Class ChatPromptClient

constructor

• new ChatPromptClient(prompt: Chat, isFallback?: boolean): ChatPromptClient

  Creates a new ChatPromptClient instance.

  Parameters

  • prompt: Chat

    The chat prompt data
  • isFallback: boolean = false

    Whether this is fallback content

  Returns ChatPromptClient

Readonlyprompt

ReadonlypromptResponse

compile

• compile(
      variables?: Record<string, string>,
      placeholders?: Record<string, any>,
  ): any[]

  Compiles the chat prompt by replacing placeholders and variables.

  First resolves placeholders with provided values, then applies variable substitution to message content using Mustache templating. Unresolved placeholders remain as placeholder objects in the output.

  Parameters

  • Optionalvariables: Record<string, string>

    Key-value pairs for Mustache variable substitution in message content
  • Optionalplaceholders: Record<string, any>

    Key-value pairs where keys are placeholder names and values are ChatMessage arrays

  Returns any[]

  Array of ChatMessage objects and unresolved placeholder objects

  Example

  const prompt = await langfuse.prompt.get("conversation", { type: "chat" });
  const compiled = prompt.compile(
    { user_name: "Alice" },
    { examples: [{ role: "user", content: "Hello" }, { role: "assistant", content: "Hi!" }] }
  );
  Copy

getLangchainPrompt

• getLangchainPrompt(options?: { placeholders?: Record<string, any> }): any[]

  Converts the prompt to LangChain ChatPromptTemplate format.

  Resolves placeholders with provided values and converts unresolved ones to LangChain MessagesPlaceholder objects. Transforms variables from {{var}} to {var} format without rendering them.

  Parameters

  • Optionaloptions: { placeholders?: Record<string, any> }

    Configuration object

    • Optionalplaceholders?: Record<string, any>

      Key-value pairs for placeholder resolution

  Returns any[]

  Array of ChatMessage objects and LangChain MessagesPlaceholder objects

  Example

  const prompt = await langfuse.prompt.get("conversation", { type: "chat" });
  const langchainFormat = prompt.getLangchainPrompt({
    placeholders: { examples: [{ role: "user", content: "Hello" }] }
  });
  Copy

toJSON

• toJSON(): string

  Serializes the prompt client to JSON.

  Returns string

  JSON string representation of the prompt