Skip to content
View S84v's full-sized avatar
📖
Learning
📖
Learning
6 followers · 13 following

Block or report S84v

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
S84v/README.md

Hi, I'm Sarang Dave 👋

AI / Applied-AI Engineer — I build production-grade LLM & RAG systems with the data-engineering discipline to run them reliably: idempotent ingestion, streaming, observability, and evaluation.

📍 Gujarat, India · ✉️ davesarang08@gmail.com · 🔗 LinkedIn

What I build

Project What it is Highlights
production-rag Production-oriented RAG — ingestion → retrieval → streaming generation SHA-256 idempotent & versioned ingestion · PostgreSQL + Qdrant split · retrieval evals (Precision@K / MRR) + DeepEval · OpenTelemetry · Docker
plant-disease-classifier End-to-end deep-learning web app (PyTorch + FastAPI) 99.04% validation accuracy · ~99% weighted precision/recall/F1 over 38 classes · top-5 confidence + disease metadata · Dockerized & tested
cli-ai-assistant Context-engineered terminal LLM app streaming · multi-turn memory · automatic context summarization · token tracking

Focus areas

LLM & RAG · AI agents · LLM evaluation & observability · Python / FastAPI · PyTorch · data engineering (Airflow · Doris · Iceberg)

Writing

  • Medium — notes on AI engineering and ML fundamentals

Open to AI / Applied-AI / ML roles — remote or onsite in India.

Pinned Loading

  1. production-rag production-rag Public

    Full-stack document question-answering application built around a production-oriented RAG architecture.

    Python

  2. plant-disease-classifier plant-disease-classifier Public

    End-to-end deep learning web application for plant disease classification using PyTorch, FastAPI, Docker, and ResNet18.

    Jupyter Notebook

  3. cli-ai-assistant cli-ai-assistant Public

    Context-engineered terminal LLM assistant — streaming, multi-turn memory, automatic context summarization, token tracking.

    Python