Implementation:Explodinggradients Ragas GoogleEmbeddings Class

Knowledge Sources	Explodinggradients_Ragas
Domains	Embeddings, Google_Cloud
Last Updated	2026-02-10 00:00 GMT

Overview

Google embeddings provider supporting both Vertex AI and Google AI (Gemini) services with automatic SDK detection.

Description

GoogleEmbeddings extends BaseRagasEmbedding to provide text embeddings via Google's cloud services. It supports both Vertex AI and Google AI (Gemini) backends, automatically detecting the appropriate SDK (new google-genai or legacy google.generativeai). The default model is gemini-embedding-001.

Usage

Use this provider when generating embeddings with Google Cloud's Vertex AI or Google AI (Gemini) embedding models.

Code Reference

Source Location

• Repository: Explodinggradients_Ragas
• File: src/ragas/embeddings/google_provider.py
• Lines: 12-349

Signature

class GoogleEmbeddings(BaseRagasEmbedding):
    PROVIDER_NAME = "google"
    DEFAULT_MODEL = "gemini-embedding-001"

    def __init__(
        self,
        client=None,
        model: str = "gemini-embedding-001",
        use_vertex: bool = False,
        project_id: Optional[str] = None,
        location: str = "us-central1",
        cache: Optional[CacheInterface] = None,
        **kwargs,
    ):
        ...
    def embed_text(self, text: str, **kwargs) -> List[float]:
        ...
    async def aembed_text(self, text: str, **kwargs) -> List[float]:
        ...
    def embed_texts(self, texts: List[str], **kwargs) -> List[List[float]]:
        ...
    async def aembed_texts(self, texts: List[str], **kwargs) -> List[List[float]]:
        ...

Import

from ragas.embeddings.google_provider import GoogleEmbeddings

I/O Contract

Inputs

Name	Type	Required	Description
model	str	No	Google embedding model (default "gemini-embedding-001")
use_vertex	bool	No	Use Vertex AI instead of Google AI (default False)
project_id	Optional[str]	No	GCP project ID (required for Vertex AI)
location	str	No	GCP region (default "us-central1")

Outputs

Name	Type	Description
embed_text returns	List[float]	Embedding vector
embed_texts returns	List[List[float]]	Batch embedding vectors

Usage Examples

from ragas.embeddings.google_provider import GoogleEmbeddings

# Google AI (Gemini)
embeddings = GoogleEmbeddings(model="gemini-embedding-001")
vector = embeddings.embed_text("What is machine learning?")

# Vertex AI
embeddings_vertex = GoogleEmbeddings(
    use_vertex=True,
    project_id="my-gcp-project",
    location="us-central1",
)
vector = embeddings_vertex.embed_text("What is ML?")