ZapierNLAWrapper#

class langchain_community.utilities.zapier.ZapierNLAWrapper[source]#

Bases: BaseModel

Wrapper for Zapier NLA.

Full docs here: https://nla.zapier.com/start/

This wrapper supports both API Key and OAuth Credential auth methods. API Key is the fastest way to get started using this wrapper.

Call this wrapper with either zapier_nla_api_key or zapier_nla_oauth_access_token arguments, or set the ZAPIER_NLA_API_KEY environment variable. If both arguments are set, the Access Token will take precedence.

For use-cases where LangChain + Zapier NLA is powering a user-facing application, and LangChain needs access to the end-user’s connected accounts on Zapier.com, you’ll need to use OAuth. Review the full docs above to learn how to create your own provider and generate credentials.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param zapier_nla_api_base: str = 'https://nla.zapier.com/api/v1/'#
param zapier_nla_api_key: str [Required]#
param zapier_nla_oauth_access_token: str [Required]#
async alist() → List[Dict][source]#

Returns a list of all exposed (enabled) actions associated with current user (associated with the set api_key). Change your exposed actions here: https://nla.zapier.com/demo/start/

The return list can be empty if no actions exposed. Else will contain a list of action objects:

[{

“id”: str, “description”: str, “params”: Dict[str, str]

}]

params will always contain an instructions key, the only required param. All others optional and if provided will override any AI guesses (see “understanding the AI guessing flow” here: https://nla.zapier.com/api/v1/docs)

Return type:

List[Dict]

async alist_as_str() → str[source]#

Same as list, but returns a stringified version of the JSON for insertting back into an LLM.

Return type:

str

async apreview(action_id: str, instructions: str, params: Dict | None = None) → Dict[source]#

Same as run, but instead of actually executing the action, will instead return a preview of params that have been guessed by the AI in case you need to explicitly review before executing.

Parameters:

  • action_id (str)

  • instructions (str)

  • params (Dict | None)

Return type:

Dict

async apreview_as_str(*args, **kwargs) → str[source]#

Same as preview, but returns a stringified version of the JSON for insertting back into an LLM.

Return type:

str

async arun(action_id: str, instructions: str, params: Dict | None = None) → Dict[source]#

Executes an action that is identified by action_id, must be exposed (enabled) by the current user (associated with the set api_key). Change your exposed actions here: https://nla.zapier.com/demo/start/

The return JSON is guaranteed to be less than ~500 words (350 tokens) making it safe to inject into the prompt of another LLM call.

Parameters:

  • action_id (str)

  • instructions (str)

  • params (Dict | None)

Return type:

Dict

async arun_as_str(*args, **kwargs) → str[source]#

Same as run, but returns a stringified version of the JSON for insertting back into an LLM.

Return type:

str

list() → List[Dict][source]#

Returns a list of all exposed (enabled) actions associated with current user (associated with the set api_key). Change your exposed actions here: https://nla.zapier.com/demo/start/

The return list can be empty if no actions exposed. Else will contain a list of action objects:

[{

“id”: str, “description”: str, “params”: Dict[str, str]

}]

params will always contain an instructions key, the only required param. All others optional and if provided will override any AI guesses (see “understanding the AI guessing flow” here: https://nla.zapier.com/docs/using-the-api#ai-guessing)

Return type:

List[Dict]

list_as_str() → str[source]#

Same as list, but returns a stringified version of the JSON for insertting back into an LLM.

Return type:

str

preview(action_id: str, instructions: str, params: Dict | None = None) → Dict[source]#

Same as run, but instead of actually executing the action, will instead return a preview of params that have been guessed by the AI in case you need to explicitly review before executing.

Parameters:

  • action_id (str)

  • instructions (str)

  • params (Dict | None)

Return type:

Dict

preview_as_str(*args, **kwargs) → str[source]#

Same as preview, but returns a stringified version of the JSON for insertting back into an LLM.

Return type:

str

run(action_id: str, instructions: str, params: Dict | None = None) → Dict[source]#

Executes an action that is identified by action_id, must be exposed (enabled) by the current user (associated with the set api_key). Change your exposed actions here: https://nla.zapier.com/demo/start/

The return JSON is guaranteed to be less than ~500 words (350 tokens) making it safe to inject into the prompt of another LLM call.

Parameters:

  • action_id (str)

  • instructions (str)

  • params (Dict | None)

Return type:

Dict

run_as_str(*args, **kwargs) → str[source]#

Same as run, but returns a stringified version of the JSON for insertting back into an LLM.

Return type:

str

Examples using ZapierNLAWrapper

On this page