---
id: llama-index-embeddings-vertex
version: "0.5.0"
license: MIT
license_treatment: permissive
maintenance: active
---

# llama-index-embeddings-vertex — llama-index embeddings vertex integration

License: permissive · Maintenance: active · Downloads: 81.6K/mo

## What it is and what it does

This package bridges LlamaIndex and Google Vertex AI's embedding models, letting you generate text and multimodal embeddings within a LlamaIndex workflow. It wraps Vertex AI's embedding APIs—including the textembedding-gecko family and multimodal models—and exposes them through LlamaIndex's standard embedding interface, handling credential management and model selection transparently.

You supply GCP credentials and a model name, and the package handles the API calls to Vertex AI. It supports both direct credential objects and service account parameters for flexibility. The main constraint is that multimodal embedding doesn't support async operations, though text embeddings do.

Use it for:

- Build RAG pipelines in LlamaIndex using Vertex AI embeddings instead of third-party providers
- Generate multilingual embeddings with textembedding-gecko-multilingual for cross-language search
- Integrate multimodal embeddings for image and text understanding in LlamaIndex applications
- Migrate existing LlamaIndex applications to use Google Cloud's managed embedding service

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates Google Vertex AI embedding models into LlamaIndex applications, providing access to text and multimodal embedding APIs with flexible credential handling.

Yes, if you are already using LlamaIndex and have access to Google Cloud with Vertex AI enabled. The package is actively maintained, has no known vulnerabilities, low install friction, and provides straightforward integration. Skip it if you don't use LlamaIndex or lack GCP infrastructure.

## Install

pip install llama-index-embeddings-vertex
uv add llama-index-embeddings-vertex
poetry add llama-index-embeddings-vertex

## Installing llama-index-embeddings-vertex

Before you install: Low install friction with only two runtime dependencies (google-cloud-aiplatform and llama-index-core). Actively maintained with recent releases.

License in practice: MIT license permits free use, modification, and distribution with minimal restrictions.

Quickstart:

pip install llama-index-embeddings-vertex

from llama_index.embeddings.vertex import VertexTextEmbedding
from google.oauth2 import service_account

credentials = service_account.Credentials.from_service_account_file(
    "path/to/service-account.json"
)
embedding = VertexTextEmbedding(
    model_name="textembedding-gecko@003",
    project="your-project-id",
    location="your-region",
    credentials=credentials,
)

Requires valid Google Cloud credentials and a GCP project with Vertex AI enabled. Python 3.10 or later required.

Verify before relying:

- Whether async support for multimodalembedding is planned or if this is a permanent limitation
- Performance characteristics and latency of the various gecko model versions

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 81.6K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

vertex ai embeddings, google cloud embeddings integration, llama index vertex, text embedding gecko, multimodal embedding vertex, embeddings, vertex-ai, rag

[View on SkillFed](https://skillfed.io/packages/llama-index-embeddings-vertex) · [View on PyPI](https://pypi.org/project/llama-index-embeddings-vertex/)