Data Science

Install Ollama, download a small language model, and run private AI inference on your own hardware in three straightforward steps.

Build a local video summarization pipeline using SmolVLM2-2.2B. Runs on consumer GPUs with 5.2 GB VRAM, no cloud API required.

LAMs and agentic LLMs both take actions, but differ fundamentally in how. Learn which to use and when.

GraphRAG and Vector RAG serve different retrieval needs. This guide breaks down their architectures, query handling, and when to use each.

A reproducible benchmark shows classical ML owns the synchronous payment hot path, while LLM agents belong on the asynchronous cold path.

A large context window is not the same as agent memory. Learn how retrieval, compression, and summarization fit into an agent's cognitive stack.

Seven open-weight coding models worth running locally in 2026, from efficient MoE models to multimodal options, all tested on consumer GPU hardware.

AI tools now let anyone build agents without Python. But prompting frameworks and hardware specs still separate casual users from serious practitioners.

Learn how to give Claude Code browser access via Playwright MCP so your coding agent can test and verify its own implementations end-to-end.

When a PDF prints a table of contents but ships no outline, RAG pipelines lose document structure. This article shows how to reconstruct it programmatically.

Tool calling transforms LLMs from text generators into agents that trigger real actions. Learn how the tool-calling loop works with practical code examples.

Materialized lake views in Microsoft Fabric simplify medallion pipelines into declarative SQL. Here's what changed from preview to general availability.