Create chatbots with Google Vertex AI on Zapier
Written by Owner
Updated at August 20th, 2025
- Tables
-
Product updates
Product updates: January 2023 Product updates: March 2023 Product updates: February 2023 Product updates: April 2023 Product updates: May 2023 Product updates: June 2023 Product updates: July 2023 Product updates: August 2023 Product updates: September 2023 Product updates: October 2023 Product updates: November 2023 Product updates: December 2023 Product updates: January 2024 Product updates: February 2024 Product updates: March 2024 Product updates: April 2024 Product updates: May 2024 Product updates: June 2024 Product updates: July 2024 Product updates: August 2024 Product updates: September 2024 Product updates: October 2024 Product updates: November 2024 Product updates: December 2024 Product updates: January 2025 Product updates: February 2025 Product updates: March 2025 Product updates: April 2025 Product updates: May 2025 Product updates: June 2025 Product updates: July 2025 Product updates: August 2025
- Zaps
- Your Zapier account
- Interfaces
- Canvas
- Chatbots
- Getting started
- Agents
- MCP
- Built-in tools
- Lead Router
- Apps
Table of Contents
With Google Vertex AI, you can use artificial intelligence to create chatbots. Send a chat to Google Vertex AI and generate a completion, with the option to store the message as you go.
To set up a Conversation action:
1. Choose the app and event
- In the Zap editor, click the action step, or click the plus + icon to add an action to your Zap.
- Search and select Google Vertex AI.
- Click the Event dropdown menu.
- Select Conversation.
- Click Continue.
2. Connect to Google Vertex AI
- Click Sign in.
- A pop-up window will appear. Log into your Google Cloud account.
- Click Continue.
3. Set up Conversation
- Context: Context shapes responses in the conversation. For example, you can use this field to specify words the model can or cannot use, topics to focus on or avoid, or the response format or style.
- User Message: The most recent message the assistant (Google Vertex AI) responds to.
- Memory Key (optional): If provided, this value will allow the assistant to continue a conversation from previous messages. Use a value that won't change over the course of a conversation (like a user's email address). If blank, the assistant will not store this conversation.
- Project ID: From the dropdown menu, select your project ID.
- Model Region: By default, us-central1 will be selected.
- Advanced Fields (optional): To adjust your large language model (LLM) parameters, select True from the Advanced Fields dropdown menu. Your screen will refresh to show the advanced fields.
- Once you’ve set up your fields, click Continue.
Note- If you opt to store messages using the Memory Key field, it will be stored in Storage by Zapier. Storage by Zapier deletes inactive data after 2 months.
- Information stored by this action is not used for fine-tuning or model training.
4. Test the action
- Click Test action.
- The next screen will show if Zapier can perform the action step successfully.
Once you’ve set up your Conversation action, you can continue setting up the rest of your Zap.