.

    Jupyter Notebook

  4. rag-document-qa rag-document-qa Public

    FastAPI document Q&A assistant with RAG and simple tool use.

    Python

  5. course-registration-system course-registration-system Public

    Full-stack course registration app built with React, Express, and MongoDB.

    JavaScript 1

  6. rag-data-pipeline rag-data-pipeline Public

    Data ingestion and parsing pipeline for a RAG system (work in progress).

    Jupyter Notebook