Extend Session Timeout for Dialog flow CX
April 18, 2024 No Comments

What is Session Timeout?

Once your webhook service receives a webhook request, it needs to send a webhook response. The following limitations apply to your response:

  • The response must occur within a timeout (max 30 seconds) that you configure when creating the webhook resources, otherwise, the request will time out.
  • The response must be less than or equal to 64 KiB in size.

In this, we increase the session timeout above 30 seconds to avoid the error of webhook timeout.

Why are we required to increase Session Timeout?

When requesting data from an API or retrieving information from databases or AI models like ChatGPT, Claude, Gemini, or LLaMA, there may be delays exceeding the maximum timeout limit of 30 seconds. To prevent encountering a webhook timeout error, extending the session timeout duration is necessary.

How to Increase the Session Timeout?

Here’s a step-by-step guide:

1. Dialogflow Setup

Sign in to the Dialogflow CX console and create a new agent. Give the Agent name as you like. You will find the below screen for the new agent:

Dialogflow setup

Now navigate to ‘Start Page’. Click on the ‘Default Welcome Intent’ and add a new page of a name you like we have used ‘page_1’. Click on Save after adding a new page.

Default

Navigate to ‘page_1’. Click on the Routes to add a new route and create a new intent ‘intent_1’.

Route

In ‘intent_1’, add Training Phrases like ‘I want to increase the webhook’ and Save the intent.

Training phrases

In ‘intent_1’, add a new parameter ‘$session.params.text = null’ in Condition of ‘page_1’.

Null condition

To do the transition, add a new page ‘page_2’ and click Save after adding a new page.

save

Navigate to page ‘page_2’ and in Condition, add parameter condition ‘$session.params.text = null’.

Null

Now, Enable webhook (create webhook if not created) and add webhook with tag ‘response’. Click on Save after adding a webhook.

response

Add a new route in ‘page_2’ and in Condition, add parameter ‘$session.params.text = True’.

True

Now, add an agent response, which will be displayed after the webhook timeout. Click on Save after adding the agent response.

agent responce

Now, click on the State Handler, select Event Handler, and click Apply.

Event handler

To do the Transition, add a new page ‘page_3’, and click Save after adding a new page.

Save

Navigate to page ‘page_3’. Click on the Routes to add a new route and in Condition, select ‘Customize expression’ and add ‘true’.

customized expression

Now, Enable webhook and add webhook with tag ‘get_response’. Add a previous page ‘page_2’ and Save after adding a previous page.

get response

2. Webhook Code

				
					
from flask import Flask, request, jsonify
import time

app = Flask(__name__)

# Webhook endpoint to handle POST requests
@app.route('/webhook', methods=['POST'])
def webhook():
    # Get the JSON data from the request
    data = request.get_json(silent=True, force=True)
    # Extract the tag from the JSON data
    tag = data["fulfillmentInfo"]["tag"]
    target_page = data['pageInfo']['currentPage']
    if tag == 'response':
        parameters_sending(target_page)
        
    if tag == "get_response":
        # Simulate delay and then fetch content from a file
        count = 0
        while True:
          time.sleep(1)
          count += 1
          print("entering get response")
          with open("user_name.txt", "r") as file:
              content = file.read().strip()
              if content:
                  # If content exists, prepare response with the content
                  reply = {
                      "fulfillmentResponse": {
                          "messages": [
                              {
                                  "text": {
                                      "text": [
                                          f'Message received: {content}'
                                      ]
                                  }
                              }
                          ]
                      },
                      "sessionInfo": {
                          "parameters": {"test": "True"},
                      },
                  }
                  # Clear the content of the file
                  with open("user_name.txt", "w") as file: 
                      file.write("")
                  return jsonify(reply)
        
    return {
            "fulfillmentResponse": {
                "messages": [
                    {
                        "text": {
                            "text": [
                                f'Completed under webhook timeout limit.'
                            ]
                        }
                    }
                ]
            },
            "sessionInfo": {
                "parameters": {"test": "True"},
            },
        }

# Function to perform a background task
def parameters_sending(target_page):
    time.sleep(8) 
    print("completed")
    # Write a message to a file
    with open("user_name.txt", "w") as file:
        file.write("Your Testing Is Successfully Executed.")
        
    response= {
                    "sessionInfo": {
                        "parameters": {"test": "False"},
                    },
                    'targetPage': target_page
                  
                }
    return response

# Main function to start the Flask app
if __name__ == '__main__':
    app.run(debug=True)
				
			

Conclusion

Extending the session timeout from the default 30 seconds is important to handle any delays that might occur when getting data from APIs or databases. By giving more time for responses, we avoid running into errors that could disrupt the flow of information between services. This adjustment ensures that operations run smoothly, ultimately enhancing the overall user experience.

Increase Your Webhook Timeout Settings

Facing delays in API responses or database queries? We can guide you through optimizing your session timeout for seamless integration.

Write a comment

Your email address will not be published. Required fields are marked *

Want to talk to an Expert Developer?

Our experts in Generative AI, Python Programming, and Chatbot Development can help you build innovative solutions and scale your business faster.