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 […]
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 […]
Documenting what I’ve learned creating a Dockerized MCP Server in Python 👍 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) […]
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 […]
Writing Data to a File When working with Rust, interacting with external APIs like OpenAI’s ChatGPT or writing data to files is common. In this article, we’ll address a couple of important questions regarding writing a Python script generated from the ChatGPT API to a file and converting data between types in Rust. Specifically, we’ll […]
https://github.com/0xPlaygrounds/rig/blob/main/rig-qdrant/examples/qdrant_vector_search.rs In the tuple |(d, embeddings)|, the components correspond to the values yielded by documents.into_iter() Thus: Example of OneOrMany Utility Type in Rust Breakdown: Example Output: In this case, OneOrMany makes it flexible to handle cases where you might have a single embedding or multiple embeddings, while keeping the code concise and readable.
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 […]
Introduction FastEmbed is a lightweight and fast Python library designed for generating high-quality text embeddings. FastEmbed supports a variety of popular text models and is continuously expanding to include more. At its core, FastEmbed utilizes the Flag Embedding model from the MTEB leaderboard, offering distinct “query” and “passage” prefixes for input text. This feature makes […]
Introduction In this guide, we will compare Rust and Python for asynchronous and multithreaded operations, particularly focusing on uploading data to a Qdrant vector search engine. We will evaluate how using Arc in Rust and AsyncQdrantClient in Python impacts performance. Imagine you get approached by a company to speed up their code and you improve […]
Webdock – Fast Cloud VPS Linux Hosting Introduction Let’s see how to create a text similarity search web app using Flask, a pre-trained BERT model, and FAISS for efficient similarity search! Section 1: Importing Libraries “First, we need to import all the necessary libraries. We’ll be using Flask to create our web application, Hugging Face’s […]