Vertex AI Embedding Configuration
Vertex AI serves Google’s text embedding models from your own Google Cloud project, billed and governed alongside the rest of your cloud resources.
Before you start
Create a service account with the Vertex AI User role and download a JSON key. The steps are the same as for Vertex AI text generation.
Required Fields
GCP Project ID *
The Google Cloud project that hosts Vertex AI. It must match the project_id inside your service account JSON.
Service Account JSON *
Upload the JSON key file. PipesHub checks that it is valid JSON, contains type, project_id and private_key, and has "type": "service_account".
Model Name *
The embedding model to use, for example text-embedding-004 or text-multilingual-embedding-002.
Use a multilingual model if your documents are not all in English.
Optional Fields
Region
The Vertex AI region, for example us-central1.
Default: us-central1
Model Friendly Name
A label shown in the PipesHub interface so you can tell several configurations apart. If you leave it blank, the model name is used.
Dimensions
The number of dimensions in the vectors this model produces. PipesHub uses it to size the vector collection.
Changing the embedding model or its dimensions after documents are indexed means existing vectors no longer match new ones. Re-index your content after switching.
Is Multimodal
Turn this on if the model can embed images as well as text. It is off by default.
