Image by Author | Canva If you like building machine learning models and experimenting with new stuff, that’s really cool — but to be honest, it only becomes useful to others once you make it available to them. For that, you need to serve it — expose it through a web API so that …
Serve Machine Learning Models via REST APIs in Under 10 Minutes Read More »
AI is rewriting the day-to-day of data scientists. , data scientists must learn how to improve productivity and unlock new possibilities with AI. Meanwhile, this transformation also poses a challenge to hiring managers: how to find the best talent that will thrive in the AI era? One critical step in building a strong AI-empowered data …
Rethinking Data Science Interviews in the Age of AI Read More »
Image by Author | ChatGPT ContentsIntroductionWhy AI-First is a Game-ChangerColab’s Core AI FeaturesGetting Started with the New AI-First ColabWalkthrough Using the New AI-First ColabFinal Thoughts Introduction For years, Google Colab has stood as a cornerstone for data scientists, machine learning engineers, students, and researchers. It has democratized access to what amount to essential computing …
tools for data visualization and exploration have allowed me to iterate way quicker on my computer vision projects, especially when the problems I am faced with are not straightforward and I need to make algorithm or design decisions based on dynamic time-varying signals. These signals can often be challenging to analyze by just looking at …
Interactive Data Exploration for Computer Vision Projects with Rerun Read More »
Image by Author | Ideogram We’ve all spent the last couple of years or so building applications with large language models. From chatbots that actually understand context to code generation tools that don’t just autocomplete but build something useful, we’ve all seen the progress. Now, as agentic AI is becoming mainstream, you’re likely hearing …
Why Agentic AI Isn’t Pure Hype (And What Skeptics Aren’t Seeing Yet) Read More »
is a versatile technique for exploring the solution space of various types of data science problems and incrementally constructing candidate solutions – a bit like navigating a maze. In this article, we will briefly go over the concept of backtracking before diving into a couple of intuitive, hands-on examples coded in Python. Note: All example …
Image by Author | ChatGPT ContentsIntroductionSetupStep 1: Streamlit + Pandas DashboardStep 2: Add Plotly for Interactive VisualizationsHow the Three Libraries Work TogetherKey Development WorkflowNext StepsDeploying Your DashboardConclusion Introduction Creating interactive web-based data dashboards in Python is easier than ever when you combine the strengths of Streamlit, Pandas, and Plotly. These three libraries work seamlessly …
How to Combine Streamlit, Pandas, and Plotly for Interactive Data Apps Read More »
We’re introducing an efficient, on-device robotics model with general-purpose dexterity and fast task adaptation.
I had just started experimenting with CrewAI and LangGraph, and it felt like I’d unlocked a whole new dimension of building. Suddenly, I didn’t just have tools and pipelines — I had crews. I could spin up agents that could reason, plan, talk to tools, and talk to each other. Multi-agent systems! Agents that summon …
A Developer’s Guide to Building Scalable AI: Workflows vs Agents Read More »
Image by Author | ChatGPT ContentsThe Data Quality Bottleneck Every Data Scientist KnowsThe Solution: A 4-Node n8n WorkflowBuilding the Workflow: Step-by-Step ImplementationUnderstanding the ResultsTesting with Different DatasetsNext StepsConclusion The Data Quality Bottleneck Every Data Scientist Knows You’ve just received a new dataset. Before diving into analysis, you need to understand what you’re working with: …
Automate Data Quality Reports with n8n: From CSV to Professional Analysis Read More »
