What You’ll Learn By the end of this tutorial, you’ll understand how to build a Model Context Protocol (MCP) server in Rust that exposes tools AI assistants can use. We’ll build a simple calculator service with four operations. Prerequisites What is MCP? The Model Context Protocol (MCP) is a standard that allows AI assistants to […]
Regardless of whether AI is a bubble or not, it might be wise to build systems that are not dependent on AI for them to be able to function. My jobstr.work site is one such concept. Sure AI can query the relays and answer questions about the jobs listed, but equally you can use the […]
The traditional job search process “sucks” – it is characterised by closed platforms which creates a “recruitment shїtshow”. Don’t just take my words for that, try Indeed or Reed or LinkedIn! Same job listed multiple times… Remote, but different “location” jobstr.work is a real solution, working via a decentralised platform for listing jobs that combines […]
Note, this article is written by me, the human who wrote the code! If you use LLMs you will need to check their output, else hallucinations, wrong answers, and unhappy customers. Note, this code is all open source, aka “Free” I built “evaluate” as the server, which does the calls to the LLMs, and you […]
What is x.max(0.0)? x.max(0.0) returns the maximum value between x and 0.0. It’s Rust’s method for finding the larger of two numbers. ReLU Worked Examples: ReLU (Rectified Linear Unit) formula: ReLU(x) = max(0, x) This means: Here are concrete examples: Visual Example: Why ReLU is Powerful: Comparison with Sigmoid: ReLU is like a one-way gate: […]
CANDLE Handles all the heavy mathematical lifting – matrix multiplications, softmax, broadcasting, gradients, and hardware acceleration. Think of it like “NumPy” for AI, for Rust! Candle lets you run ML models entirely inside a Rust program, without Python or a separate service like Ollama. The Magic: When you write something like q.matmul(&k.t())?.softmax(D::Minus1)?, CANDLE automatically: So […]
Once you have Docker installed, you can simply run Qdrant with an API key For testing, just make your own value without the API key you chose -> Qdrant Rust Client Create a “collection” and “upsert” some data Do a vector search Filter search Prepare a model to do embeddings with Qdrant (fastembed) *Each model […]
rmcp was updated July 16 2025 – this article looks as how to use the latest custom procedural macro attributes and build a minimalist example. There are some significant differences to earlier versions and we analyze them here. What you read here is not in the documentation, I have spent a few hours identifying the […]
Revisiting A’ Level Maths – Calculus with the help of AI 🔢 What is Calculus? Calculus is the branch of mathematics that studies change. It has two big halves: 1. Differential Calculus 2. Integral Calculus Bonus: They’re Connected! They’re two sides of the same coin — and the Fundamental Theorem of Calculus links them.It basically […]
Rather than use Rig.rs or Ollama-rs let’s consider the bare bones of the frameworks that we take for granted.. We make a POST reqwest to the Ollama API and send a body specifying the model and messages ( role & content ). Next – iterate over the stream and display the chunks until there are […]