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

    LangChain Assistant

    Ask a question to get started

    Enter to send•Shift+Enter new line

    Menu

    MCP Adapters
    Standard Tests
    Text Splitters
    OverviewAgentsCallbacksChainsChat modelsEmbeddingsEvaluationGlobalsHubMemoryOutput parsersRetrieversRunnablesLangSmithStorage
    Language
    Theme
    Pythonlangchain-classicagentsconversationalbaseConversationalAgentcreate_prompt
    Methodā—Since v1.0

    create_prompt

    Copy
    create_prompt(
      cls,
      tools: Sequence[BaseTool],
      prefix: str = PREFIX
    View source on GitHub
    ,
    suffix
    :
    str
    =
    SUFFIX
    ,
    format_instructions
    :
    str
    =
    FORMAT_INSTRUCTIONS
    ,
    ai_prefix
    :
    str
    =
    'AI'
    ,
    human_prefix
    :
    str
    =
    'Human'
    ,
    input_variables
    :
    list
    [
    str
    ]
    |
    None
    =
    None
    )
    ->
    PromptTemplate

    Parameters

    NameTypeDescription
    tools*Sequence[BaseTool]

    List of tools the agent will have access to, used to format the prompt.

    prefixstr
    Default:PREFIX

    String to put before the list of tools.

    suffixstr
    Default:SUFFIX

    String to put after the list of tools.

    format_instructionsstr
    Default:FORMAT_INSTRUCTIONS
    ai_prefixstr
    Default:'AI'
    human_prefixstr
    Default:'Human'
    input_variableslist[str] | None
    Default:None

    Create prompt in the style of the zero-shot agent.

    Instructions on how to use the tools.

    String to use before AI output.

    String to use before human output.

    List of input variables the final prompt will expect. Defaults to ["input", "chat_history", "agent_scratchpad"].