Using the Large Language Models (LLMs) in Generative AI

The playground is an interface in the Oracle Cloud Console for exploring the hosted pretrained and custom models in OCI Generative AI without writing a single line of code. Use the playground to test your use cases and refine prompts and parameters. When you're happy with the results, integrate the generated code into your applications.

In addition to the playground, you can generate text, summarize, or generate embeddings using the Generative AI Inference API operations and the Generative AI Inference CLI commands.

You can perform the following tasks with the OCI Generative AI large language models (LLMs):

  • Generate text: Run prompts to generate or classify text or extract information from text.
  • Summarize: Use as an executive summary generator for documents that are too long to read and summarize any type of text into free-form paragraphs or bullet points and optionally specify the tone.
  • Generate embeddings for text: Provide sentences and phrases and have the model group those sentences based on their meaning. Then use the generated embeddings in applications.