TorchServe is PyTorch’s official model serving framework, designed to take a trained PyTorch model from a .pt or .pth file to a production HTTP endpoint with minimal configuration. It handles the serving infrastructure — request batching, multi-model management, logging, metrics, and health checks — so you can focus on your model and handler logic rather … Read more
ONNX Runtime is a high-performance inference engine for machine learning models in the ONNX (Open Neural Network Exchange) format. It accelerates model inference across CPUs, GPUs, and specialised hardware, with optimisations that often produce 2–10x speedups over running the same model in its original framework. For teams deploying ML models in production — whether on … Read more
The MCP Web Search Server gives AI assistants the ability to search the web during a conversation, pulling in current information that goes beyond their training data cutoff. Instead of the AI saying “I don’t have information about recent events,” it can search, read results, and answer with up-to-date data. For developers, analysts, and researchers … Read more
The MCP Database Server connects AI assistants directly to your database, letting them query data, inspect schemas, and answer questions about your data in natural language without requiring you to write SQL or export data manually. Instead of asking “how do I write a query to find all users who signed up last month and … Read more
browser-use is an open-source Python library that connects AI agents to a real web browser, letting them navigate websites, fill forms, click buttons, extract information, and interact with web applications through natural language instructions. Unlike web scraping libraries that parse static HTML, browser-use controls an actual browser — it handles JavaScript-rendered content, authentication flows, multi-step … Read more
The MCP Filesystem Server gives AI assistants like Claude direct access to read and write files on your local machine or a specified directory. Rather than copying file contents into a chat manually, you connect the server once and the AI can browse directories, read files, create new ones, and make edits — all through … Read more
GPT-4o’s vision capabilities allow you to send images alongside text prompts and receive detailed, contextually aware responses about what the model sees. Released as part of GPT-4o in mid-2024, the vision API accepts standard image formats, handles multiple images per request, and produces responses that range from simple descriptions to complex reasoning about visual content. … Read more
Google’s Gemini models are natively multimodal — they were trained from the ground up to understand text, images, audio, video, and documents together rather than having vision bolted on as a separate capability. The Gemini API exposes this through a unified interface where any combination of these modalities can appear in the same request. For … Read more
Building a voice assistant with local LLMs means combining three components: a speech-to-text model that transcribes your voice, a language model that understands and responds, and a text-to-speech model that speaks the response aloud. None of these need to touch external servers — Whisper handles transcription locally, Ollama runs the LLM, and tools like Piper … Read more
Transcribing and analysing video with AI combines two capabilities — speech-to-text for the audio track and vision or language understanding for the content — to produce searchable transcripts, summaries, topic extractions, and structured insights from video at scale. The tooling for this has matured significantly: Whisper handles transcription reliably, and frontier LLMs handle analysis of … Read more
