Back to integrations
Google Vertex AI and HTTP Request integration
Save yourself the work of writing custom integrations for Google Vertex AI and HTTP Request and use n8n instead. Build adaptable and scalable AI, workflows that work with your technology stack. All within a building experience you will love.
How to connect Google Vertex AI and HTTP Request
Create a new workflow and add the first step
In n8n, click the "Add workflow" button in the Workflows tab to create a new workflow. Add the starting point – a trigger on when your workflow should run: an app event, a schedule, a webhook call, another workflow, an AI chat, or a manual trigger. Sometimes, the HTTP Request node might already serve as your starting point.
Build your own Google Vertex AI and HTTP Request integration
Create custom Google Vertex AI and HTTP Request workflows by choosing triggers and actions. Nodes come with global operations and settings, as well as app-specific parameters that can be configured. You can also use the HTTP Request node to query data from any app or service with a REST API.
Supported API Endpoints for Google Vertex AI
POST
Generate content
This endpoint generates content based on the input provided.
/vertex-ai/generative-ai/docs/model-reference/inference
POST
Call function
This endpoint allows for calling functions as part of the generative tasks.
/vertex-ai/generative-ai/docs/model-reference/function-calling
POST
Ground content
This endpoint grounds the content to ensure relevance and context.
/vertex-ai/generative-ai/docs/model-reference/grounding
GET
List API errors
This endpoint retrieves potential API errors that can occur during requests.
/vertex-ai/generative-ai/docs/model-reference/api-errors
POST
Generate text embeddings
This endpoint generates embeddings for given text inputs.
/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api
POST
Generate multimodal embeddings
This endpoint generates embeddings that leverage multiple modalities.
/vertex-ai/generative-ai/docs/model-reference/multimodal-embeddings-api
POST
Generate and edit images
This endpoint is used for generating and editing images based on input specifications.
/vertex-ai/generative-ai/docs/model-reference/imagen-api
GET
Use code completions
API for generating code completion suggestions.
/vertex-ai/generative-ai/docs/model-reference/code-completion
GET
Perform batch predictions
API for executing batch predictions on data.
/vertex-ai/generative-ai/docs/model-reference/batch-prediction-api
POST
Batch prediction
API for performing batch prediction.
/vertex-ai/generative-ai/docs/model-reference/batch-prediction-api
GET
Tune models
API for tuning machine learning models.
/vertex-ai/generative-ai/docs/model-reference/tuning
POST
Tuning model parameters
API for tuning model parameters.
/vertex-ai/generative-ai/docs/model-reference/tuning
GET
Rapid evaluation
API for quickly evaluating model performance.
/vertex-ai/generative-ai/docs/model-reference/evaluation
POST
Evaluate model performance
API for rapid evaluation of models.
/vertex-ai/generative-ai/docs/model-reference/evaluation
GET
Use LlamaIndex
API for accessing the LlamaIndex for retrieval-augmented generations.
/vertex-ai/generative-ai/docs/model-reference/rag-api
GET
Manage extensions
API for managing custom extensions.
/vertex-ai/generative-ai/docs/model-reference/extension
POST
Manage extensions
API for handling extensions.
/vertex-ai/generative-ai/docs/model-reference/extension
GET
Count tokens
API for counting tokens in text inputs.
/vertex-ai/generative-ai/docs/model-reference/count-tokens
GET
Use reasoning engine
API for performing reasoning tasks.
/vertex-ai/generative-ai/docs/model-reference/reasoning-engine
POST
Utilize reasoning engine
API for using the reasoning engine capabilities.
/vertex-ai/generative-ai/docs/model-reference/reasoning-engine
GET
Use MedLM API
API for accessing medical language models.
/vertex-ai/generative-ai/docs/model-reference/medlm
POST
Access MedLM
API for accessing MedLM functionality.
/vertex-ai/generative-ai/docs/model-reference/medlm
POST
Generate and edit images
API for generating and editing images.
/vertex-ai/generative-ai/docs/model-reference/code-completion
POST
Access LlamaIndex
API for accessing LlamaIndex functionality.
/vertex-ai/generative-ai/docs/model-reference/rag-api
POST
Count tokens
API for counting tokens in text.
/vertex-ai/generative-ai/docs/model-reference/count-tokens
To set up Google Vertex AI integration, add the HTTP Request node to your workflow canvas and authenticate it using a generic authentication method. The HTTP Request node makes custom API calls to Google Vertex AI to query the data you need using the API endpoint URLs you provide.
See the example hereThese API endpoints were generated using n8n
n8n AI workflow transforms web scraping into an intelligent, AI-powered knowledge extraction system that uses vector embeddings to semantically analyze, chunk, store, and retrieve the most relevant API documentation from web pages. Remember to check the Google Vertex AI official documentation to get a full list of all API endpoints and verify the scraped ones!
Google Vertex AI and HTTP Request integration details
Google Vertex AI
Google Vertex AI is a unified machine learning platform that enables developers to build, deploy, and manage models efficiently. It provides a wide range of tools and services, such as AutoML and datasets, to accelerate the deployment of AI solutions.
Related categories
HTTP Request
Related categories
FAQs
FAQ
Can Google Vertex AI connect with HTTP Request?
Can I use Google Vertex AI’s API with n8n?
Can I use HTTP Request’s API with n8n?
Is n8n secure for integrating Google Vertex AI and HTTP Request?
How to get started with Google Vertex AI and HTTP Request integration in n8n.io?
Need help setting up your Google Vertex AI and HTTP Request integration?
Discover our latest community's recommendations and join the discussions about Google Vertex AI and HTTP Request integration.
Self-host [email protected] login page error
Mohiria
Self-Hosted n8n (v1.120.4) Fails to Load in Browser with Cannot read properties of undefined (reading 'ldap') TypeError description： Issue: I self-hosted n8n version 1.120.4 using Docker. The container logs confirm the s…
JSON parameter needs to be valid JSON on an HTTP request
Armand Ferveur
Hey, I tried to call the Gemini 2.5 flash image model via HTTP request, but I’m getting this error that I can’t seem to resolve in the JSON code. I feel like I’m doing it right, and ChatGPT doesn’t see any errors either.…
Getting detailed error messages when AI Agent tools fail
Agustin Pezzani
Hello n8n Community, I’m facing an issue when using Tools within the AI Agent node, specifically when one of the tools fails for a valid reason (e.g., an external API returns an expected error). The Problem: When a T…
I have an issue when sending an http request to fal.ai to get results api
Ahmed Ennaime
Description: I’m trying to send a GET http request to fal.ai to get results but it fails everytime even though the credentials are right in the headers, this api doesn’t take anything in the body (API link: Ffmpeg Api Me…
Google Verification Denied
Moiz Contractor
Describe the problem/error/question Hi, I am getting a - Google hasnt verified this app error. I have Enable the API, the domain is verified on the Cloud Console, the user is added in the search console and the google do…
The world's most popular workflow automation platform for technical teams including
Why use n8n to integrate Google Vertex AI with HTTP Request
Build complex workflows, really fast
