Hello, I'm
Naresh Edagotti
Building production-ready RAG systems, AI agents, and AI-powered platforms
WHAT I BUILD?
Production-ready GenAI systems built with reliability, context, and real-world impact in mind.
Retrieval-Augmented Generation (RAG) Systems
I build RAG systems that are designed for real-world reliability, not just demos. My focus is on structuring knowledge correctly using effective chunking, embeddings, and retrieval so language models generate answers grounded in the right context. I pay close attention to retrieval quality, context injection, and reducing hallucinations in production environments.
AI Agents & Multi-Agent Workflows
I design AI agents that can reason, use tools, and complete tasks autonomously. Instead of treating agents as black boxes, I focus on clear control flow, task decomposition, memory, and orchestration. My goal is to build agent systems that are predictable, debuggable, and safe to use in real applications.
AI Automation & Knowledge Systems
I build AI-driven automation systems that turn unstructured data into usable knowledge. This includes automating content creation, extracting insights from documents and APIs, and integrating AI into backend workflows. I focus on reducing manual effort and scaling intelligence through well-designed, end-to-end AI pipelines.
about me
who am i ?
I’m Naresh Edagotti, a GenAI Engineer and Data Scientist focused on building production-ready AI systems, with a strong interest in retrieval-centric AI and system design.
Currently, I work at Hitloop as a Data Scientist & GenAI Engineer, where I build scalable GenAI systems with a focus on RAG pipelines, AI agents, and backend integration for real-world use cases.
Previously, I worked at Konam Foundation, where I designed and delivered end-to-end AI solutions across education and agriculture, including RAG-based systems, AI automation pipelines, and voice-enabled assistants.
Going forward, I want to continue building reliable GenAI systems that move beyond demos and create meaningful real-world impact.
My Projects
Basicrag - Lightweight RAG Pipeline
A powerful Python package that simplifies Retrieval-Augmented Generation (RAG) pipeline development. Supports multi-format document loading (PDF, DOCX, TXT, URLs), customizable text chunking, and integration with multiple LLM providers (Groq, Gemini, OpenAI). Enables developers to build production-ready RAG systems in minutes instead of hours.
Tech Stack: Python | RAG Architecture | Groq/Gemini/OpenAI APIs | Sentence Transformers
Finance News Intelligence System - Full Stack
An automated full-stack system that continuously fetches financial news from multiple sources, filters and deduplicates content using AI embeddings, structures articles with Gemini LLM for sentiment analysis, and stores enriched data in MongoDB. Features a React + Vite frontend with search capabilities and REST APIs. Runs autonomously every 2 minutes.
Tech Stack: FastAPI | React + Vite | MongoDB | Gemini API | Web Scraping | Tailwind CSS
TradeWise AI - Smart Trading Companion
A Streamlit-based web application for intelligent stock analysis combining real-time Yahoo Finance data with AI-powered forecasting using Ollama DeepSeek-R1. Generates interactive candlestick charts with technical indicators, provides price predictions, and creates AI-driven trading strategies with risk assessments for both Indian and global markets.
Tech Stack: Streamlit | Python | Yahoo Finance | Ollama DeepSeek-R1 | Plotly | Linear Regression
RAG + Text-to-SQL - Hybrid Query System
A hybrid system combining Retrieval-Augmented Generation (RAG) with Text-to-SQL for intelligent database querying. Converts natural language questions into SQL queries using Gemini API while simultaneously retrieving relevant context from PDF documents using FAISS embeddings. Synthesizes final answers by combining both database results and document context.
Tech Stack: Gemini API | FAISS | Text-to-SQL | Streamlit | SQLite | PyMuPDF
my Skills
Python, R, SQL, MongoDB
Hypothesis Testing, ANOVA, Time Series, Pandas,
NumPy, Scikit-learn, Power BI
Transformers, LLMs, Prompt Engineering, Context Engineering, RAG, AI Agents LangChain, LangGraph, CrewAI
FastAPI, PyTorch, TensorFlow, Docker, Pinecone, FAISS
Regression, Decision Trees, Random Forest, XGBoost, CNNs, RNNs, LSTMs
AI CONTENT & COMMUNITY
I actively share practical GenAI insights focused on building real-world, production-ready AI systems. I’m the creator of PracticAI and regularly post AI and GenAI content on LinkedIn, where I’ve built a 20K+ professional network. My content covers topics like RAG systems, AI agents, and production AI design, with a strong emphasis on how these systems work beyond demos.