The GeminiEmbedder class is used to embed text data into vectors using Google’s Gemini API. You can use it through Google AI Studio or Google Cloud Vertex AI.

​
Usage

For Google AI Studio: 
from agno.agent import AgentKnowledge
from agno.vectordb.pgvector import PgVector
from agno.embedder.google import GeminiEmbedder

# Embed sentence in database
embeddings = GeminiEmbedder().get_embedding(
    "The quick brown fox jumps over the lazy dog."
)

# Print the embeddings and their dimensions
print(f"Embeddings: {embeddings[:5]}")
print(f"Dimensions: {len(embeddings)}")

# Use an embedder in a knowledge base
knowledge_base = AgentKnowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="gemini_embeddings",
        embedder=GeminiEmbedder(),
    ),
    num_documents=2,
)
For Vertex AI: 
from agno.agent import AgentKnowledge
from agno.vectordb.pgvector import PgVector
from agno.embedder.google import GeminiEmbedder

embedder = GeminiEmbedder(
    vertexai=True,
    project_id="your-gcloud-project-id",  # Optional
    location="us-central1",  # Optional
)

# Use in a knowledge base
knowledge_base = AgentKnowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="gemini_embeddings_vertex",
        embedder=embedder,
    ),
    num_documents=2,
)

​
Params

ParameterTypeDefaultDescription
idstrgemini-embedding-exp-03-07The Gemini embedding model ID to use
task_typestrRETRIEVAL_QUERYThe type of task for which embeddings are being generated
titleOptional[str]NoneOptional title for the embedding task
dimensionsOptional[int]1536The dimensionality of the generated embeddings
api_keyOptional[str]NoneThe API key used for authenticating requests
request_paramsOptional[Dict[str, Any]]NoneOptional dictionary of parameters for the embedding request
client_paramsOptional[Dict[str, Any]]NoneOptional dictionary of parameters for the Gemini client
gemini_clientOptional[GeminiClient]NoneOptional pre-configured Gemini client instance
vertexaiboolFalseWhether to use Vertex AI instead of Google AI Studio
project_idOptional[str]NoneGoogle Cloud project ID for Vertex AI
locationOptional[str]NoneGoogle Cloud region for Vertex AI

​
Developer Resources