Zapier 自然语言操作

已弃用 此 API 将于 2023-11-17 停止服务：https://nla.zapier.com/start/

Zapier Natural Language Actions gives you access to the 5k+ apps, 20k+ actions on Zapier's platform through a natural language API interface.

NLA supports apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot, Google Sheets, Microsoft Teams, and thousands more apps: https://zapier.com/apps Zapier NLA handles ALL the underlying API auth and translation from natural language --> underlying API call --> return simplified output for LLMs. The key idea is you, or your users, expose a set of actions via an oauth-like setup window, which you can then query and execute via a REST API.

NLA 提供 API Key 和 OAuth 两种方式用于签署 NLA API 请求。

服务器端（API 密钥）：适用于快速入门、测试以及生产场景，其中 LangChain 将仅使用开发者 Zapier 账户中公开的操作（并将使用开发者在 Zapier.com 上连接的账户）。
面向用户（OAuth）：适用于生产场景，即您正在部署面向最终用户的应用程序，且 LangChain 需要访问最终用户在 Zapier.com 上公开的操作和已连接的账户。

本快速入门主要侧重于服务器端用例以保持简洁。请跳转至使用 OAuth 访问令牌的示例，查看如何为面向用户的场景设置 Zapier 的简短示例。请参阅完整文档，获取全面的面向用户的 OAuth 开发者支持。

本示例介绍如何将 Zapier 集成与 SimpleSequentialChain 以及随后的 Agent 配合使用。代码如下：

import os

# get from https://platform.openai.com/
os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY", "")

# get from https://nla.zapier.com/docs/authentication/ after logging in):
os.environ["ZAPIER_NLA_API_KEY"] = os.environ.get("ZAPIER_NLA_API_KEY", "")

Agent 示例

Zapier 工具可以与代理一起使用。请参阅下面的示例。

from langchain.agents import AgentType, initialize_agent
from langchain_community.agent_toolkits import ZapierToolkit
from langchain_community.utilities.zapier import ZapierNLAWrapper
from langchain_openai import OpenAI

API 参考：AgentType | initialize_agent | ZapierToolkit | ZapierNLAWrapper | OpenAI

## step 0. expose gmail 'find email' and slack 'send channel message' actions

# first go here, log in, expose (enable) the two actions: https://nla.zapier.com/demo/start -- for this example, can leave all fields "Have AI guess"
# in an oauth scenario, you'd get your own <provider> id (instead of 'demo') which you route your users through first

llm = OpenAI(temperature=0)
zapier = ZapierNLAWrapper()
toolkit = ZapierToolkit.from_zapier_nla_wrapper(zapier)
agent = initialize_agent(
    toolkit.get_tools(), llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)

agent.run(
    "Summarize the last email I received regarding Silicon Valley Bank. Send the summary to the #test-zapier channel in slack."
)

[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m I need to find the email and summarize it.
Action: Gmail: Find Email
Action Input: Find the latest email from Silicon Valley Bank[0m
Observation: [31;1m[1;3m{"from__name": "Silicon Valley Bridge Bank, N.A.", "from__email": "sreply@svb.com", "body_plain": "Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG", "reply_to__email": "sreply@svb.com", "subject": "Meet the new CEO Tim Mayopoulos", "date": "Tue, 14 Mar 2023 23:42:29 -0500 (CDT)", "message_url": "https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a", "attachment_count": "0", "to__emails": "ankush@langchain.dev", "message_id": "186e393b13cfdf0a", "labels": "IMPORTANT, CATEGORY_UPDATES, INBOX"}[0m
Thought:[32;1m[1;3m I need to summarize the email and send it to the #test-zapier channel in Slack.
Action: Slack: Send Channel Message
Action Input: Send a slack message to the #test-zapier channel with the text "Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild."[0m
Observation: [36;1m[1;3m{"message__text": "Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.", "message__permalink": "https://langchain.slack.com/archives/C04TSGU0RA7/p1678859932375259", "channel": "C04TSGU0RA7", "message__bot_profile__name": "Zapier", "message__team": "T04F8K3FZB5", "message__bot_id": "B04TRV4R74K", "message__bot_profile__deleted": "false", "message__bot_profile__app_id": "A024R9PQM", "ts_time": "2023-03-15T05:58:52Z", "message__bot_profile__icons__image_36": "https://avatars.slack-edge.com/2022-08-02/3888649620612_f864dc1bb794cf7d82b0_36.png", "message__blocks[]block_id": "kdZZ", "message__blocks[]elements[]type": "['rich_text_section']"}[0m
Thought:[32;1m[1;3m I now know the final answer.
Final Answer: I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.[0m

[1m> Finished chain.[0m

'I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.'

SimpleSequentialChain 示例

如果您需要更明确的控制，请使用链，如下所示。

from langchain.chains import LLMChain, SimpleSequentialChain, TransformChain
from langchain_community.tools.zapier.tool import ZapierNLARunAction
from langchain_community.utilities.zapier import ZapierNLAWrapper
from langchain_core.prompts import PromptTemplate
from langchain_openai import OpenAI

## step 0. expose gmail 'find email' and slack 'send direct message' actions

# first go here, log in, expose (enable) the two actions: https://nla.zapier.com/demo/start -- for this example, can leave all fields "Have AI guess"
# in an oauth scenario, you'd get your own <provider> id (instead of 'demo') which you route your users through first

actions = ZapierNLAWrapper().list()

## step 1. gmail find email

GMAIL_SEARCH_INSTRUCTIONS = "Grab the latest email from Silicon Valley Bank"


def nla_gmail(inputs):
    action = next(
        (a for a in actions if a["description"].startswith("Gmail: Find Email")), None
    )
    return {
        "email_data": ZapierNLARunAction(
            action_id=action["id"],
            zapier_description=action["description"],
            params_schema=action["params"],
        ).run(inputs["instructions"])
    }


gmail_chain = TransformChain(
    input_variables=["instructions"],
    output_variables=["email_data"],
    transform=nla_gmail,
)

## step 2. generate draft reply

template = """You are an assisstant who drafts replies to an incoming email. Output draft reply in plain text (not JSON).

Incoming email:
{email_data}

Draft email reply:"""

prompt_template = PromptTemplate(input_variables=["email_data"], template=template)
reply_chain = LLMChain(llm=OpenAI(temperature=0.7), prompt=prompt_template)

## step 3. send draft reply via a slack direct message

SLACK_HANDLE = "@Ankush Gola"


def nla_slack(inputs):
    action = next(
        (
            a
            for a in actions
            if a["description"].startswith("Slack: Send Direct Message")
        ),
        None,
    )
    instructions = f'Send this to {SLACK_HANDLE} in Slack: {inputs["draft_reply"]}'
    return {
        "slack_data": ZapierNLARunAction(
            action_id=action["id"],
            zapier_description=action["description"],
            params_schema=action["params"],
        ).run(instructions)
    }


slack_chain = TransformChain(
    input_variables=["draft_reply"],
    output_variables=["slack_data"],
    transform=nla_slack,
)

## finally, execute

overall_chain = SimpleSequentialChain(
    chains=[gmail_chain, reply_chain, slack_chain], verbose=True
)
overall_chain.run(GMAIL_SEARCH_INSTRUCTIONS)

[1m> Entering new SimpleSequentialChain chain...[0m
[36;1m[1;3m{"from__name": "Silicon Valley Bridge Bank, N.A.", "from__email": "sreply@svb.com", "body_plain": "Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG", "reply_to__email": "sreply@svb.com", "subject": "Meet the new CEO Tim Mayopoulos", "date": "Tue, 14 Mar 2023 23:42:29 -0500 (CDT)", "message_url": "https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a", "attachment_count": "0", "to__emails": "ankush@langchain.dev", "message_id": "186e393b13cfdf0a", "labels": "IMPORTANT, CATEGORY_UPDATES, INBOX"}[0m
[33;1m[1;3m
Dear Silicon Valley Bridge Bank, 

Thank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. 

Best regards, 
[Your Name][0m
[38;5;200m[1;3m{"message__text": "Dear Silicon Valley Bridge Bank, \n\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \n\nBest regards, \n[Your Name]", "message__permalink": "https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629", "channel": "D04TKF5BBHU", "message__bot_profile__name": "Zapier", "message__team": "T04F8K3FZB5", "message__bot_id": "B04TRV4R74K", "message__bot_profile__deleted": "false", "message__bot_profile__app_id": "A024R9PQM", "ts_time": "2023-03-15T05:59:28Z", "message__blocks[]block_id": "p7i", "message__blocks[]elements[]elements[]type": "[['text']]", "message__blocks[]elements[]type": "['rich_text_section']"}[0m

[1m> Finished chain.[0m

'{"message__text": "Dear Silicon Valley Bridge Bank, \\n\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\n\\nBest regards, \\n[Your Name]", "message__permalink": "https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629", "channel": "D04TKF5BBHU", "message__bot_profile__name": "Zapier", "message__team": "T04F8K3FZB5", "message__bot_id": "B04TRV4R74K", "message__bot_profile__deleted": "false", "message__bot_profile__app_id": "A024R9PQM", "ts_time": "2023-03-15T05:59:28Z", "message__blocks[]block_id": "p7i", "message__blocks[]elements[]elements[]type": "[[\'text\']]", "message__blocks[]elements[]type": "[\'rich_text_section\']"}'

使用 OAuth 访问令牌示例

以下代码片段展示了如何使用已获取的 OAuth 访问令牌初始化包装器。请注意，此处是作为参数传入，而非设置环境变量。请查阅认证文档以获取完整的面向用户的 OAuth 开发者支持。

开发人员负责处理 OAuth 握手，以获取并刷新访问令牌。

llm = OpenAI(temperature=0)
zapier = ZapierNLAWrapper(zapier_nla_oauth_access_token="<fill in access token here>")
toolkit = ZapierToolkit.from_zapier_nla_wrapper(zapier)
agent = initialize_agent(
    toolkit.get_tools(), llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)

agent.run(
    "Summarize the last email I received regarding Silicon Valley Bank. Send the summary to the #test-zapier channel in slack."
)

工具概念指南
工具如何使用指南

Agent 示例​

SimpleSequentialChain 示例​

使用 OAuth 访问令牌示例​

相关​

Agent 示例

SimpleSequentialChain 示例

使用 OAuth 访问令牌示例

相关