completion_with_retry_batching#

langchain_community.llms.fireworks.completion_with_retry_batching(

llm: Fireworks,

use_retry: bool,

*,

run_manager: CallbackManagerForLLMRun | None = None,

**kwargs: Any,

) → Any[source]#

Use tenacity to retry the completion call.

Parameters:

• llm (Fireworks)

• use_retry (bool)

• run_manager (CallbackManagerForLLMRun | None)

• kwargs (Any)

Return type:

Any