About Zapier Community
New to our Community? Get to know more about our space and how to make the most of your time here.

Code of Conduct Community FAQ's Zapier Common Questions What to Expect

Get Started With Zapier
New to Zapier? We have got you covered with our Zapier 101 Resources.

Zapier Essentials

Get Support
Have a question? Let's get you an answer!

How Do I...? Troubleshooting Code & Webhooks Developer Zone

Other Help Resources
Wait, there's more! Check out these Community sourced spaces for additional resources.

Zapier Help Center Hire an Expert

Zapier Products
Learn more about Zapier's new products.

Zapier Tables Zapier Interfaces

Zapier Reading
All of our best learning resources can be found here.

Featured Articles Show & Tell AI Hub Zapier Tools Hub

Learning Groups
Excited to meet other builders? Check out our interest areas full of doers, dreamers, and in-betweeners.

User Groups

Other Learning Resources
Some of our favorite additional ways to upskill your Zapier knowledge.

Zapier Learn Zapier Blog Zapier Webinars

Product Updates
Check out what is new and upcoming with Zapier with our regular product updates.

Product Updates

Early Access Program
Want to join Early Access? Learn more here.

Question

Observation: null?

  • 4 August 2023
  • 2 replies
  • 270 views
B
Userlevel 1

Greetings,

While in the process of testing Langchain and Zapier functionalities, I encountered an issue where the response I received was "observation: null." I followed the code provided in the documentation, but the problem persists. I'm seeking guidance on how to resolve this issue. Below is the code I used for reference.

 

from langchain.llms import OpenAI
from langchain.agents import initialize_agent, load_tools
from langchain.agents.agent_toolkits import ZapierToolkit
from langchain.agents import AgentType
from langchain.memory import ConversationBufferMemory
from langchain.utilities.zapier import ZapierNLAWrapper

OPENAI_API_KEY = "..."
ZAPIER_NLA_API_KEY = "..."

llm = OpenAI(temperature=1, openai_api_key=  OPENAI_API_KEY)
memory = ConversationBufferMemory(memory_key="chat_history")
zapier = ZapierNLAWrapper(zapier_nla_api_key = ZAPIER_NLA_API_KEY)
toolkit = ZapierToolkit.from_zapier_nla_wrapper(zapier)
tools = toolkit.get_tools() + load_tools(["human"])
agent = initialize_agent(tools, llm, memory=memory, agent="conversational-react-description", verbose=True)

message = "Find the last email I received from giabao.corn20@gmail.com"
assistant_message = agent.run(message)
print(assistant_message)

This is what i got as a return: 



> Entering new AgentExecutor chain...

Thought: Do I need to use a tool? Yes
Action: Gmail: Find Email
Action Input: Search for 'from giabao.corn20@gmail.com'
Observation: null
Thought: Do I need to use a tool? No
AI: I'm sorry, I couldn't find an email from that address. Is there anything else I can help you with?

> Finished chain.
I'm sorry, I couldn't find an email from that address. Is there anything else I can help you with?

Edit 1: It appears that I can view the result in the Zapier NLA (Natural Language API) logs, but the process is still in the "previewed" state and hasn't automatically executed yet. I have to manually click the "run" button for it to execute and return the answer. How can I resolve this issue?

 

This post has been closed for comments. Please create a new post if you need help or have a question about this topic.

2 replies

coredumped 
{
  "id": "01H8QVAH3RSX29BV6EMQGH1ETS",
  "action_used": "Notion: Find Page (By Title)",
  "input_params": {
    "Title": "tech"
  },
  "review_url": "https://nla.zapier.com/execution/01H8QVAH3RSX29BV6EMQGH1ETS/?needs_confirmation=true",
  "result": null,
  "additional_results": [],
  "result_field_labels": null,
  "status": "preview",
  "error": null,
  "assistant_hint": "When the response status=preview, always send the user to review_url to confirm and run the action. After the user confirms, fetch the execution log to see the results."
}

Similar issue with langchain, making an API request yields this message. Not sure why but it needs a manual review_url which is a pain, because I dont know if langchain can natively handle that. 

canola_timer
Userlevel 1

For me this problem was caused because my Zapier actions all had the option “require preview before running AI Action” toggled on (this is default). To toggle it off, go to https://nla.zapier.com/dev/actions/ and click on the action you want > show all options > scroll down and toggle off “require preview before running AI Action”.

Terms & Conditions