Skip to main content
Ctrl+K
PyFlink 1.20+vvr.11.7.dev0 documentation - Home PyFlink 1.20+vvr.11.7.dev0 documentation - Home
  • API Reference
  • Examples
  • API Reference
  • Examples

Section Navigation

  • PyFlink Table
  • PyFlink DataStream
  • PyFlink DataFrame
    • DataFrame
    • DataFrame Creation
    • Input/Output
    • SQL
    • DataType
    • User Defined Functions
    • Configuration
    • GPU Support
    • AI / LLM
  • PyFlink Common
  • API Reference
  • PyFlink DataFrame
  • AI / LLM
  • pyflink.dataframe.ai.providers.GenericProvider

pyflink.dataframe.ai.providers.GenericProvider#

class GenericProvider(name: str, **options: Any)[source]#

Generic provider for unknown or custom model providers.

Options are passed through to the Java side as-is without any key name translation.

Parameters:
  • name – Provider identifier recognized by Flink’s Java runtime.

  • **options – Arbitrary key-value options.

Example::
>>> provider = GenericProvider("my-provider", endpoint="https://...",
...                           **{"api-key": "sk-..."})

Methods

model_option_key()

Return the Java-side option key used for a per-call model name.

provider_name()

Return the provider identifier recognized by Flink's Java runtime.

to_options()

Return all configured options as a dict with Java-side key names.

previous

pyflink.dataframe.ai.providers.TritonProvider

next

pyflink.dataframe.ai.llm.LLMAccessor.predict

On this page
  • GenericProvider

This Page

  • Show Source

Created using Sphinx 7.4.7.

Built with the PyData Sphinx Theme 0.16.1.