InGenerative AIbyPatrick KalkmanKubeVox: Sub-200ms Kubernetes Voice Control with Local Llama 3Build a low-latency, privacy-focused Kubernetes voice interface using Llama 3 and local inference—a step-by-step guide.Feb 111Feb 111
InTowards AIbyGao Dalie (高達烈)Browser-use + LightRAG Agent That Can Scrape 99% websites with LLM!!In this story, I have a quick tutorial showing how to create a powerful chatbot using Browser-use, LightRAG, and a local LLM to develop an…Nov 20, 20249Nov 20, 20249
Henry NavarroThe cheapest GPU cloud providers, a fair comparisson💰🌐Exploring Affordable AI: Harnessing Gaming GPUs for High-Performance Cloud Solutions (Article Updated)Dec 30, 20242Dec 30, 20242
InTDS ArchivebyMatthew GuntonLoRA Fine-Tuning On Your Apple Silicon MacBookLet’s Go Step-By-Step Fine-Tuning On Your MacBookNov 20, 20245Nov 20, 20245
Sjoerd TiemensmaHow I use o1-mini to Generate Slide DecksEver since ChatGPT came out, I’ve been looking for ways to make use of the abilities of LLMs, whether that’s in writing code, analyzing…Sep 22, 20241Sep 22, 20241
InData Science in your pocketbyMehul GuptaForget DeepSeek : Qwen 2.5 VL and Qwen Max is herebeats DeepSeek-v3, OpenAI modelsJan 308Jan 308
Sebastian PetrusDeveloping RAG Systems with DeepSeek R1 & Ollama (Complete Code Included)Ever wished you could directly ask questions to a PDF or technical manual? This guide will show you how to build a Retrieval-Augmented…Jan 2428Jan 2428
InTowards AIbyJúlio AlmeidaBuilding an On-Premise Document Intelligence Stack with Docling, Ollama, Phi-4 | ExtractThinkerSecurely build an on-prem Document Intelligence stack with ExtractThinker & local LLMs. Keep data private. Perfect for fintech.Jan 1614Jan 1614
Shravan KumarPyMuPDF4LLM is all You Need for Extracting Data from PDFsThis package converts the pages of a PDF to text in Markdown format using PyMuPDF. Standard text and tables are detected, brought in the…Nov 1, 20246Nov 1, 20246
InLevel Up CodingbyArman HossenMarkItDown: Microsoft’s Game-Changing Tool That Turns Any Document into Clean MarkdownA deep dive into Microsoft’s new Python library that seamlessly converts PDFs, Office files, and more into clean, version-control-friendly…Dec 18, 202412Dec 18, 202412
InMedialessonbySebastian JensenUsing Microsoft.Extensions.AI to Generate Embeddings in .NETLet’s explore the newly Microsoft.Extensions.AI NuGet package.Nov 27, 2024Nov 27, 2024
InMedialessonbySebastian JensenUsing Phi-3 Vision with ONNX as local Small Language Model to analyze imagesThis blog post contains a simple .NET Console application to demonstrate how you can easily integrate the Phi-3 Vision Model using ONNX to…Jul 5, 2024Jul 5, 2024
Ivan FioravantiQwen 2.5 Coder: quantization does not matter — Aider benchmarks on Apple MLXIf you can’t read this article because of the firewall, go hereNov 22, 20243Nov 22, 20243
InTDS ArchivebyJon FlynnExploring Music Transcription with Multi-Modal Language ModelsUsing Qwen2-Audio to transcribe music into sheet musicNov 17, 20244Nov 17, 20244
InTDS ArchivebyEivind KjosbakkenFine-Tune Llama 3.2 for Powerful Performance on Targeted TasksLearn how you can fine-tune Llama3.2, Meta’s most recent Large language model, to achieve powerful performance on targeted domainsOct 10, 202410Oct 10, 202410
InAI AdvancesbyMarco RodriguesI Used Photos of My Girlfriend to Train the FLUX.1 ModelGenerate realistic AI images of your loved ones by training a Flux LoRa model with only a few photos.Aug 26, 202410Aug 26, 202410
InAI AdvancesbyTarun SinghAI-Powered OCR with Phi-3-Vision-128K: The Future of Document ProcessingIn the fast-evolving world of artificial intelligence, multimodal models are setting new standards for integrating visual and textual data…Oct 9, 202423Oct 9, 202423
InnttlabsbyAkihiro SudaAccelerating Llama on Lima, with WASI-NN RPCWasmEdge v0.14 was released last month, with our contribution for exposing WASI-NN (WebAssembly System Interface API for Neural Networks)…Jun 19, 2024Jun 19, 2024
OlaresBuilding a Local Perplexity Alternative with Perplexica, Ollama, and SearXNGLearn how to build your selfhosted AI search engine on Terminus, using open source tools like Ollama, SearXNG, and Perplexica.Jul 31, 2024Jul 31, 2024
