Ctrl+K
Logo image Logo image

Site Navigation

  • API Reference
  • Examples

Site Navigation

  • API Reference
  • Examples

Section Navigation

  • PyFlink Table
  • PyFlink DataFrame
    • DataFrame
    • DataFrame Creation
    • Input/Output
    • SQL
    • Data Types
    • User Defined Functions
    • Configuration
    • Catalog
    • GPU Support
    • AI / LLM
  • PyFlink Multimodal
  • PyFlink DataStream
  • PyFlink Common

pyflink.dataframe.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([input_columns])

Return Java-side options for ModelDescriptor.

previous

pyflink.dataframe.TritonProvider

next

pyflink.dataframe.ai.llm.LLMAccessor.vector_search

Show Source

Created using Sphinx 4.5.0.