Use PL/SQL Packages to Generate Embeddings

Choose to implement Vector Utility PL/SQL packages to perform chunking, embedding, and text generation operations along with text processing and similarity search, within and outside Oracle Database.

Vector Utility PL/SQL APIs work with both the ONNX embedding models (loaded into the database) and third-party REST providers, such as Cohere, Google AI, Hugging Face, Oracle Cloud Infrastructure (OCI) Generative AI, OpenAI, or Vertex AI. You can create, run, and schedule end-to-end data transformation and search pipelines.

These packages are made up of subprograms, such as chainable utility functions and vector helper procedures.

• Terms of Using Vector Utility PL/SQL Packages
  You must understand the terms of using REST APIs that are part of Vector Utility PL/SQL packages.
• About Chainable Utility Functions and Common Use Cases
  These are intended to be a set of chainable and flexible "stages" through which you pass your input data to transform into a different representation, including vectors.
• About Vector Helper Procedures
  Vector helper procedures let you configure authentication credentials and language-specific data, for use in chainable utility functions.
• Supplied Vector Utility PL/SQL Packages
  Use either a lightweight DBMS_VECTOR package or a more advanced DBMS_VECTOR_CHAIN package with full capabilities.
• Supported Third-Party Provider Operations
  Review the list of third-party REST providers that are supported with Vector Utility PL/SQL packages and the corresponding REST API calls allowed for each of those.
• Validate JSON Input Parameters
  You can optionally validate the structure of your JSON input to the DBMS_VECTOR.UTL and DBMS_VECTOR_CHAIN.UTL functions, which use JSON to define their input parameters.