AI Accelerator - Pipelines 2.1.1 release notes

The model names openai_embedding and openai_completion have been renamed to embeddings and completions respectively. The old names are still supported for backward compatibility.

Improve model provider credential management in the create_model() call. New credentials no longer get silently ignored if credentials already exist.

The handler has no functionality but it satisfies the FDW handler interface. This avoids certain issues with PG system calls that happen when FDWs don't have any handlers.

For retrievers with table sources, the source table and vector table can now be in any schema in the PG database. The schema can either be passed during retriever creation (fully qualified identifier) or can be omitted. If the schema is omitted, we resolve and store the applicable schema.