Function pull

Parameters

• ownerRepoCommit: string

  The name of the repo containing the prompt, as well as an optional commit hash separated by a slash.

• Optionaloptions: {
      apiKey?: string;
      apiUrl?: string;
      includeModel?: boolean;
      modelClass?: new (...args: any[]) => BaseLanguageModel;
      secrets?: Record<string, string>;
      secretsFromEnv?: boolean;
  }

  • OptionalapiKey?: string

    LangSmith API key to use when pulling the prompt

  • OptionalapiUrl?: string

    LangSmith API URL to use when pulling the prompt

  • OptionalincludeModel?: boolean

    Whether to also instantiate and attach a model instance to the prompt, if the prompt has associated model metadata. If set to true, invoking the resulting pulled prompt will also invoke the instantiated model. For non-OpenAI models, you must also set "modelClass" to the correct class of the model.

  • OptionalmodelClass?: new (...args: any[]) => BaseLanguageModel

    If includeModel is true, the class of the model to instantiate. Required for non-OpenAI models. If you are running in Node or another environment that supports dynamic imports, you may instead import this function from "langchain/hub/node" and pass "includeModel: true" instead of specifying this parameter.

  • Optionalsecrets?: Record<string, string>

    A map of secrets to use when loading, e.g. {'OPENAI_API_KEY': 'sk-...'}. If a secret is not found in the map, it will be loaded from the environment if secrets_from_envisTrue. Should only be needed when includeModelistrue`.

  • OptionalsecretsFromEnv?: boolean

    Whether to load secrets from environment variables. Use with caution and only with trusted prompts.