Alberto San Millan Diaz’s Post

Built a Voice Assistant using Python 🎤🤖 It can listen, understand, and respond to user commands in real-time! 🔹 Features: – Wikipedia search – Time updates – Opens YouTube & Google via voice This project helped me explore speech recognition and automation using Python. 🔗GitHub : https://lnkd.in/gCFWV39P #PythonProjects #AI #VoiceRecognition #TechProjects #DataScience

“InsightFace Explained: From Images to Embeddings in Python Using Deep Learning” Most tutorials focus on how to use a library. In this article, I focused on something more important: 👉 Understanding how InsightFace works under the hood 👉 How images are converted into embeddings 👉 How face matching actually works 👉 And how to build a simple, production-style pipeline using Django I’ve broken everything down step by step—from uploading a selfie to retrieving matching photos from a database. If you’re working with: Computer Vision Machine Learning Python backend systems Or building real-world AI applications this might be useful for you. Would love your feedback 👇 Here is the link to read my article https://lnkd.in/gARtC9Ng #ArtificialIntelligence #MachineLearning #ComputerVision #Python #DeepLearning

I built a tiny Python library for AI agents. It's called ExAgent. No complex setup. No heavy framework. Just agents + skills. This video shows how it works in under a minute. Trying to make agent building as simple as writing a script. Feedback welcome 👇 #python #ai #opensource

Ever find yourself writing extra lines just to add data to a dictionary? Checking if a key exists before adding an item gets old. This Python trick automatically initializes your dictionary values. It cleans up your data aggregation and processing loops. ✨ It's a lifesaver for grouping features or metrics in your AI/ML workflows. What's your favorite Python shortcut for cleaning up data processing? #Python #AIDeveloper #MachineLearning #CodingTips #DataScience

🧠 This is where Python becomes AI 💡 Think Basic : loop & function combo - logical structure - Visual Learning #ThinkFirst_14 Most people learn: 📦 Data 🔁 Loops But real systems need something more… 👉 Reusable intelligence 📊 Raw Data ↓ 📦 Store (List/Dictionary) ↓ 🔁 Loop (iterate) ↓ ⚙️ Function (logic) ↓ 📊 Output (insight) ↓ 🤖 AI System (scale) #FamAI #ThinkFirst_BuildSmart #Python 🙂

Day 28 of My AI & Data Science Journey Today I learned about Strings in Python 🔹 What I explored: ✔ Creating and accessing strings ✔ String slicing ✔ Common string methods Useful Methods: • lower() / upper() • strip() • replace() • split() Strings are very important for data preprocessing and text analysis. Learning step by step and staying consistent #Python #AI #DataScience #CodingJourney

📌 Building Robust Credit Scoring Models with Python 🗂 Category: DATA SCIENCE 🕒 Date: 2026-04-07 | ⏱️ Read time: 24 min read A Practical Guide to Measuring Relationships between Variables for Feature Selection in a Credit Scoring. #DataScience #AI #Python

🚀 Day 9 of My Generative & Agentic AI Journey! Today’s focus was on Dictionaries in Python — a powerful way to store data in key-value pairs. Here’s what I learned: 📘 Dictionaries in Python: • Store data in key:value format • Defined using {} or dict() • Example using dict(): student_name = dict(first_name="Rohan", last_name="Sharma") • Example using {}: student = {} student["first_name"] = "Mohan" ⚙️ Common Dictionary Operations: • del → Used to delete a key-value pair Example: del student["first_name"] • popitem() → Removes the last inserted item Example: student_name.popitem() • update() → Used to update or add new values Example: student.update({"age": 20}) 👉 Key takeaway: Dictionaries are extremely useful for handling structured data and are widely used in real-world applications like APIs and databases. Another step forward in my Python learning journey 🚀 #Day9 #Python #GenerativeAI #AgenticAI #LearningJourney #BuildInPublic

The bottleneck in AI-assisted coding isn't the model or your prompts. When an agent can't see your notebook state, it guesses. You're relaying error messages and stuck in the (endless) loop at every step. With marimo-pair, coding agents get a live view of your notebook. Variables, errors, UI elements - if you can interact with it, the agent can too. PS: you're also not paying per token to analyze your own CSV files. https://lnkd.in/gcBjKijm #python #AI #datascience #openSource #mlops

6 months ago I published a Python package with my teammate Harsh Bhatt. Today, LazyCook has crossed 2,500 downloads and we're in the top 7% of Python contributors worldwide. What is LazyCook? A multi-agent AI assistant with 4 specialized agents — Generator, Analyzer, Optimizer, and Validator — that work together on every single query to give the best possible answer. It supports PDFs, DOCX, CSV, context across sessions, and even auto-generates graphs for data-heavy queries. The best part? Quality is scored on every response (Completeness 40%, Accuracy 40%, Length 20%). pip install lazycook #Python #OpenSource #PyPI #BuildInPublic #AI