SYSTEM STATUS: ONLINE // BANGALORE (IST)
[ENV: FASTAPI · OLLAMA · CUDA · DOCKER · RAGAS]
🔍
SHOWING 12 / 12 SYSTEMS Click "Inspect Architecture" for system workflows

Risk Minor

PRODUCTION

Multi-agent risk intelligence platform built for regulatory compliance workflows at Hansraj Ventures. Combines dense and sparse retrieval with a fine-tuned LLM, full evaluation tracing, and input/output safety guardrails in a single coherent pipeline.

// Architecture

  • Hybrid retrieval: BM25 keyword search + Milvus dense vector search running in parallel; results merged via reciprocal rank fusion (top_k=12) before passing to the LLM context window.
  • LLM layer: LoRA-fine-tuned Llama 3.1 8B served via FastAPI with CUDA inference; guardrails enforce output format, hallucination checks, and regulatory policy compliance before any response is returned.
  • Observability: Full RAGAS eval harness (faithfulness, answer relevancy, context recall) + Langfuse distributed tracing across all pipeline nodes — every inference logged with latency, token counts, and eval scores.
  • Infra: Async FastAPI microservices containerized with Docker CI/CD; 40% latency reduction, 99%+ uptime in production at Hansraj Ventures.
FastAPIMilvusRAGASLangfuseLlama 3.1Docker
Hansraj Ventures (Private) ⚡ 38ms p95
01. User Query → FastAPI Async Handler
02. BM25 Sparse + Milvus Dense Vector Search (Parallel)
03. Reciprocal Rank Fusion (RRF top_k=12)
04. LoRA-adapted Llama 3.1 8B CUDA Generation
05. RAGAS Verification (0.94 Faithfulness) → Langfuse Trace

Banking Compliance RAG

OPEN-SOURCE

End-to-end financial compliance system combining classical machine learning with retrieval-augmented generation to answer natural language regulatory queries over banking policy documents in real time.

// Architecture

  • ML layer: Multivariate regression pipeline trained on loan-default and risk-scoring datasets; integrated directly into response generation to provide quantitative compliance context alongside retrieved text.
  • Retrieval: FAISS dense vector index + Qdrant persistent vector DB for hybrid retrieval across RBI and banking regulation corpora; BM25 reranking applied before final context assembly.
  • Validation: Citation verification module cross-checks every LLM output claim against the source document passages; rule-based validators enforce domain-specific banking policy constraints.
  • Storage: SQLite for document metadata, conversation history, and audit logs; LangChain orchestrates the full retrieval-generation chain.
LangChainFAISSQdrantScikit-LearnSQLite
github.com/Chetanchhetri ↗ 🎯 94% Precision
01. RBI Circular & Loan Dataset Ingestion
02. FAISS + Qdrant Hybrid Index Search
03. Multivariate Risk Regression Scoring
04. Citation Grounding & Policy Validation

AstraRoute Navigation Engine

OPEN-SOURCE

Full-stack, disaster-resilient navigation platform engineered for high-risk climate corridors. Dynamically calculates safe perimeter detours around real-time climate hazards and breaking news bounding boxes.

// Architecture

  • Disaster Scraping: Background workers monitor news RSS feeds using Scrapling and BeautifulSoup to auto-extract disaster locations into spatial hazard boxes.
  • Perimeter Routing: Evaluates OSRM polyline intersections against MongoDB hazard coordinates to dynamically compute cardinal (N, S, E, W) detour vectors.
  • Live Weather & Crowdsourcing: Queries Open-Meteo forecast API across route waypoints while accepting authenticated community hazard reports on Leaflet.js.
FastAPIMongoDBLeaflet.jsOSRMScrapling
github.com/AstraRoute ↗ ⚡ Live Demo ↗
01. Scrapling Disaster News Scraper → Bounding Box Parser
02. MongoDB Geospatial Index Query
03. OSRM Waypoint Intersection & Perimeter Vector Calculation
04. Leaflet.js Real-time Render + Open-Meteo Alerts

AI Blur & Defect Detector

OPEN-SOURCE

Assessment-ready computer vision pipeline and REST API that automatically evaluates image quality metrics, detects structural blur, exposure anomalies, and noise levels.

// Architecture

  • Quality Analytics: Computes OpenCV Variance of Laplacian for blur detection alongside grayscale standard deviation differences for noise estimation.
  • Scoring & Persistence: Combines multi-issue metric deductions into an interpretable 0–100 quality score, logging full evaluation history to SQLite.
  • Deployment: Asynchronous FastAPI backend paired with a dynamic JavaScript UI, containerized using Docker Compose for instant deployment.
FastAPIOpenCVSQLiteDockerJavaScript
01. Image Upload → Stream Buffer Validation
02. OpenCV Laplacian Variance + FFT Frequency Analysis
03. Multi-Metric Penalty Matrix → 0-100 Quality Score
04. SQLite Audit Log & JSON API Response

Fact Check Multi-Agent (VeriCore)

OPEN-SOURCE

Fake-news and misinformation detection engine that queries three locally-running LLMs in parallel and aggregates their verdicts through a consensus scoring layer, dramatically reducing single-model hallucination and bias.

// Architecture

  • Model ensemble: Qwen2:0.5B, Phi-3:latest, and LLaMA 3.1:latest queried simultaneously via Ollama; each returns a structured verdict (TRUE / FALSE / UNVERIFIED) with confidence score and reasoning chain.
  • Consensus engine: Weighted majority voting across the three verdicts; disagreements trigger a fourth "tiebreaker" call with a larger model context window.
  • Live context: Optional DuckDuckGo web search module injects real-time news snippets as additional context before the consensus round — addresses recency gaps in local model training data.
  • Evaluation: RAGAS faithfulness metrics validate each model's reasoning against its cited context; disagreement deltas tracked per model to identify consistent bias patterns.
StreamlitOllamaRAGASMulti-AgentPython
github.com/Chetanchhetri ↗ ⚡ 3 Local Models
01. User Claim Input → DuckDuckGo Live News Context Fetch
02. Async Query to Qwen2 + Phi-3 + LLaMA 3.1 (Ollama)
03. Weighted Consensus Voting & Reasoning Aggregator
04. RAGAS Grounding Verification & Final Confidence Score

Intelligent Proxy Gateway (IPG)

OPEN-SOURCE

Four-stage LLM request optimization middleware deployed as both a Flask/FastAPI backend and a Chrome Manifest V3 extension — routes queries intelligently between local on-device models and cloud LLMs based on task classification and cost.

// Pipeline Stages

  • Stage 1 — Prompt Reformulation: Rewrites incoming queries for improved clarity, specificity, and instruction alignment before routing begins.
  • Stage 2 — Security Filtering: Scans for prompt injection patterns, jailbreak attempts, and PII leakage using rule-based and embedding-similarity checks; blocks or sanitizes before forwarding.
  • Stage 3 — Task Triage: Classifies request complexity (simple/medium/complex) and routes to the appropriate model: local Ollama models (Mistral, Phi-3) for lightweight tasks; cloud LLM fallback (OpenAI/Anthropic) for complex reasoning.
  • Stage 4 — Token Optimization: Compresses context window before final LLM call via extractive summarization, reducing token cost by up to 35% on long-context requests.
FastAPIFlaskOllamaChrome ExtensionMV3
github.com/Chetanchhetri ↗ ⚡ 35% Cost Cut
01. Prompt Reformulation & Instruction Sanitization
02. Injection & PII Scanning (Cosine Guardrail)
03. Complexity Triage: Local Ollama vs Cloud Fallback
04. Token Compression & Response Cache Hit

RAG · Airbus FCOM

RESEARCH

Ultra-high-precision retrieval-augmented question-answering system grounded in Airbus Flight Crew Operating Manual (FCOM) documentation — a domain where factual errors are operationally unacceptable.

// Architecture

  • Document processing: FCOM PDFs parsed with structure-aware chunking preserving section hierarchy, chapter numbering, and callout blocks; custom metadata tagging enables procedure-level retrieval.
  • Retrieval: Dense vector index with re-ranking optimized for precision over recall — every retrieved chunk must be from the correct section and version of the manual.
  • Faithfulness guardrail: Every generated answer traced back to source passage citations; any answer with insufficient grounding returns a confidence warning rather than a fabricated response.
PythonRAGVector DBPDF Parsing
github.com/RAG_AIRBUS-FCOM ↗
01. FCOM Document Hierarchy & Procedure Chunking
02. Precision Vector Indexing & Chapter Metadata Filtering
03. Reranking (Cross-Encoder Precision Priority)
04. Flight Procedure Citations & Strict Non-Fabrication Check

Local Co-pilot

OPEN-SOURCE

On-device AI coding assistant extension for VS Code, built on Ollama for fully offline, zero data-leakage developer workflows with real-time code completion and context-aware suggestions.

// Architecture

  • Context engine: Sliding window context manager maintains relevant code context (open file, cursor position, recent edits, imports) for accurate completions without exceeding model context limits.
  • Local inference: Routes completions to Ollama-served models (Codestral, DeepSeek-Coder, Phi-3) — no data leaves the machine; works fully offline.
  • VS Code API integration: Custom inline completion provider with debounced triggering; separate command palette integration for longer generation tasks like docstring generation and test scaffolding.
OllamaVS Code APIPythonTypeScript
github.com/Local_Co-pilot ↗ 🔒 100% Offline
01. VS Code Cursor Position & Sliding Context Window
02. Debounced Local IPC Stream to Ollama (Codestral/DeepSeek)
03. Low-latency Token Stream Completion Provider

Image Enhancer

OPEN-SOURCE

Computer vision pipeline combining super-resolution and intelligent denoising for automated image quality improvement — built as companion infrastructure for specialized vision models with degraded input data.

// Architecture

  • Super-resolution: ESRGAN-based upscaling pipeline achieving 4× resolution enhancement with perceptual loss training for natural detail preservation over pixel-accuracy MSE.
  • Denoising: Adaptive bilateral + DnCNN hybrid approach; noise level estimation module selects denoising strength dynamically per-image rather than using a fixed filter.
  • Pipeline integration: Exposes a REST API endpoint for batch processing and integrates as a preprocessing stage for downstream vision classifiers — designed for VRAM-constrained environments.
TensorFlowOpenCVPythonESRGAN
github.com/Image-Enhancer ↗ ⚡ 4× Upscale
01. Noise Variance Estimation Module
02. DnCNN Adaptive Denoising Filter
03. ESRGAN Generator 4× Perceptual Upscaling
04. Batch REST API Payload Response

Potato Disease Classifier

OPEN-SOURCE

CNN-based agricultural leaf disease detection system identifying early blight, late blight, and healthy potato plants from field images — designed for high-throughput inference in resource-limited agricultural environments.

// Architecture

  • Model: Custom CNN architecture trained on the Plant Village dataset; data augmentation pipeline (rotation, flipping, color jitter, Gaussian noise) improves generalization to real-world field photography conditions.
  • Optimization: Post-training quantization to INT8 reduces model size by 75% while maintaining accuracy within 2% of the full-precision baseline; enables deployment on edge devices and mobile inference.
  • Inference throughput: Batch inference pipeline with TFServing for production deployment; ~120 images/sec throughput on a single consumer GPU.
TensorFlowCNNKerasTFServing
github.com/potato-disease-classifier ↗ ⚡ 120 img/sec
01. Leaf Image Ingestion & Color Space Normalization
02. INT8 Quantized CNN Inference (Edge-optimized)
03. Softmax Multi-class Diagnosis & Severity Score

Civic Connect Engine

OPEN-SOURCE

Smart India Hackathon (Internal Round Winner) project — CNN classifier for detecting urban civic hazards (potholes, garbage, damaged infrastructure) from crowdsourced citizen photos, integrated with GCP microservices for automated complaint routing.

// Architecture

  • Classifier: Transfer-learning on MobileNetV2 fine-tuned on a custom civic hazard dataset; achieved 91% validation accuracy across 8 hazard categories with a balanced precision-recall tradeoff.
  • Crowdsourced pipeline: Mobile photo uploads routed through GCP Cloud Storage → Cloud Run inference container → automated complaint ticket creation in the civic management system based on predicted hazard type and severity score.
  • Infra: Fully containerized with Docker; GCP Cloud Run autoscaling handles variable citizen submission volumes; image metadata (GPS, timestamp) attached to every complaint for geographic routing.
TensorFlowCNNDockerGCPMobileNetV2
github.com/Civic-Connect ↗ 🏆 SIH Winner · 91% Acc
01. Citizen Mobile Upload → GCP Cloud Storage
02. MobileNetV2 Cloud Run Container Inference
03. GPS Tag Extraction & Municipal Ward Routing
04. Automated Ticket Creation & Severity Dispatch

NetScan Pro

OPEN-SOURCE

High-performance network reconnaissance utility for discovering active hosts, enumerating open ports, fingerprinting service banners, and building a structured inventory of network topology — built as a developer security research tool.

// Architecture

  • Host discovery: Multi-threaded ICMP ping sweep with configurable concurrency and timeout parameters; CIDR range parsing for subnet-level scans.
  • Port scanning: SYN, TCP Connect, and UDP scan modes with configurable port ranges; banner grabbing for common service identification (HTTP, SSH, FTP, SMTP, etc.).
  • Output: Structured JSON and CSV export of scan results with service version fingerprints; designed for integration into broader security pipeline workflows.
PythonSocketsThreadingNetworking
github.com/NetScan_Pro ↗
01. CIDR Subnet Parser & Concurrent ICMP Sweeper
02. Async TCP/UDP SYN & Connect Port Scanner
03. Service Banner Grabbing & Fingerprint Matching
04. Structured JSON/CSV Export Engine
LIVE_DEMO

Want a walkthrough of any architecture?

I can walk through retrieval code, LoRA fine-tuning setups, or eval harness implementations live on a call.

› ESC to close
Navigation
🏠 01. Home Overview
Page
💼 02. Experience & Internships
Page
🚀 03. Projects (12 Systems)
Page
👤 04. About & Tech Stack
Page
✉️ 05. Contact & IDE Shell
Page
Featured Systems
⚡ Risk Minor (Milvus + LoRA Llama 3.1)
RAG
🗺️ AstraRoute Navigation Engine (OSRM + Scrapling)
Infra
👁️ AI Blur & Quality Detector (OpenCV API)
Vision
✈️ Airbus FCOM Precision QA Engine
RAG
Quick Actions
◐ Toggle Theme (Dark / Light)
Action
📋 Copy Email (chhetrichetan45@gmail.com)
Clipboard
🔊 Toggle Audio FX Sounds
Setting