Home Up PDF Prof. Dr. Ingo Claßen
Noch lesen

  • VS Code’s New AI Did My Job for 30 Minutes. The Results? Honestly Shocking! (link)

  • Building a modern Data Warehouse from scratch (link)

  • Stop Using Hibernate: The Hidden Dangers You Need to Know (link)

  • Agentic AI: Comparing New Open-Source Frameworks (link)

  • Building a Modern Data Lakehouse with DuckDB and MinIO (link)

  • A case where SQL joins struggle but MongoDB documents shine (link)

  • pgai: Importing Wikipedia into PostgreSQL (link)

  • TimescaleDB to the Rescue - Speeding Up Statistics (link)

  • Comparing Model Context Protocol (MCP) Server Frameworks (link)

  • A Postgres MCP server (link)

  • Model Context Protocol (MCP): The AI Integration Breakthrough You Need to Know (link)

  • Model Context Protocol(MCP) with Google Gemini 2.5 Pro — A Deep Dive (Full Code) (link)

  • Fine-Tuning a Text-to-SQL LLM for Reasoning Using GRPO (link)

  • From Zero to Production: Building a Rock-Solid K3s Cluster with PostgreSQL (link)

  • Beyond Materialized Views: Using DuckDB for In-Process Columnar Caching (link)

  • LLMs Do Not Predict the Next Word (link)

  • I tested out all of the best language models for frontend development. One model stood out amongst the rest. (link)

  • Transforming VS Code into a Powerful SQL IDE (link)

  • smallpond (link)

  • Life Altering Postgresql Patterns (link)

  • API-First AI Agentic Patterns: Building Smarter Systems Without the Framework Overhead (link)

  • PostgreSQL Indexes for Columnstore: 1,185x Faster Lookup Queries, 224x Faster Inserts in TimescaleDB (link)

  • Bauplan: Operate your lakehouse with zero infrastructure (link)

  • bauplan (link)

  • Open Source Python Data Lineage with OpenLineage and Hamilton (link)

  • Maximizing Simple RAG Performance Using RL in Python (link)

  • The Most Comprehensive Explanation of Session, Cookie, Token, and JWT (link)

  • Should Stakeholders be Writing SQL for Self-Service? (link)

  • PgBouncer: Don’t Let Connection Chaos Ruin Your Day (link)

  • Xata Agent, your AI expert in PostgreSQL (link)

  • Can Artificial Intelligence Created Better Tables Than You? (link)

  • Claude with MCPs Replaced Cursor & Windsurf — How Did That Happen? (link)

  • Turbocharging Denodo AI SDK: How Semantic Caching Makes Text-to-SQL 9X Faster (link)

  • How I built a SaaS product with 100% AI generated code (link)

  • How an Undergraduate Shattered a 40-Year-Old Computer Science Theory (link)

  • Benchmarking PostgreSQL Batch Ingest (link)

  • Google’s Gemma-3 Fine-Tuning Made Simple: Create Custom AI Models with Python and Unsloth (link)

  • This Happens Inside Python…When We Call a Function (link)

  • SQLAlchemy 2.0: The Most Powerful ORM for Python Yet (link)

  • After DeepSeek-R1, a goldmine of research is waiting to be discovered. (link)

  • Reinforcement Learning (link)

  • Stop Writing Manual Validators! Use Pydantic for Data Validation (link)

  • PostgreSQL: 1 trillion rows in Citus (link)

  • Microsoft PostgreSQL OSS engine team: reflecting on 2024 (link)

  • Model Context Protocol (MCP) (link)

  • Getting Started: Model Context Protocol (link)

  • Is Kimball Still Relevant in the Modern Data Warehouse Era? (link)

  • STOP Using Python Dictionaries Like This! (link)

  • Multi-Tenant Architecture using SpringBoot and PostgreSQL (link)

  • PyGWalker (link)

  • OpenAI’s new prompting guide: how to get the best results from reasoning models (link)

  • Claude 3.7 Sonnet: the first AI model that understands your entire codebase (link)

  • Using Custom Agents in Cursor, Windsurf, Copilot and Others to Supercharge Your Workflow (link)

  • Data Warehouse Basics: How to Handle Changing Data with SCDs (link)

  • Postgres is all you need for vectors (link)

  • Building a Perfect Million Parameter LLM Like ChatGPT in Python (link)

  • I “vibe-coded” over 160,000 lines of code. It IS real. (link)

  • Hard-Earned Lessons from a Year of Building AI Agents (link)

  • License to Kill: Coding with Cursor AI Agents (link)

  • How To Train Your PyTorch Models (Much) Faster (link)

  • Prompt Decorators: A Simple Way to Improve AI Responses (link)

  • Postgres query plan visualization tools (link)

  • Vector Search at 10,000 QPS in PostgreSQL with VectorChord (link)

  • Optimizing PostgreSQL Performance: Essential Queries for Monitoring and Maintenance (link)

  • One Line of SQL, All the LiteLLM Embeddings (link)

  • How to Map Column Values in a Pandas DataFrame? (link)

  • Introducing Wren AI’s New AI-Powered Spreadsheets & Pre- (link)

  • Finding the Best Open-Source Embedding Model for RAG (link)

  • Top 6 Core App Dashboard Building Tools (link)

  • How I Learned to Love init.py : A Simple Guide (link)

  • Postgres as a Graph Database: (Ab)using pgRouting (link)

  • EdgeDB is now Gel and Postgres is the Future (link)

  • EdgeDB 1.0 (link)

  • Use PASSING with JSON_TABLE() To Make Calculations (link)

  • How PostgreSQL’s Aggregate FILTER Will Spoil You (link)

  • Handling Billions of Rows in PostgreSQL (link)

  • Creating an AI Agent That Uses a Computer Like People Do (link)

  • Delta Lake 4.0: Next-Level Big Data Management (link)

  • From Traditional BI to GenBI: Embracing a Smarter, More Human Approach (link)

  • Building a Reliable Text-to-SQL Pipeline: A Step-by-Step Guide pt.1 (link)

  • Building a Reliable Text-to-SQL Pipeline: A Step-by-Step Guide pt.2 (link)

  • Batch processing at Scale: How PostgreSQL outperformed BigQuery for us (link)

  • Try Deep Research and our new experimental model in Gemini, your AI assistant (link)

  • Introducing Perplexity Deep Research (link)

  • ClickBench — a Benchmark For Analytical DBMS (link)

  • Economics of LLMs: Evaluations vs Pricing (link)

  • Open Source Data Engineering Landscape 2025 (link)

  • Modern CI-CD Pipelines of REST API Python Project with UV (link)

  • Real-Time Chat Application with FastAPI and WebSockets (link)

  • 10 Advanced Python Concepts You Should Know To Be a Senior Developer (link)

  • ETL, ELT… or Something Better? (link)

  • MkDocs (link)

  • Building DeepSeek R1 from Scratch Using Python (link)

  • Postgres in the time of monster hardware (link)

  • Representing graphs in Postgresql (link)

  • Expanding Pgai Vectorizer: SQLAlchemy and LiteLLM Make Vector Search Simple (link)

  • Redis with FastAPI for Lightning-Fast Applications (link)

  • Top 8 PostgreSQL Extensions (link)

  • No need to write the boilerplate code again. Use Python dataclasses instead (link)

  • Building the Modern PostgreSQL GUI With PopSQL (link)

  • The twelve-factor app (link)

  • What I’ve Discovered While Using uv (link)

  • 11+ React Ecosystem: Libraries That Shape Modern Development in 2025 (link)

  • 20 Advanced Statistical Approaches Every Data Scientist Should Know (link)

  • How Uber Handles TRILLIONS of Transactions — The Secret (link)

  • Data Formulator: Create Rich Visualizations with AI (link)

  • Improving Agentic SQL Generation (link)

  • Several ways to improving the accuracy of AI-generated SQL (link)

  • IceCream (link)

  • Building a SQL Bot with LangChain, Azure OpenAI, and Microsoft Fabric (link)

  • 11 Free Must-Know Websites for Every Developer (link)

  • OpenAI just quietly released another agentic framework. It’s really fucking cool (link)

  • Google just ANNIHILATED DeepSeek and OpenAI with their new Flash 2.0 model (link)

  • Enhancing Text-to-SQL Agents with Step-by-Step Reasoning (link)

  • Top 16+ Modern React Libraries To Supercharge Your Next Big Project (link)

  • Developing RAG Systems with DeepSeek R1 & Ollama (Complete Code Included) (link)

  • Let’s reproduce GPT-2 (1.6B): one 8XH100 node, 24 hours, $672, in llm.c (link)

  • Drawing DeepSeek R1 Architecture and Training Process from Scratch (link)

  • Advanced SQL for Data Professionals (link)

  • FineWeb: decanting the web for the finest text data at scale (link)

  • Step-by-Step: Running DeepSeek locally in VSCode for a Powerful, Private AI Copilot (link)

  • DeepSeek R1 in 24GB GPU : Dynamic Quantization by Unsloth AI for a 671B-Parameter Model (link)

  • Fine-Tuning DeepSeek-R1 on Consumer Hardware: A Step-by-Step Guide (link)

  • DeepSeek Fine-Tuning Made Simple: Create Custom AI Models with Python (link)

  • Beyond Cost Savings: The True Power of Apache Iceberg in Modern Data Architectures (link)

  • Handling Slowly Changing Dimensions (SCD) in Modern Data Pipelines: A Complete Guide with SQL Examples (link)

  • Top 15 Must-Have JavaScript UI Libraries to Elevate Your Web Development (link)

  • I ranked every AI Coder: Bolt vs. Cursor vs. Replit vs Lovable (link)

  • Ollama vs vLLM: which framework is better for inference? (Part II) (link)

  • Automating Data Summarization in PostgreSQL With Claude (link)

  • RunSQL (link)

  • ChartDB (link)

  • Rethinking the frontend with HTMX (link)

  • Why Docker Might Not Be Your Best Choice (link)

  • SQLModel (link)

  • Why Choose Caddy Server instead Nginx? (link)

  • documentdb (link)

  • Top 15 Trending GitHub Repositories For AI Developement (link)

  • Stream Processing Systems in 2025: RisingWave, Flink, Spark Streaming, and What’s Ahead (link)

  • Full-stack RAG: FastAPI Backend (Part 1) (link)

  • Ollama vs vLLM: which framework is better for inference? (link)

  • Is Cursor better than VS Code? (link)

  • Stop Being Racist! Just Use DeepSeek Dammit! (link)

  • AlloyDB vs PostgreSQL: Unleash Performance, Slash Costs, Simplify Data Stack (link)

  • 2025 Data Engineering & AI Trends (link)

  • Don’t Fear Async: A Friendly Guide to Python’s Most Powerful Tool (link)

  • Top 11 AI-Powered Developer Tools Transforming Workflows in 2025 (link)

  • A Simple Guide to DeepSeek R1: Architecture, Training, Local Deployment, and Hardware Requirements (link)

  • Building an End-to-End Data Lake ELT Pipeline using Modern Data Stack (link)

  • 25 Game-Changing Websites Every Developer Must Bookmark (link)

  • I am among the first people to gain access to OpenAI’s “Operator” Agent. Here are my thoughts. (link)

  • Building a Reliable Text-to-SQL Pipeline: A Step-by-Step Guide pt.1 (link)

  • DeepSeek-R1: A Cutting-Edge Logical Reasoning Model for Local AI Development with Ollama (link)

  • I spent 6 hours learning AWS Glue. Here is what I found (link)

  • LlamaCoder (link)

  • OCR with Phi-3-Vision: Revolutionizing Document Processing (link)

  • How We Built a Content Recommendation System With Pgai and Pgvectorscale (link)

  • SQL Applications using LlamaIndex (link)

  • Step-by-Step Guide to Creating Your Own Large Language Model (link)

  • LLM Finetuning Strategies (link)

  • A Visual Exploration of Semantic Text Chunking (link)

  • The Best NVIDIA GPUs for LLM Inference: A Comprehensive Guide (link)

  • Jupyter Agent: Revolutionizing Data Analysis with LLMs (link)

  • Combining FastAPI, PostgreSQL, and Leaflet — GIS Tutorial (link)

  • Unlock Custom Quantization for Hugging Face Models Locally with Ollama (link)

  • Python Mako (link)

  • Python Memory Management: Best Practices for Performance (link)

  • From query to plot: Exploring GeoParquet Overture Maps with Ibis, DuckDB, and Lonboard (link)

  • PostGIS meets DuckDB: Crunchy Bridge for Analytics goes Spatial (link)

  • FlockMTL is a DuckDB extension that integrates language model (LLM) (link)

  • DuckERD CLI (link)

  • Enhance your AI/ML applications with flexible Bring Your Own Model options (link)

  • Building a High-Performance Data Pipeline Using DuckDB (link)

  • Why PyMuPDF4LLM is the Best Tool for Extracting Data from PDFs (link)

  • This is How I Use Swagger to Design REST APIs Before Starting the Development (link)

  • The Ultimate Guide to Relational Databases for Backend Developers (link)

  • Dynamic SQL Query Formation with Jinja Template (link)

  • How I Made A Python Script 130 Times Faster with PostgreSQL Query Optimization (link)

  • Examples of specialized DB Usage (link)

  • Turn Your CSVs Into Graphs Using LLMs (link)

  • Optimizing Your Database for Analytics (link)

  • Implementing Hybrid Search with Postgres and pgvector (link)

  • rainfrog - terminal ui for postgres (link)

  • Build an LLM RAG Chatbot With LangChain (link)

  • How SELECT FOR UPDATE Works (link)

  • Storage Disaggregated Databases and Shared Transaction Log Architecture In Comparison (link)

  • Microsoft GraphRAG and Ollama: Code Your Way to Smarter Question Answering (link)

  • Implementing Filtered Semantic Search Using Pgvector and JavaScript (link)

  • Open-Source Visual ETL Tools in 2024 (link)

  • 4 SQLAlchemy Features For Data Engineering (link)

  • Fine-Tuning LLM model (Meta-Llama-3.1–8B) using unsloth for Text-to-SQL Data (link)

  • Navigating the New Types of LLM Agents and Architectures (link)

  • Self-Hosting LLaMA 3.1 70B (or any ~70B LLM) Affordably (link)

  • Extracting Meaning from Tables in Financial Statements With LLMs and Chatbots (link)

  • How to Containerize Your Local LLM (link)

  • LLM Monitoring and Observability: Tools, Tips and Best Practices (link)

  • Quantization of LLMs with llama.cpp (link)

  • Why I Use Open Weights LLMs Locally (link)

  • Best practices for LLM optimization for call and message compliance: prompt engineering, RAG, and fine-tuning (link)

  • Build your own Large Language Model (LLM) From Scratch Using PyTorch (link)

  • What We Learned from a Year of Building with LLMs (Part I) (link)

  • TEXTGRAD vs DSPY : Revolutionizing AI System Optimization through Automatic Text-Based Differentiation (link)

  • IDE in the Web Browser? Let me show you Project IDX by Google (link)

  • A Practical Guide to using Pydantic (link)

  • Build Your Own Llama 3 Architecture from Scratch Using PyTorch (link)

  • Running Ollama on Google Colab (Free Tier): A Step-by-Step Guide (link)

  • Using docker init to write Dockerfile and docker-compose configs (link)

  • Grok 2–Why It’s HUGE for AI (link)

  • 6 Best Practices for Writing Dockerfiles (link)

  • Document Extraction Is GenAI’s Killer App (link)

  • Understanding pgvector’s HNSW Index Storage in Postgres (link)

  • Graph RAG — A Conceptual Introduction (link)

  • High-Precision RAG for Table Heavy Documents (link)

  • Fine-Tuning LLAMA 3 Model for Relation Extraction Using UBIAI Data (link)

  • Splicing Duck and Elephant DNA (link)

  • DuckDB & PyArrow: Lightweight and Speed Data Analysis (link)

  • When PostgreSQL Query Planner Goes Rogue: A Deep Dive into Query Optimization (link)

  • Real-time Distributed score streaming using gRPC and Redis (link)

  • Claude Dev (link)

  • Customize Generative AI Models for Enterprise Applications with Llama 3.1 (link)

  • Pinecone vs. Postgres pgvector (link)

  • Postgres vs. Pinecone (link)

  • No, Data Engineers Don’t NEED dbt. (link)

  • Improving Performance for Data Visualization AI Agent (link)

  • The new “window.ai” API will blow your mind. (link)

  • Cost-Effective Text Embedding: Leveraging Ollama Local Models with Azure SQL Databases (link)

  • Why Your RAG Doesn’t Work (link)

  • GPT Fine-tuning (link)

  • Claude 3.5 Sonnet vs. GPT-4o (link)

  • Claude 3.5 Sonnet (link)

  • Fine-Tuning Mistral 7b in Google Colab with QLoRA (complete guide) (link)

  • Mastering RAG Chunking Techniques for Enhanced Document Processing (link)

  • PostgreSQL and Pgvector (link)

  • Making PostgreSQL a Better AI Database (link)

  • When Should You Use Distributed PostgreSQL for Gen AI Apps? (link)

  • Building the Best PostgreSQL GUI: Announcing Our Acquisition of PopSQL (link)

  • Web Scraping With 5 Different Methods: All You Need to Know (link)

  • How to use PostgreSQL for (military) geoanalytics tasks (link)