Все публикации

0:07:50

Intro to burr: A State Machine for LLM apps

0:04:27

Llama 3.2-vision: The best open vision model?

0:03:30

Moonshine: Real-Time Speech-To-Text on your laptop

0:04:08

NuExtract: An LLM that extracts information

0:04:12

Using LLMs on the command line

0:02:32

Ollama: Running Hugging Face GGUF models just got easier!

0:03:52

The fastest way to run OpenAI Whisper Turbo on a Mac

0:03:32

Ollama: How to send multiple prompts to vision models

0:04:09

Running OpenAI Whisper Turbo on a Mac

0:04:43

An intro to rerankers: A uniform API for reranking models

0:05:06

DuckDB dynamic column selection gets even better

0:05:21

Ollama and LanceDB: The best combination for Local RAG?

0:03:13

Searching images on my laptop with LanceDB

0:06:14

Rewriting RAG Queries with OpenAI Structured Outputs

0:03:23

DuckDB function chaining: The simpler SQL you didn't know you needed

0:05:50

Why OpenAI's new Structured Outputs feature is awesome!

0:07:18

What Are Matryoshka Embeddings?

0:06:45

How to evaluate retrieval in RAG pipelines

0:06:30

Hybrid Search for RAG in DuckDB (Reciprocal Rank Fusion)

0:05:53

Full-Text Search vs Vector Search (RAG with DuckDB)

0:07:35

Search-Based RAG with DuckDB and GLiNER

0:08:38

Local RAG with llama.cpp

0:05:01

A UI to quantize Hugging Face LLMs

0:05:19

Mistral 7B Function Calling with llama.cpp