Solved anagram problem with hashmaps, not sorting.

#AILearningSKC | Day 59: From Theory to Code – Connecting to Mistral AI with Python Yesterday, I learnt from theory how AI tools secretly use APIs. Today, I got my hands dirty and connected to Mistral AI using Python. Here’s what I learned: 🔹 The Mistral platform provides a clean and powerful SDK (`mistralai`) that lets developers and testers connect directly to AI models. 🔹 By using an API key and a few lines of Python code, I could send a user message to an AI model and get a meaningful response. 🔹 The system message doesn’t appear in the output — it’s used internally to guide how the AI behaves. With this, I understand how AI models interact through APIs. Have you experimented with any AI APIs recently? 🔗 Catch up on my AI learning journey: https://bit.ly/ailearnskc #AI #MistralAI #Python #APITesting

📊 Visualizing How AI Learns — With Python 🧠🐍 The image above shows two 3D surfaces plotted in Python mathematical landscapes defined by f(x,y)=x2+xy2f(x, y) = x^2 + xy^2f(x,y)=x2+xy2 and f(x,y)=2x+y2f(x, y) = 2x + y^2f(x,y)=2x+y2. These aren’t just cool visuals 👀 They represent the loss surfaces that every AI model must navigate to learn. 🔍 Why this matters for AI ⛰️ Peaks = bad solutions 🌄 Valleys = good solutions 📉 Gradients guide models downhill toward better performance 🧭 The curvature shows how hard it is for algorithms like gradient descent to find the best parameters 🐍 Why Python? Using SymPy, NumPy, and Matplotlib, we can literally see how models improve by following the slope of these surfaces. 💡 The takeaway These 3D plots aren’t just math, they’re the terrain AI walks through as it learns, improves, and optimizes itself. #AI #Python #MachineLearning #DeepLearning #DataScience #Visualization #STEM #Innovation

Excited to share my latest AI project — a PDF Summarization App powered by Gemini 2.5 Pro! The tool reads PDFs, processes the content, and generates summaries in multiple formats (short, medium, detailed, or bullet points). Built using Python, LangChain, and Streamlit, this project explores how LLMs can streamline document understanding and content generation. #AI #Gemini #LangChain #Python #LLM #Streamlit #GenerativeAI

📘 Resource Recommendation: Understanding Vector Embeddings in AI A very insightful session by Pamela Fox that demystifies vector embeddings and their role in modern AI systems. 🎥 Watch here: https://lnkd.in/e9mwTMdA In just one hour, the session covers: 🔹 How vector embeddings work across models 🔹 The idea of similarity space 🔹 Vector search — Exhaustive vs ANN (HNSW, DiskANN) 🔹 Quantization (Scalar, Binary) 🔹 MRL dimension reduction 🔹 Compression with rescoring The accompanying Python notebooks allows for practical experimentation — ideal for those who want to go beyond theory. This session is part of the broader Python + AI series. You can explore more recordings here: 📌 https://aka.ms/PythonAI/2 #AI #MachineLearning #Python #VectorSearch #Embeddings #MicrosoftAI #TechLearning

Code Meet Intelligence: Day-4 🧠 Building a Private, Offline AI Search Engine! Forget keyword searching. This video dives into Semantic Search, showing how we built a custom engine that searches by meaning, not just text matches. We convert documents (including PDFs!) into Vector Embeddings using Sentence Transformers and index them with FAISS for ultra-fast retrieval. The demo proves the system's resilience by correctly answering a query even with a misspelling! This is the core technology behind internal knowledge bases and advanced RAG systems. #CodeMeetIntelligence #SemanticSearch #VectorDatabases #AIinSearch #SentenceTransformers #FAISS #MachineLearning #DeepLearning #Python #RAG

Every new “Agentic AI” framework sounds futuristic… Until you look under the hood and it’s still Python running the show. Python didn’t survive the AI wave. It became the wave. From orchestrating agents to LLM workflows, it has become the backbone powering innovations. Simple. Stable and Scalable. #Python #AgenticAI #AI #Automation #TechTrends

How to Build an OpenAI Realtime Voice/Video/Vision #AI Agent in #Python Install Vision Agents and get started in Python 👉: https://lnkd.in/dguX5gSx ⭐️ the open-source video AI framework and test the sample demos 👉: https://lnkd.in/drePftjd

A little late, but it got me out of town. If you haven’t heard, there’s a new alternative that can cut about 40–50% off your AI bro’s bill (though it’s always recommended to cut 100% of that bill). Here is the simplest way to encode JSON to TOON. #AI #TOON #JSON #TOONJSON #PYTHON

My new AI platform bypasses the need for expensive, time-consuming Python/SQL coding for real-time ML features. We’re moving feature engineering from the ML developer's desk to the analyst's interface, collapsing months of work into minutes. See how we're using AI to automate the work, not just assist it https://lnkd.in/gAqbarYy #AI #MachineLearning #FeatureEngineering

Fake News Detection using Machine Learning  I built a Fake News Detection model that classifies articles as Real or Fake using Python ,Scikit-learn and TF-IDF Vectorizer.   – Data preprocessing & feature extraction using TF-IDF   – Logistic Regression for classification   – Achieved ~95 % accuracy on test data   – Implemented in Google Colab and uploaded on GitHub   Project Link: [https://lnkd.in/gEqUfWfc)   #MachineLearning #AI #Python #DataScience #FakeNewsDetection #MLProjects #GitHub