Harsh Arora

🚀 Built an Agentic AI WhatsApp bot. User message → classify → router → specialized agents (Code, Content, Math) → review → reply. Each agent uses different LLM configs & temperature tuning for task-specific responses. Built using FastAPI + LangChain.

Built a fully async RAG system 🚀 ⚡ FastAPI 🔁 Redis Queues + Workers 🧠 Qdrant 🤖 OpenAI Flow: User → /chat → Redis Queue → Worker (embed → retrieve → generate) → Store → /result/{job_id} No blocking. Scalable. Production-ready. GitHub: github.com/harsharora05/d…

Why It Matters? Without RAG → LLM guesses With RAG → LLM answers using context.

Phase 2: Retrieval • User sends query • Convert query into embedding • Similarity search • Send relevant chunks + query to LLM

RAG is how you turn LLMs from guessing machines into knowledge-powered systems. Here’s how RAG actually works (in simple terms) 🧵👇

Built my first CLI Weather Agent 🌦️ Used tool calling to fetch real-time weather data. Biggest learnings: • Prompt quality matters more than I thought • Explored prompting styles: Direct, One-shot, Few-shot & Chain of Thought • Better prompts = smarter agents

One step toward Gen AI 🚀 asyncio in python feels a lot like async/await in JS called corutine in python same event-loop magic. Big takeaway: thread pools for I/O-bound work, process pools for CPU-heavy tasks, and daemon threads for background jobs that shouldn’t block shutdown.

Goals for this year :- 1. AWS Cloud Practitioner Certification 2. Learn remaining devops conceps like Kubernetes, Grafana etc 3. Learn Gen Ai concepts 4. Build more while learning 5. Grab better opportunities

Joined as Infosys an Intern🙂.

Dived deep into Auto Scaling Groups in AWS today. Set up an EC2 instance → created an AMI → built a launch template → configured target groups + load balancer (round-robin) → and finally an Auto Scaling Group with dynamic & scheduled scaling policies. Loved AWS elasticity

Exams: DONE ✅ Brain: REBOOTED ⚡ Back on X after a month — ready to dive back into projects, code, and build cool stuff! 🚀💻

Stateless servers that just talk to the DB can scale horizontally - add more instances as CPU or requests/sec increase. But if your backend does heavy computation, use queues + workers. Workers pick a task, process it, then grab the next. Scale workers up or down based on load.⚙️

After hours of debugging and learning new things, I finally got it working! 🚀 CI/CD pipelines, AWS setups, Docker containers… so much to absorb, but persistence paid off.

Never thought doing a master’s from a private college in India would be this hectic — from attendance pressure to writing composition. They drain students so much that there’s no energy left to upskill — but we still push harder and make time for it.

🚀 How do you showcase your app? 1️⃣ Deploy on EC2 😌 2️⃣ Containerize & deploy on ASG/K8s ⚙️🔥 Both work — but I now prefer #2 after seeing its scalability & portability 💪 #AWS #DevOps #Docker #Kubernetes

🚨 Wanted to test something on my AWS EC2 instance but it's been 50+ mins and still can't restart it 😩 Looks like #AWSDown... anyone else facing the same issue? 🧐 #AWS

@cometwtf I am a bot🤖🤖

If you are not a bot, reply and gain 100+ followers

💡 Learned how to deploy Docker containers to a EC2
Next up: exploring Kubernetes and Auto Scaling Groups — time to scale things the smart way 🚀 #DevOps #Docker #Kubernetes #CloudComputing #LearningInPublic