Full Stack Dev & Open Source Builder | Building LexGuard AI | Next.js, FastAPI & RAG pipelines

Sujal Meena  • Peerlist

• Designed and deployed an end-to-end ML-based warehouse optimization system to reduce resource wastage and improve logistics efficiency • Engineered feature pipelines using Python and Pandas, processing structured operational data to train predictive models • Applied optimization algorithms to improve inventory allocation, reducing simulated lead time and storage cost • Evaluated model performance using cross-validation, achieving robust generalization across unseen data distributions

Warehouse Optimization System ML Project · Py

Built a distributed incident root-cause analysis platform for DevOps/SRE teams ingesting live Prometheus alerts. → Feedback-aware RAG pipeline (LlamaIndex + ChromaDB) auto-generates root-cause hypotheses — cutting mean triage time by ~70% → Non-blocking FastAPI endpoints sustaining sub-200ms P99 latency under high-throughput alert bursts → Multi-tenancy, JWT auth, rate-limiting; deployed on Render + Vercel with CI/CD via GitHub Actions → Built chaos simulator to stress-test incident detection across microservices Stack: Python · FastAPI · LlamaIndex · ChromaDB · PostgreSQL · Prometheus · Docker · Next.js Live Url - https://sentinel-sre-zeta.vercel.app

Sentinel-SRE — AI-Powered Incident RCA Platfo

I built LexGuard AI because most AI legal tools are just standard API wrappers that hallucinate or struggle with specific legislation. With India's DPDP Act 2023 introducing massive penalty risks, companies need deterministic compliance auditing, not guesswork.Here is how the system actually works under the hood:Grounding LLMs in the DPDP Act (RAG Setup)Instead of relying on the LLM's pre-trained knowledge, I built a hybrid RAG pipeline using FAISS and SentenceTransformers (all-MiniLM-L6-v2) in the backend. - Uploaded policies are split into paragraph-sized chunks.- A custom scoring algorithm combines vector similarity, lexical overlap, and rule-based topic boosters (boosting terms like 'consent withdrawal' or 'grievance officer' to retrieve exact sections of the DPDP Act).- This guarantees that the context passed to the LLM is anchored directly to the actual legal provisions. Two-Tier Pipeline &amp; Fail-safes- For quick landing page widget runs, the app uses gemini-2.0-flash for high-speed triage.- For deep dashboard audits, it flags complex clauses and processes them using higher-parameter models.- If Gemini hits quota limits, the backend automatically fails over to Llama-3.3-70b via Groq using a Tenacity-based exponential retry wrapper. Core Auditing Features- Differential Policy Auditing: You can upload old vs. new versions of a privacy policy to track exactly which compliance issues were fixed, which were introduced, and which remain unchanged.- Privacy UX Scorecard: Calculates a readability grade, translates dense legal jargon into plain language, and audits "multilingual readiness" since the DPDP Act mandates regional language notices.- Data Retention &amp; Privacy: The database uses MongoDB TTL indexes to auto-purge uploaded policy files and audit reports once a session expires, aligning with data minimization rules.Tech Stack- Frontend: Next.js 14, Tailwind, shadcn/ui.- Backend: FastAPI, Docker, Docker Compose, FAISS, SentenceTransformers.- Database &amp; Auth: MongoDB Atlas + Supabase.- Payments: Razorpay (with webhook verification).- Deployment: Vercel Edge Serverless Proxies (to handle CORS/routing) and AWS EC2.Feel free to play around with the app or browse the codebase!GitHub: <a target="_blank" rel="noopener noreferrer" class="break-all link-break text-gray-500 hover:underline" href="https://github.com/sujalmeena7/lexguard-ai">https://github.com/sujalmeena7/lexguard-ai</a>