Mirumee Labs’ Post

🚀 Day 7 of #30DaysOfLeetCode Challenge Continuing my consistency journey as a Python Developer, with a strong focus on Data Science! ✅ Today’s Problem: Roman to Integer 🔍 Platform: LeetCode 💡 Approach: Solved this problem using a right-to-left traversal approach. Stored Roman values in a dictionary and iterated through the string in reverse. If the current value is smaller than the previous value, it is subtracted; otherwise, it is added. 👉 Simple Explanation: We read the string from right to left. If a smaller numeral appears before a larger one (like IV), we subtract it; otherwise, we add it. This way, we can convert the entire Roman number into an integer. ⏱️ Time Complexity: O(n) 📌 Key Learning: Recognizing patterns and choosing the right traversal direction makes problem solving easier. Using a dictionary keeps the code efficient and clean! Consistency is making me better every day 🚀 #Python #DataScience #LeetCode #ProblemSolving #CodingJourney #30DaysOfCode

Build a production AI agent in 10 lines of Python. Strands Agents SDK: ```python from strands import Agent from strands.models.bedrock import BedrockModel from strands_tools import calculator, web_search agent = Agent( model=BedrockModel("anthropic.claude-sonnet-4-20250514-v1:0"), tools=[calculator, web_search] ) response = agent("What's the GDP per capita of the top 5 economies?") ``` That's it. Tool calling, conversation management, streaming, multi-turn context is all handled. Why Strands over LangChain for AWS: - Built for Bedrock integration (not retrofitted) - Works with any Bedrock model - ToolSimulator for agent testing (just released) - Strands Evals for evaluation pipelines - Open-source, runs locally For production: pair with Bedrock AgentCore for managed deployment, guardrails, and observability. The stack: Strands (build) → ToolSimulator (test) → Strands Evals (evaluate) → AgentCore (deploy) Full lifecycle. Open-source foundation. Managed deployment when ready. Start: https://strandsagents.com #AWS #AIAgents #Python #Strands #Bedrock

3 RAG chunking strategies. 2 cost the same. 1 costs double. Here's why 👇 Building my own RAG pipeline, I hit a wall. Everyone talks about WHAT chunking is. Nobody talks about WHERE the money goes. Here's what I figured out: 💰 The $ only comes from ONE place — the embedding model API call. Splitting → FREE (plain Python) Storage in FAISS/CSV → FREE Embedding API call → costs money Ingestion → ONE TIME cost only Semantic costs 2x because it calls the embedding API twice: → Once to find topic shifts → Once to store vectors in FAISS Rule of thumb: Start with Document Aware. Upgrade to Semantic only when your data has no clear structure. Ingestion cost = one time only. Query cost? That's a whole different story. 🔜 Follow so you don't miss it. Which chunking strategy are you using? Drop it below 👇 #RAG #AIEngineering #DataEngineering #LLM #Python #VectorDatabase #OpenAI #LangChain #Claude

My AI Voice Assistant is now a Python Package! I’m excited to share a major update to my "JARVIS" project. I’ve officially converted it into a modular Python package! 🚀 This assistant doesn't just process text; it listens to your voice, understands commands using Gemini 2.5 Flash, and speaks back with a professional voice using Edge-TTS. Key Features: Voice-Activated: Stays in standby until it hears its name. AI-Powered: Uses Google's latest Gemini models for intelligent responses. Modular Architecture: Organized as a package for easy installation and scalability. Real-time Interaction: Fast speech-to-text and text-to-speech loop. You can now install it directly from my GitHub repository with a single command: pip install git+https://lnkd.in/gTBk8R_2 #Python #ArtificialIntelligence #Gemini #VoiceAssistant #Coding #OpenSource #SoftwareEngineering

In 2026, "knowing Python" is the baseline. The real premium is on developers who can orchestrate. If you're looking to level up your stack this quarter, look past the hype and master these three libraries: 1)LangChain/LlamaIndex: For building real-world RAG pipelines and autonomous agents. 2)Pydantic v2: Essential for type-safe data validation in AI APIs. It’s powered by Rust now, making it blazing fast. 3)FastAPI: Still the king of modern backend, but the real power is how it integrates with asynchronous AI workflows.

Merge In Between Linked Lists — and got it Accepted ✅ This problem really tested my understanding of: 🔹 Linked List traversal 🔹 Pointer manipulation 🔹 Edge case handling One small mistake in pointer connection... and everything breaks. 😅 But that’s where real learning happens. 💡 Key takeaway: In linked lists, it’s not about values—it's about how you connect nodes. Step by step, I’m getting stronger in data structures & algorithms and building the problem-solving mindset needed for top tech roles. 🔥 Consistency is the real game changer. #LeetCode #DSA #ProblemSolving #Python #CodingJourney #SoftwareDeveloper #FullStackDeveloper #KeepLearning

Stumbled across this GitHub repo last night and ended up going down a rabbit hole for two hours. It's called AI Engineering from Scratch by Rohit Ghumare, and the scope is honestly ridiculous. 260+ lessons, 20 phases, covering everything from linear algebra all the way to building autonomous agent swarms. Python, TypeScript, Rust, Julia, all in one place. What got me is that most AI resources teach you to use the tools. This one teaches you to build them. Big difference. It's open source, MIT licensed, and actively maintained (3.9K stars already). If you're trying to go deeper than just calling APIs, worth bookmarking. 🔗 Link in the first comment 👇 #AIEngineering #OpenSource #MachineLearning #Python #LLMs

🔥 FastAPI in 2026: Why It’s Still Dominating Python Backend Development FastAPI continues to evolve as one of the fastest-growing Python frameworks, powering modern APIs, AI systems, and microservices at scale. Today’s backend world is shifting toward: ⚡ Async-first architecture ⚡ AI/ML-powered APIs ⚡ Microservices & event-driven systems ⚡ Cloud-native deployments And FastAPI fits perfectly into this ecosystem.

I’ve spent the last few weeks moving beyond just analyzing data to actually building the systems that create it. It’s been a massive learning curve, but I’ve finally started to wrap my head around:   𝗠𝗼𝗱𝗲𝗹𝘀 & 𝗔𝗱𝗺𝗶𝗻: How the database actually structured.   𝗩𝗶𝗲𝘄𝘀 & 𝗧𝗲𝗺𝗽𝗹𝗮𝘁𝗲𝘀: Passing variables between the backend and the UI.   𝗣𝗲𝗿𝗺𝗶𝘀𝘀𝗶𝗼𝗻𝘀: Managing users and groups.   𝗕𝗼𝗼𝘁𝘀𝘁𝗿𝗮𝗽: Keeping things clean and responsive. Huge shoutout to my mentor Rathan Kumar for the guidance. Check out the live site - https://lnkd.in/g-jkXR5x On to the next build! #Django #Python #DataEngineering #Learning #FullStack

📣 Bad API docs don't fail loudly. They waste hours quietly. Have a look into our API doc- 📖 https://lnkd.in/dvr6Nyhx You install a framework. The README looks clean. The examples run. Then you try to do something slightly off the happy path and you're reading source code at midnight trying to figure out what the second argument actually does. This is why we treat SynapseKit's documentation as a first-class feature not an afterthought shipped after the code. Every public API is documented. Every parameter explained. Every method shows you what it accepts, what it returns, and what happens when you pass the wrong thing. Architecture docs explain why decisions were made, not just what they are. The cookbook has real patterns, not toy examples. Because the engineers who evaluate a framework in the first 30 minutes are not the same engineers who maintain it six months later. The second group lives in the docs. #Python #LLM #OpenSource #AI #Documentation #DeveloperExperience #SynapseKit