Scikit-learn is an open-source library for developing machine learning models using Python. It supports the traditional approaches to regression, classification and clustering tasks and covers the full ML workflow from training to evaluation.

Google Drive is a cloud storage service for storing files online. It enables secure sharing, collaboration and access to files across applications, supporting document management, data storage and easy integration into AI workflows.

Microsoft Azure is a large collection of cloud services for building, running and storing applications and data without physical hardware. AI Modeler utilises the object storage service for storing documents, datasets, and other files.

DeepSeek is a large language model used for conversational AI and general text generation. It is commonly used for research tasks, writing content, support with coding, answering questions and a wide range of other AI applications.

Stable Diffusion is a generative AI model that creates photo-realistic images from text prompts. It is widely used in creative and design applications to generate stylised or artistic visuals in concept design and content creation.

Google BigQuery is a production-grade cloud data warehouse for storing and analysing large-scale datasets. It allows SQL-based querying of structured and semi-structured data without the need to manage the underlying infrastructure.

Gradio is an open-source library for building simple user interfaces in both machine learning and AI applications. Interaction with models is achieved through web-based inputs and outputs, enabling easy user testing and sharing.

MLflow is a platform for managing the machine learning lifecycle and is used to track experiments, version models and organise workflows. It supports the consistent and structured development, testing and deployment of AI models.

Docker is an open-source platform for building, packaging and running applications in containers. It ensures that applications run consistently across different environments by bundling the application and its dependencies.

FastAPI is an open-source framework for building APIs with Python and enables fast, structured communication through defined endpoints. It is used to facilitate data exchange between models, databases and user interfaces.

Python Package Index (PyPi) is a public package repository widely used in the distribution and installation of Python code libraries. It supports effective dependency management and robust, scalable application development.

Prefect is an open-source workflow orchestration platform used to design, schedule, and monitor data and machine learning pipelines. It enables automation of workflows and manages task dependencies and execution.

GitHub is a platform used for storing, managing, and sharing code using version control. It enables the tracking of changes, collaboration between software developers and assists in the overall organisation of coding projects.

Kaggle is a platform for data science and machine learning that provides datasets, notebooks, and competitions. It is used for education, research, experimentation and also for building predictive models in AI workflows.

Hugging Face is a platform for building, sharing and deploying machine learning and AI models. It provides free access to many pre-trained models, datasets and tools that are used for NLP tasks and in AI application development.

Pinecone is a production-grade, managed vector database for storing and searching in high-dimensional data. It is widely used in AI applications for semantic search in knowledge base retrieval and recommender systems.

Tavily is an online search API designed for AI applications, providing access to real-time information. It enables the retrieval of relevant, up-to-date content from the web and supports tasks such as research and question answering.

Google Cloud Platform is a collection of cloud services for building, running and storing applications and data without physical hardware. AI Modeler utilises the object storage service for storing documents, datasets and other files.

ChatGPT is a large language model used for conversational AI and general text generation. It is commonly used for research tasks, writing content, support with coding, answering questions and a wide range of other AI applications.

Amazon Web Services is a collection of cloud services for building, running and storing applications and data without physical hardware. AI Modeler utilises the object storage service for storing documents, datasets, and other files.

Claude is a large language model used for both conversational AI and general text generation. It is commonly used for research tasks, writing content, support with coding, answering questions and a wide range of other AI applications.

Streamlit is an open-source framework for building interactive web applications in Python. It is used to create simple user interfaces for data and AI projects, allowing results to be displayed and explored in a clear, accessible way.

Command R is a large language model used for conversational AI and general text generation. It is commonly used for research tasks, writing content, support with coding, answering questions and a wide range of other AI applications.

FAISS is an open-source library used to search and compare large collections of data using semantic similarity. It is efficient at finding related sections or chunks of text and is widely used in AI to support LLM retrieval systems.