embed_content

def embed_content(
    self,
    *,
    model: str,
    contents: Union[ContentListUnion, ContentListUnionDict],
    config: Optional[EmbedContentConfig] = None,
) -> EmbedContentResponse

async def embed_content(
    self,
    *,
    model: str,
    contents: Union[ContentListUnion, ContentListUnionDict],
    config: Optional[EmbedContentConfig] = None,
) -> EmbedContentResponse

from google import genai

client = genai.Client(api_key='your-api-key')

response = client.models.embed_content(
    model='text-embedding-004',
    contents='What is your name?'
)

embedding = response.embeddings[0].values
print(f"Embedding dimension: {len(embedding)}")
print(f"First 5 values: {embedding[:5]}")
# Embedding dimension: 768
# First 5 values: [0.013168523, -0.008711934, ...]

response = client.models.embed_content(
    model='text-embedding-004',
    contents=[
        'What is your name?',
        'What is your favorite color?',
        'Where do you live?',
    ]
)

for i, embedding in enumerate(response.embeddings):
    print(f"Text {i+1}: {len(embedding.values)} dimensions")
    print(f"  Tokens: {embedding.statistics.token_count}")
    print(f"  Truncated: {embedding.statistics.truncated}")

from google.genai import types

# Document embeddings for search
doc_response = client.models.embed_content(
    model='text-embedding-004',
    contents=[
        'Python is a high-level programming language.',
        'JavaScript is used for web development.',
    ],
    config=types.EmbedContentConfig(
        task_type='RETRIEVAL_DOCUMENT',
        output_dimensionality=256,  # Reduce from 768 to 256
    )
)

# Query embedding for search
query_response = client.models.embed_content(
    model='text-embedding-004',
    contents='programming languages',
    config=types.EmbedContentConfig(
        task_type='RETRIEVAL_QUERY',
        output_dimensionality=256,
    )
)

print(f"Document embeddings: {len(doc_response.embeddings)}")
print(f"Query dimension: {len(query_response.embeddings[0].values)}")

import numpy as np
from google.genai import types

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# Embed documents
documents = [
    'The quick brown fox jumps over the lazy dog.',
    'A fast auburn fox leaps above an idle canine.',
    'Python is a programming language.',
]

doc_response = client.models.embed_content(
    model='text-embedding-004',
    contents=documents,
    config=types.EmbedContentConfig(task_type='SEMANTIC_SIMILARITY')
)

# Embed query
query = 'agile fox jumping'
query_response = client.models.embed_content(
    model='text-embedding-004',
    contents=query,
    config=types.EmbedContentConfig(task_type='SEMANTIC_SIMILARITY')
)

# Calculate similarities
query_embedding = np.array(query_response.embeddings[0].values)
for i, doc in enumerate(documents):
    doc_embedding = np.array(doc_response.embeddings[i].values)
    similarity = cosine_similarity(query_embedding, doc_embedding)
    print(f"Document {i+1}: {similarity:.4f}")
    print(f"  {doc[:50]}...")

# Output:
# Document 1: 0.8234
#   The quick brown fox jumps over the lazy dog.
# Document 2: 0.8156
#   A fast auburn fox leaps above an idle canine.
# Document 3: 0.3421
#   Python is a programming language.

from google import genai
from google.genai import types

client = genai.Client(vertexai=True, project='my-project', location='us-central1')

response = client.models.embed_content(
    model='gemini-embedding-2-exp-11-2025',
    contents=[
        types.Part.from_uri(
            file_uri='gs://generativeai-downloads/images/scones.jpg',
            mime_type='image/jpeg',
        ),
    ],
    config=types.EmbedContentConfig(
        output_dimensionality=64,
    )
)

print(f"Multimodal embedding: {len(response.embeddings[0].values)} dimensions")

response = client.models.embed_content(
    model='text-embedding-004',
    contents='Python is widely used in data science and machine learning applications.',
    config=types.EmbedContentConfig(
        task_type='RETRIEVAL_DOCUMENT',
        title='Introduction to Python Programming',
    )
)

embedding = response.embeddings[0].values
print(f"Document embedding with title: {len(embedding)} dimensions")

import time

def embed_large_dataset(client, texts, batch_size=100):
    """Embed large datasets in batches."""
    all_embeddings = []
    
    for i in range(0, len(texts), batch_size):
        batch = texts[i:i+batch_size]
        response = client.models.embed_content(
            model='text-embedding-004',
            contents=batch,
            config={'output_dimensionality': 256}
        )
        all_embeddings.extend([emb.values for emb in response.embeddings])
        
        # Rate limiting
        time.sleep(1)
    
    return all_embeddings

# Use it
texts = [f"Document {i}" for i in range(500)]
embeddings = embed_large_dataset(client, texts)
print(f"Generated {len(embeddings)} embeddings")

import asyncio
from google import genai

client = genai.Client(api_key='your-api-key')

async def embed_async():
    response = await client.aio.models.embed_content(
        model='text-embedding-004',
        contents=[
            'First text to embed',
            'Second text to embed',
            'Third text to embed',
        ],
        config={'output_dimensionality': 256}
    )
    
    for i, emb in enumerate(response.embeddings):
        print(f"Embedding {i+1}: {len(emb.values)} dimensions")

asyncio.run(embed_async())