Llama3.2 local LLM query
1. gossipsub 2. mdns (Multicast DNS) 3. noise 4. swarm::{NetworkBehaviour, SwarmEvent} 5. tcp 6. yamux Summary Table Name Type Purpose gossipsub PubSub Message propagation in P2P networks. mdns Discovery Finds peers in local networks. noise Encryption Secure communication between peers. NetworkBehaviour, SwarmEvent Core API Defines P2P behavior and handles events. tcp Transport Reliable peer communication. […]
How to Create a Docker MCP Server in Python
Documenting what I’ve learned creating a Dockerized MCP Server in Python đź‘Ť In this article I give the links and show the syntax to build the server inside a Docker image ready for you to provide to users of Claude, Cursor and all clients capable of using an MCP server. Create Model Context Protocol (MCP) […]
Building Dynamic MCP Resources with Templates (Python)
Let’s extend our MCP server’s capabilities using resource templates – one of the most powerful features of the Model Context Protocol (MCP) ecosystem. What Are Resource Templates? Resource templates allow you to define dynamic resources using URI patterns. Unlike static resources with fixed URIs, templates let you create resources whose URIs and content can be […]
Understanding Token Usage in Conversation History with LLMs
Question: Where is this held? As tokens in the LLM? (Maintains a conversation history list with message roles and content) Answer: The conversation history is held in memory as a Python list variable, not as tokens in the LLM. In the code, you can see this implementation: This is a regular Python list that contains […]
MCP – Model Context Protocol
This article covers using the MCP Python SDK and using the Model Context Protocol Inspector It’s new, but it’s likely to be around a long time, due to it being a protocol – not a framework! What actually is MCP? How can I develop with it? https://github.com/modelcontextprotocol/python-sdk credit : https://github.com/modelcontextprotocol/python-sdk To run as a server […]
Docker for Networks
Dockerfile FROM debian:latestRUN apt-get update && apt-get install -y \iputils-ping traceroute dnsutils curl iperf3 nmap \&& apt-get cleanCMD [“/bin/bash”] Build the Docker Image Verify the Image Was Built Run the Container Now, you can run networking tools inside the container: ping 8.8.8.8traceroute google.comcurl https://example.com Remove a Specific Image To remove an image by its name […]
Querying a database directly with natural language
No SQL, no hunting through Stack Overflow for the syntax you forgot—just type in what you want, and let the LLM handle your query. We’ll use LangChain to hook up to a MySQL database with ChatGPT doing the heavy lifting. Here’s the setup: I’ve got a MySQL database full of employee data—names, hire dates, that […]
Qdrant & Rust – embeddings
While most examples for performing embeddings will be Python code, Rust is better when performance, safety, and scalability are critical. Most examples/tutorials stick to Python, maybe it’s easier to start with but let’s look beyond “getting started”. Let’s explore Qdrant some more, this time we’ll delve into the Rust client plus fastembed. (Note: If you […]
On premise AI for business
In this article we show how to leverage a Large Language Model and a Vector Database to search private data without touching the internet. Why worry? Well, for instance, 11% of data employees paste into ChatGPT is confidential! On premise AI for business is not as difficult as it may sound… This article will guide […]