Generate code for development tasks in programming languages like Python, JavaScript, Prolog, Fortran, and Verilog with human language descriptions.
New customers get $300 in free credits to generate code and more in Vertex AI.
Overview
AI code generation is the use of artificial intelligence (AI) and machine learning (ML) to create code based on a user’s conversational prompt. Google Cloud powers its code generation AI with PaLM 2, a state-of-the-art language model with coding capabilities. Code can be generated based on general best practices, organizational governance, and even a natural language description of the desired code.
Google's most capable AI Gemini includes AI that not only generates code, but also helps with debugging and code explanation. Gemini can handle more than 20 programming languages, including C++, Go, Java, Javascript, Python and Typescript. Google Cloud’s Vertex AI also includes a suite of models called Codey APIs that generate code, power chats, and aid in code completion.
Developers now have access to a wide variety of AI solutions for code generation. Google Cloud’s Vertex AI offers generative AI models that allow for all types of content generation, including code. Vertex AI leverages Google's cutting edge Pathways Language Model 2 (PaLM 2) to generate text and code in response to conversational prompts—even across various human languages.
Google Cloud’s Vertex AI includes a suite of models that work with code called Codey APIs. These APIs include three models that not only generate code, but can suggest code for code completion and let developers get code-related questions through a conversational interface.
Vertex AI’s Codey APIs supports Python and many other programming languages including: C++, C#, Go, GoogleSQL, Java, JavaScript, Kotlin, PHP, Python, Ruby, Rust, Scala. Swift, TypeScript. Codey APIs also supports the following infrastructure as code interfaces: Google Cloud CLI, Kubernetes Resource Model (KRM), and Terraform.
How It Works
AI code generation uses machine learning models and algorithms trained on programming languages and publicly available source code to generate code. Google Cloud’s foundation models allow developers to build next-generation applications with access to multimodal models from Google, including code generation and code completion models with Codey.
Common Uses
Vertex AI includes a suite of models that work with code referred to as the Codey APIs. Codey can generate code based on a natural language description of the desired code, power a chatbot that assists with code-related questions, and provide auto-completion suggestions as you code.
Vertex AI includes a suite of models that work with code referred to as the Codey APIs. Codey can generate code based on a natural language description of the desired code, power a chatbot that assists with code-related questions, and provide auto-completion suggestions as you code.
Gemini Code Assist gives application developers and data engineers code recommendations in real time, full function and code blocks, and identifies vulnerabilities and errors in the code, while suggesting fixes. Developers will find code assistance through a chat interface, Cloud Shell Editor, or via our Cloud Code IDE extensions for VSCode and JetBrains IDEs. It supports multiple languages including Go, Java, Javascript, Python, and SQL.
Gemini Code Assist gives application developers and data engineers code recommendations in real time, full function and code blocks, and identifies vulnerabilities and errors in the code, while suggesting fixes. Developers will find code assistance through a chat interface, Cloud Shell Editor, or via our Cloud Code IDE extensions for VSCode and JetBrains IDEs. It supports multiple languages including Go, Java, Javascript, Python, and SQL.