Starburst AI

Artificial intelligence (AI) is the ability of a constructed machine, such as a computer, to simulate or duplicate human cognitive tasks. A machine with AI can make calculations, analyze data in order to create predictions, identify various types of signs and symbols, converse with humans, and help execute tasks without manual input.

Starburst AI brings artificial intelligence capabilities to your data applications, letting you seamlessly integrate with large language models (LLMs). With Starburst AI, you can use retrieval-augmented generation (RAG), embeddings, and LLMs for a wide range of use cases.

Note

Starburst Enterprise AI is available as a private preview. Contact your Starburst account team for further information.

Get started

Starburst Enterprise supports a variety of embedding and language models. The following topics cover configuration of AI models, providers, and functions.

• Configure Starburst AI
  • Configuration
  • Providers
    • AWS Bedrock
      • Configuration
    • OpenAI
      • Configuration
• AI functions
  • Embedding functions
    • ai.generate_embeddings()
  • Prompt functions
    • ai.prompt()
  • Task functions
    • ai.analyze_sentiment()
    • ai.classify()
    • ai.fix_grammar()
    • ai.mask()
    • ai.translate()
  • Use cases

What are embeddings?

Embedding models transform input data—such as text, images, or other content types—into dense numerical vectors that capture the meaning and context of the data. These vectors enable advanced capabilities like semantic search, letting you find similar content based on meaning rather than exact matches. Embeddings are also commonly used for grouping or clustering text based on shared ideas or topics.

What are language models?

Language models take text as input and predict or generate the next likely sequence of words based on learned probability distributions. These models are trained on vast datasets to understand context, grammar, and semantics, enabling them to perform tasks like text generation, summarization, translation, and conversational AI. By leveraging these probabilistic predictions, language models power a wide variety of applications in natural language processing.