LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
  • Overview
  • MCP Adapters
    • Overview
    • Agents
    • Callbacks
    • Chains
    • Chat models
    • Embeddings
    • Evaluation
    • Globals
    • Hub
    • Memory
    • Output parsers
    • Retrievers
    • Runnables
    • LangSmith
    • Storage
    Standard Tests
    Text Splitters
    ⌘I

    LangChain Assistant

    Ask a question to get started

    Enter to send•Shift+Enter new line

    Menu

    MCP Adapters
    OverviewAgentsCallbacksChainsChat modelsEmbeddingsEvaluationGlobalsHubMemoryOutput parsersRetrieversRunnablesLangSmithStorage
    Standard Tests
    Text Splitters
    Language
    Theme
    Pythonlangchain-classicoutput_parsersretryRetryWithErrorOutputParserfrom_llm
    Method●Since v1.0

    from_llm

    Create a RetryWithErrorOutputParser from an LLM.

    Copy
    from_llm(
      cls,
      llm: BaseLanguageModel,
      parser: BaseOutputParser[T],
      prompt: BasePromptTemplate = NAIVE_RETRY_WITH_ERROR_PROMPT,
      max_retries: int = 1
    ) -> RetryWithErrorOutputParser[T]

    Parameters

    NameTypeDescription
    llm*BaseLanguageModel

    The LLM to use to retry the completion.

    parser*BaseOutputParser[T]

    The parser to use to parse the output.

    promptBasePromptTemplate
    Default:NAIVE_RETRY_WITH_ERROR_PROMPT

    The prompt to use to retry the completion.

    max_retriesint
    Default:1

    The maximum number of times to retry the completion.

    View source on GitHub