Generative AI with Local LLMs

Generative AI with Local LLMs

Sign in Subscribe

Update on Our Website & Publishing Direction

Update on Our Website & Publishing Direction

Hey everyone, I wanted to share a quick update about our website and where things are heading. For a while, I’ve been overcomplicating things. My co-author Shamim often reminds me that while he loved the simplicity of Wix (our earlier setup), I pulled him into more developer-heavy tools just

Your AI is a Caged Genius. Here’s How to Set It Free.

Your AI is a Caged Genius. Here’s How to Set It Free.

Picture this: It’s 9 AM Monday morning. You have 30 minutes to pull together a project status report for your director. You turn to your $200/month AI assistant—the same one that can write poetry, debug code, and explain quantum physics—and ask it to summarize last week’

Modern AI Integrations: MCP Server Meets REST API and Local LLMs — Part 3 (MCP Agent Integration)

Modern AI Integrations: MCP Server Meets REST API and Local LLMs — Part 3 (MCP Agent Integration)

In the final part of our series, we demonstrate how to build a complete real-world workflow using the MCP Agent to interact with an MCP Server that exposes a RESTful inventory service. If you’ve followed along with Part 1 and Part 2, you now have an MCP-compliant FastAPI app

Modern AI Integrations: MCP Server Meets REST API and Local LLMs, Part 2

Modern AI Integrations: MCP Server Meets REST API and Local LLMs, Part 2

In Part 1, we built a FastAPI-based application to manage warehouse orders and exposed it as an MCP server. We demonstrated how the Model Context Protocol (MCP) can be used to describe APIs in a structured way and make them discoverable to AI agents or MCP client. Now, in Part

Modern AI Integrations: MCP Server Meets REST API and Local LLMs, Part 1

Modern AI Integrations: MCP Server Meets REST API and Local LLMs, Part 1

As AI workflows become more modular and service-driven, integrating local LLMs into existing infrastructure becomes essential. One way to achieve this is through the Model Context Protocol (MCP), which allows services and models to expose structured, discoverable metadata. In this post, we demonstrate how to connect an MCP server with

Turn Ideas into Income: Create AI-Driven Content Pipelines with Local LLMs

Turn Ideas into Income: Create AI-Driven Content Pipelines with Local LLMs

The rise of Large Language Models (LLMs) has completely changed how we create and distribute content. From blog posts to documentation, tutorials to newsletters, what used to take hours can now be done in minutes. But even better—you can now turn this content into income with ease. And you

Google Agent-to-Agent (A2A) Protocol Explained — with Real Working Examples

Google Agent-to-Agent (A2A) Protocol Explained — with Real Working Examples

There are already tons of blog posts and vlogs floating around about agent-based systems, protocols, and AI orchestration. Most of them go deep into the theory or stick to flashy diagrams — but leave developers wondering:"Okay, but how do I actually use this?" In this post, I’ll

OpenAI Agents SDK with local LLM

OpenAI Agents SDK with local LLM

The OpenAI Agents SDK is a Python-based framework designed for building production-ready AI agent applications. It provides a streamlined approach to creating agentic systems where multiple AI agents collaborate through task delegation and tool usage. Core Components: * Agent Loop: Manages iterative task execution with integrated tool usage and result processing.

Model Context Protocol (MCP): Connecting Local LLMs to Various Data Sources

Model Context Protocol (MCP): Connecting Local LLMs to Various Data Sources

Anthropic launched the Model Context Protocol (MCP) in November 2024 — an open standard for data exchange between LLMs and various data sources. The protocol provides a simplified way for LLMs to integrate with tools and services to perform tasks such as searching files on local systems, accessing GitHub repositories to

Minion(s): A Simple Protocol for Communicating with Local and Cloud LLMs

Minion(s): A Simple Protocol for Communicating with Local and Cloud LLMs

Recently, HazyResearch introduced a simple communication protocol for integrating local and cloud LLMs. The core idea behind the protocol is to maximize the use of local LLM models with local data, minimizing cloud API costs while maintaining high-quality outputs. The protocol comes in two flavors: * Minion: A local LLM model

Web crawling for RAG with CrawlAI

Web crawling for RAG with CrawlAI

The importance of AI-powered web crawling and data extraction cannot be overstated. With the exponential growth of online data, businesses and organizations need efficient and accurate methods for collecting and analyzing data to inform their decision-making processes. Crawl4AI and Ollama offer a range of features and benefits that can help

How to Use Retrieval-Augmented Generation (RAG) locally

How to Use Retrieval-Augmented Generation (RAG) locally

In this blog post, we'll explore how to use Retrieval-Augmented Generation (RAG) for building more effective and engaging conversational AI applications. We'll cover the basics of RAG, its benefits, and provide step-by-step instructions on how to develop your own RAG mechanism for local use. What is

How to Use Llama 3.2 Vision Models-part-1

How to Use Llama 3.2 Vision Models-part-1

How to Use Llama 3.2 Vision Models: From Local Inference to API Integration, part 1 Llama 3.2, the latest iteration of the LLaMA series, brings enhanced multimodal capabilities, including a powerful vision model. Whether you're processing images for analysis, generating visual content, or building AI-driven applications,

First step to the world of AI: installing a local LLM

First step to the world of AI: installing a local LLM

Installing a local LLM After a long time, I've decided to embark on my journey with AI. Over this period, significant progress has been made in the field. Today, we're surrounded by numerous Large Language Model (LLM) models, tools, and agents. It's therefore timely