Get text embeddings

This guide shows you how to create a text embedding by using the Vertex AI Text embeddings API. This page covers the following topics:

The Vertex AI text embeddings API uses dense vector representations of text. These embeddings are created using deep-learning methods similar to those used by large language models. Unlike sparse vectors, which tend to map words directly to numbers, dense vectors are designed to represent the meaning of a piece of text. This lets you search for passages that align with the meaning of a query, even if the passages don't use the same words.

Key characteristics of these embeddings include:

  • High dimensionality: Models produce high-dimensional vectors. For example, gemini-embedding-001 uses 3072-dimensional vectors. You can reduce the output dimensionality to save storage space and increase computational efficiency.
  • Normalized vectors: The output vectors are normalized, so you can use cosine similarity, dot product, or Euclidean distance to get the same similarity rankings.

To learn more, see the following resources:

Before you begin

  1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

  2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

    Go to project selector

  3. Enable the Vertex AI API.

    Enable the API

  4. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

    Go to project selector

  5. Enable the Vertex AI API.

    Enable the API

    6.
  6. Choose a task type for your embeddings job.

Supported models

You can get text embeddings by using the following models:

Model name Description Output Dimensions Max sequence length Supported text languages
gemini-embedding-001 State-of-the-art performance across English, multilingual and code tasks. It unifies the previously specialized models like text-embedding-005 and text-multilingual-embedding-002 and achieves better performance in their respective domains. Read our Tech Report for more detail. up to 3072 2048 tokens Supported text languages
text-embedding-005 Specialized in English and code tasks. up to 768 2048 tokens English
text-multilingual-embedding-002 Specialized in multilingual tasks. up to 768 2048 tokens Supported text languages

For superior embedding quality, gemini-embedding-001 is our large model designed to provide the highest performance. Note that gemini-embedding-001 supports one instance per request.

Only use the model names as they are listed in the supported models table. Do not specify a model name without the @version suffix or use @latest, as these formats are not valid.

Get text embeddings for a snippet of text

You can get text embeddings for a snippet of text by using the Vertex AI API or the Vertex AI SDK for Python.

API limits

Each request is limited to 250 input texts and a total of 20,000 input tokens. If a request exceeds the token limit, it returns a 400 error. Each individual input text is limited to 2048 tokens, and any excess tokens are silently truncated. To disable silent truncation, set autoTruncate to false.

For more information, see Text embedding limits.

Choose an embedding dimension

By default, all models produce a full-length embedding vector. For gemini-embedding-001, this vector has 3072 dimensions, and for other models, it's 768 dimensions. To control the size of the output embedding vector, you can use the output_dimensionality parameter. A smaller output dimensionality can save storage space and increase computational efficiency for downstream applications, with a potential trade-off in quality.

The following examples use the gemini-embedding-001 model.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
 

from google import genai
from google.genai.types import EmbedContentConfig

client = genai.Client()
response = client.models.embed_content(
    model="gemini-embedding-001",
    contents=[
        "How do I get a driver's license/learner's permit?",
        "How long is my driver's license valid for?",
        "Driver's knowledge test study guide",
    ],
    config=EmbedContentConfig(
        task_type="RETRIEVAL_DOCUMENT",  # Optional
        output_dimensionality=3072,  # Optional
        title="Driver's License",  # Optional
    ),
)
print(response)
# Example response:
# embeddings=[ContentEmbedding(values=[-0.06302902102470398, 0.00928034819662571, 0.014716853387653828, -0.028747491538524628, ... ],
# statistics=ContentEmbeddingStatistics(truncated=False, token_count=13.0))]
# metadata=EmbedContentMetadata(billable_character_count=112)

Add an embedding to a vector database

After you generate your embedding, you can add it to a vector database, like Vector Search. This enables low-latency retrieval and is critical as the size of your data increases.

To learn more about Vector Search, see Overview of Vector Search.

What's next