Yash-Chindam

👋 About Me

class YashChindam:
    def __init__(self):
        self.name        = "Yash Chindam"
        self.role        = "AI / ML Engineer"
        self.focus       = ["LLMs", "RAG Systems", "Computer Vision", "NLP", "Deep Learning"]
        self.passion     = "Building AI systems that solve real-world problems"
        self.currently   = "Exploring Generative AI & multimodal research"
        self.hf_profile  = "https://huggingface.co/yashchindam"

    def say_hi(self):
        print("Thanks for dropping by! Let's build something intelligent together 🚀")

me = YashChindam()
me.say_hi()

🛠️ Tech Stack

Languages & Frameworks

AI / ML

LLMs & Models

Vector Databases & RAG

Data & Tools

🚀 Featured Projects

🧬 Drug-Protein Interaction Prediction

Predicts drug-protein binding strength (Ki values) using OpenAI's CLIP vision encoders on 2D molecular images & protein sequence logos.

Results: RMSE 0.6041 · MSE 0.3649
Stack: PyTorch CLIP RDKit Transformers CUDA

🗣️ AI Voice Onboarding System

Modular, scalable AI onboarding framework with multi-LLM support, vector stores, and guided setup workflows.

Stack: LangChain LlamaIndex FastAPI FAISS Pydantic

📄 Multi-PDF Chatbot with RAG & FAISS

Chat with multiple PDFs using Retrieval Augmented Generation powered by Mistral Nemo and FAISS vector search.

Stack: Mistral Nemo FAISS RAG LangChain

📑 RFP Document Info Extraction via LLMs

Automatically extracts structured information from RFP documents using few-shot prompting and chain-of-thought reasoning.

Accuracy: 85–92% · Speed: 30–60s/doc
Stack: GPT-4 LangChain Pydantic PyPDF2

👁️ Vision-Based Entity Extraction

Extracts named entities from images using OCR + NER pipeline. Supports forms, invoices, ID cards, and business cards.

Accuracy: Entity F1 80–92%
Stack: EasyOCR spaCy YOLO OpenCV Tesseract

🌿 ECO2 — Environmental ML Platform

Environmental sustainability platform for carbon footprint tracking, climate modeling, and biodiversity assessment.

Stack: GeoPandas Folium NetCDF4 scikit-learn Plotly

📺 YouTube Video Summarizer via Gemini Pro

Transcribes & summarizes YouTube videos using Google Gemini Pro with a clean Streamlit UI.

Stack: Gemini Pro Streamlit YouTube API

🎙️ Podcast Generator

AI-powered podcast script and audio generation pipeline using language models and TTS synthesis.

Stack: LLMs TTS Python

🏦 AI-Powered Bank Statement & Credit Report Analyzer

Finlyzer — Intelligent financial document analysis platform using Google Gemini AI to extract, categorize, and summarize transactions from bank statements and credit reports.

Pipeline: 9-step automated analysis · Parallel multi-key processing
Stack: Gemini Pro FastAPI Streamlit GCS Docker

🗣️ AI-Powered Natural Language to SQL Engine

NaturalSQL — Ask questions in plain English, get executable PostgreSQL queries instantly — powered by Defog's SQLCoder-7b-2 LLM.

Stack: SQLCoder-7b-2 PyTorch Cloud SQL Transformers pandas

🔍 Intelligent Claims Document Processing

ClaimLens AI — Agentic document-processing pipeline for US commercial property insurance that extracts structured data, generates summaries, and writes comprehensive claim notes.

Supported: 8+ document types · FNOL · Proof of Loss · Damage Photos
Stack: LangGraph Azure OpenAI GPT-4 Pydantic Datalab

🗂️ More Projects (click to expand)

Project	Description	Stack
RAG w/ LLaMA2 + LangChain + ChromaDB	End-to-end RAG pipeline using LLaMA 2	`LLaMA 2` `ChromaDB` `LangChain`
PDF Chatbot with RAG	Conversational PDF Q&A with RAG architecture	`RAG` `FAISS` `LLMs`
Conversational Q&A Chatbot — Mistral Nemo	Contextual, multi-turn chatbot using Mistral Nemo	`Mistral Nemo` `LangChain`
Image Captioning	Deep learning-based automatic image captioning	`PyTorch` `CNN` `LSTM`
License Plate Recognition	Automatic license plate detection and OCR	`OpenCV` `OCR` `Python`
Text Summarization — BART	Abstractive text summarization with BART	`BART` `Transformers` `HuggingFace`
Anime Title Generator — Flan-T5	Fine-tuned Flan-T5 for creative anime title generation	`Flan-T5` `HuggingFace`
Research Paper Title Generator — BART	Fine-tuned BART for academic title generation	`BART` `Transformers`
Movie Title Generator — Flan-T5	Flan-T5 fine-tuned for cinematic title generation	`Flan-T5` `HuggingFace`
Predicting Credit Card Approvals	ML classifier for credit card approval prediction	`scikit-learn` `Pandas`
Google Play Store Trend Analysis	EDA and trend analysis of Play Store app data	`Pandas` `Matplotlib` `Seaborn`
RAG Implementation & Prompt Optimization	Benchmarking and optimizing RAG prompt strategies	`RAG` `LLMs` `Python`

📊 GitHub Stats

🤗 Hugging Face

Published models & datasets on Hugging Face

Resource	Link
🧬 Drug-Protein Interaction Model	yashchindam/Drug-Protein-Interaction-Prediction-Using-CLIP-and-Deep-Learning
📦 Drug-Protein Dataset	datasets/yashchindam/Drug-Protein-Interaction-Prediction-Using-CLIP-and-Deep-Learning

🏆 Highlights

"The best way to predict the future is to invent it." — Alan Kay

Navigation Menu