CodeCut Newsletter

Home
Notes
Archive
Leaderboard
About

June 2026

pandas vs Polars vs DuckDB: A Data Scientist’s Guide to Choosing the Right Tool
Compare pandas, Polars, and DuckDB for data analysis. Learn when to use each tool based on data size, performance needs, and workflow preferences.
 • CodeCut
Quick Tips: dotenvx - Separate Dev, Staging, and Prod Configs Safely
Plus generate images locally with Ideogram 4
 • CodeCut
PDF Table Extraction: Docling vs Marker vs LlamaParse Compared
Compare three Python tools for PDF table extraction: Docling, Marker, and LlamaParse. Learn which handles merged cells and multi-level headers best.
 • CodeCut
Quick Tips: PP-OCRv6 - Extract Text from Receipts with Small OCR Models
Plus pick local LLMs that fit your machine
 • CodeCut
Stop Hand-Tuning Prompts: Auto-Optimize an LLM Classifier with DSPy
Stop hand-tuning prompts with DSPy. Build an LLM classifier that evaluates, optimizes, and reuses better prompts with examples.
 • CodeCut
Quick Tips: Polars 1.41 - Speed Up Wide Parquet Scans Without Code Changes
Plus one interface for OpenAI, Anthropic, and Gemini
 • CodeCut
Add Long-Term Memory to LLM Applications with Mem0
Build a memory-aware LLM workflow with Mem0 that extracts useful facts, retrieves relevant memories, and improves follow-up responses.
 • CodeCut
Quick Tips: LM Studio - Try local LLMs without setup code
Plus refactor AI code with clean skills
 • CodeCut
Extracting PDF Tables on Apple Silicon: olmOCR-2 vs PaddleOCR-VL
Compare olmOCR-2 and PaddleOCR-VL for PDF table extraction on a Mac. See which open-source VLM handles merged cells and numeric tables better.
 • CodeCut

May 2026

© 2026 CodeCut Newsletter · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture