Generative AI

AI systems that can create new content, such as text, images, or music.

Best match

computer-vision

An interdisciplinary field that enables computers to interpret and process visual information from the world.

Best match

deepfake

A synthetic media in which a person in an image or video is replaced with someone else's likeness.

generative-adversarial-networks

A class of machine learning frameworks that generate new data samples via adversarial training.

variational-autoencoder

A generative model that learns to represent data in a latent space using variational inference.

Generative Modeling

A type of modeling that generates new data instances that resemble the training data.

retrieval augmented generation

Retrieval-augmented generation (RAG) grounds answers on retrieved documents instead of parametric memory alone.

synthetic-data-generation

The process of creating artificial data that mimics real-world data for training machine learning models.

auto-encoding

A type of artificial neural network used to learn efficient codings of unlabeled data.

natural-language-generation

The use of algorithms to produce human-like text based on given data or prompts.

DALL·E 3

Instruction-following image generation model integrated with safety classifiers and chat-native prompting flows.

Best match

GPT-4o

Flagship multimodal model tuned for tool use, vision understanding, and low-latency chat experiences across consumer and enterprise surfaces.

Best match

Grok-2

xAI flagship chat model positioned for real-time knowledge integrations and high-throughput conversational products.

Midjourney

Midjourney specializes in generating artistic images from text prompts with an emphasis on creative styles and artistic interpretations, supporting large resolutions of up to 2048x2048 pixels.

Mixtral

Mixtral integrates large language processing with generative capabilities, managing up to 16,384 tokens while delivering high-quality content creation and response generation.

text-embedding-3-large

High-dimensional embedding model designed for semantic search, clustering, and retrieval with adjustable output size.

Gemini Flash

Gemini Flash focuses on fast inference with a 4k token limit, ideal for applications requiring quick responses while maintaining decent accuracy in language tasks.

Vercel AI SDK

TypeScript SDK for building AI features in web apps with streaming responses, multi-provider model adapters, and ergonomic server/client integration patterns.

Best match

OpenAI Playground

Provider of widely used frontier model APIs for text, vision, and audio, with strong developer tooling and broad ecosystem adoption across production AI applications.

Best match

Hugging Face Transformers

AI platform and model hub for discovering, hosting, and deploying open models, datasets, and inference endpoints across NLP, vision, audio, and multimodal tasks.

Vertex AI

Google Cloud Vertex AI is a managed platform for training, tuning, and serving models—including Gemini and partner models—with IAM integration, VPC-SC, and data residency options for enterprises that already standardize on Google Cloud for analytics and data lakes.

Fireworks AI

Fireworks AI offers fast, serverless inference APIs for leading open and proprietary models with a focus on low-latency chat and batch workloads, plus deployment options for teams standardizing on a single inference surface for production assistants and eval harnesses.

Agent Memory: Scratchpad vs Vector Store

This tutorial compares scratchpad memory and vector store memory in AI agents, focusing on their use cases and performance characteristics. Prerequisites include a basic understanding of AI memory architectures.

Best match

Establishing SLI/SLO for Generative AI Endpoints in Customer Support

This tutorial guides you through setting up Service Level Indicators (SLIs) and Service Level Objectives (SLOs) for generative AI endpoints used in customer support scenarios. Prerequisites include familiarity with service metrics and basic knowledge of AI endpoint operations.

Best match

Together AI vs Groq

Together AI emphasizes hosted open-weight serving and fine-tuning with flexible GPU-backed endpoints; Groq focuses on ultra-low-latency inference via specialized hardware. Choose based on whether you need model breadth and training adjacency or maximum interactive speed for a narrower catalog.

Best match