Projects

Production AI systems designed, built, and deployed — case studies in agentic AI, RAG, knowledge graphs, and healthcare applications.

Production

CogniMail AI

Autonomous email intelligence system using multi-agent orchestration

An agentic AI system that autonomously processes, categorizes, prioritizes, and drafts responses to emails using a multi-agent architecture with specialized worker agents coordinated by a supervisor agent.

PythonLangGraphOpenAI GPT-4FAISSFastAPIPostgreSQLRedis

View Case Study

Development

GraphRAG Movie Recommendation Engine

Hybrid recommendation system combining knowledge graphs with vector search

A movie recommendation engine that combines collaborative filtering, knowledge graph traversal, and semantic search for contextually aware, explainable recommendations — 25% better than collaborative filtering alone.

PythonNeo4jPyTorchSentence TransformersStreamlitFastAPIDocker

View Case Study

Research

Omkara Extractor

Knowledge graph construction pipeline from unstructured text

An LLM-powered pipeline that extracts entities, relationships, and structured knowledge from unstructured documents, building domain-specific knowledge graphs with 93% precision.

PythonLangChainNeo4jspaCyOpenAI GPT-4Hugging Face TransformersFastAPI

View Case Study

Production

PyPM

Production-ready Python package manager with true multi-version support

A Python package manager that eliminates dependency duplication across projects and supports true multi-version package isolation — tested with TensorFlow and complex dependency trees.

PythonpipGit

View Case Study

Development

SageLoRa

Parameter-efficient fine-tuning framework for domain-specific LLMs

A batteries-included LoRA fine-tuning framework that reduces costs by 90% while achieving 95% of full fine-tuning performance. Pre-built configurations for medical, legal, and scientific domains with automated evaluation and deployment.

PythonPyTorchHugging Face PEFTWeights & BiasesFastAPIDockerKubernetes

View Case Study

Development

Sarbeksyan (सर्वेक्षण)

Zero-budget survey platform built for Nepal and emerging markets

A fast, mobile-first, localized online survey platform designed for creators, brands, NGOs, and students in Nepal and emerging markets. Supports Nepali/Devanagari, local payments, and slow connections.

Next.jsTypeScriptSupabaseTailwind CSSVercelResendUpstash Redis

View Case Study

Frequently Asked Questions

What AI systems has Avishek Rauniyar built?

He has built CogniMail AI (multi-agent email intelligence), Omkara Extractor (knowledge graph construction from unstructured text), GraphRAG Movie Recommendation Engine (hybrid recommendation with knowledge graphs), and SageLoRa (parameter-efficient LLM fine-tuning).

What technologies does Avishek Rauniyar use in his projects?

Python, LangGraph, LangChain, Neo4j, PyTorch, FastAPI, PostgreSQL, FAISS, Docker, Kubernetes, and various LLM APIs including OpenAI GPT-4. Each project case study lists the full tech stack.

Where can I find the source code for these projects?

Source code is available on GitHub at github.com/Avishek8136. Each project page includes a direct link to its repository.