Philippe Charrièrek33g.hashnode.dev·Dec 23, 2024"Tool Calling" and OllamaPrerequisites You should have read the previous article, Developing Generative AI Applications in Go with Ollama, to understand the basics of using Ollama and baby LLMs. For this new article, we'll use this LLM, qwen2.5:1.5b. So run the following com...1 like·332 readsOllama, Tiny Language Models & Golangollama
Krishna Sarathi GhoshforfreeCodeCampfreecodecamp.org·Dec 20, 2024How to Run Open Source LLMs on Your Own Computer Using OllamaAI tools have become commonplace these days, and you may use them daily. One of the key ways to secure your confidential data – both personal and business-related – is by running your own AI on your own infrastructure. This guide will explain how to ...Artificial Intelligence
Torben Haackt0rb3n.hashnode.dev·Dec 20, 2024Korrektor: Wie KI Clean Code zugänglich machtDie Idee kam spontan: "Wie viel kann man in nur 30 Minuten mit modernen KI-Tools erreichen?". Die Antwort: mehr als erwartet. Mit Korrektor entstand ein funktionaler Prototyp – ein Tool, das Code analysiert und basierend auf den Prinzipien von Clean ...ollama
Ray Yaoknack4tech.hashnode.dev·Dec 17, 2024WSL2 Docker Setup in a Proxmox Guest Windows VMIn preparation of test environments for the next localized AI server, I have opted to spin up a Windows 10 guest VM under Proxmox. In the guest VM, the goal is to have a Ubuntu WSL (Windows Subsystem for Linux) running Ollama and Docker. The Docker w...AI
Henry Aduhenryadu.hashnode.dev·Dec 16, 2024Step-by-Step Guide to Local RAG with Ollama's Gemma 2, and LangChain.dartIntroduction to Local RAG What is Retrieval-Augmented Generation (RAG)? The core idea is to enhance the generative capabilities of language models by incorporating external knowledge retrieved from a document store or database. This approach is very ...42 readsLangChainRAG
Philippe Charrièrek33g.hashnode.dev·Dec 13, 2024FeaturedRAG "from Scratch" with Go and OllamaToday, we'll discuss RAG (Retrieval Augmented Generation). This is a way to provide knowledge that an LLM (Large Language Model) doesn't have, allowing it to answer better questions about the Bible, your documentation, a particular domain of knowledg...25 likes·740 readsOllama, Tiny Language Models & GolangRAG
Lino Valdovinoso1-at-home.hashnode.dev·Dec 11, 2024Run o1 at Home Privately: Think-Respond Pipe Tutorial with Open-webui & OllamaRunning advanced AI models like o1 on your personal computer is now more accessible than ever, thanks to tools like Open WebUI and Ollama and models like QwQ. This guide will walk you through setting up the Think-Respond Chain Pipe, enabling you to p...3 likes·85 readsqwq
Philippe Charrièrek33g.hashnode.dev·Dec 8, 2024Generating JSON with an LLM: The Old Method and the New MethodEven with a baby LLM, it's possible to generate JSON. In this article, we'll explore how to generate JSON with an LLM using both the traditional method (with a detailed prompt) and the new method called "Structured Outputs". Prerequisites To understa...4 likes·1.4K readsOllama, Tiny Language Models & Golangollama
Philippe Charrièrek33g.hashnode.dev·Dec 7, 2024Developing Generative AI Applications in Go with Ollama (and Tiny models)Generative AI A generative AI application is a software that uses artificial intelligence to create new content from existing data and user-provided instructions. This content can be text, music, images, and more. The operation of these types of appl...2 likes·422 readsOllama, Tiny Language Models & Golangollama
Mohanraj Rbinarysouljour.me·Dec 5, 2024CVE-2024-46455 : XML eXternal Entity vulnerability in unstructured.io <= 0.14.2Before proceeding I would like to give a shoutout to my awesome friend and colleagueMohit Kwho tagged along in this journey and played a pivotal role. Summary This blog is a result of the applied vulnerability research that we did against open-webui...1 like·426 readsCVE