f-strings in Python clearly explained:

Let's learn how to finetune your RAG pipeline using DSPy, step-by-step:

Object oriented programming in Python, clearly explained:

Synthetic datasets with Llama 3? It's easier than you think.

I've been playing with a Distilabel, an open-source framework that lets you generate domain-specific synthetic text data using Llama 3.

Try it yourself: lightning.ai/lightning-a...

Image to LaTeX powered by multimodal Llama 3.2!
.
.
Upload image of an equation, and it gives you the corresponding LaTeX code.

Find code here: github.com/patchy631/a...

PydanticAI: Build production-grade Agentic AI apps in pure Python!

PydanticAI offers the same elegance and ease of use as FastAPI, now extending that experience to building production-grade LLM applications.

GitHub repo: github.com/pydantic/py...

Decorators in Python, clearly explained:

15 cheat sheets you shouldn't miss as a data scientist:

SQLite-Vec: a small, portable vector database powered by SQLite!

It's lightning fast, lightweight, perfect for on-device RAG solutions!

Key Feats:

- MRL slicing
- 32x storage reduction with binary quantization
- SDKs for Python, JavaScrip

GitHub repo: https://github.com/asg017/sqlite-vec

Machine learning is hard.

Multimodal RAG, visually explained!

Effortless Document Parsing with Docling!

Docling is an open-source Python package that transforms any document into LLM ready data!

Key feats:

🔍 OCR for scanned PDFs
🗂️ PDF, PPTX, DOCX & more → Markdown, JSON
🤖 Integrates with LlamaIndex & LangChain

GitHub repo: https://github.com/DS4SD/docling

Let's learn how to deploy a RAG application powered by Llama 3.2, running 100% locally:

aisuite - a Python library to simplify your LLM integrations!

Introduced by Andrew Ng, aisuite provides a simple, unified interface to multiple Generative AI providers.

It supports:
- OpenAI & Anthropic
- Azure, Google & AWS,
- Groq, Mistral, HF & Ollama

GitHub repo: github.com/andrewyng/ai...

Data Classes in Python, clearly explained:

K-Nearest Neighbours (KNN), clearly explained:

SAMURAI vs. MetaAI's SAM 2!

Traditional visual object tracking struggles in crowded, fast-moving, or self-occluded scenes, as does SAM2.

Meet SAMURAI: a completely open-source adaptation of the Segment Anything Model for zero-shot visual tracking!