Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.phidata.com/llms.txt

Use this file to discover all available pages before exploring further.

The GeminiEmbedder class is used to embed text data into vectors using the Gemini API. You can get one from here.

​
Usage

cookbook/embedders/gemini_embedder.py
from phi.agent import AgentKnowledge
from phi.vectordb.pgvector import PgVector
from phi.embedder.google import GeminiEmbedder

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)}")

# Example usage:
knowledge_base = AgentKnowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="gemini_embeddings",
        embedder=GeminiEmbedder(),
    ),
    num_documents=2,
)

​
Params

ParameterTypeDefaultDescription
dimensionsint768The dimensionality of the generated embeddings
modelstrmodels/text-embedding-004The name of the Gemini model to use
task_typestr-The type of task for which embeddings are being generated
titlestr-Optional title for the embedding task
api_keystr-The API key used for authenticating requests.
request_paramsOptional[Dict[str, Any]]-Optional dictionary of parameters for the embedding request
client_paramsOptional[Dict[str, Any]]-Optional dictionary of parameters for the Gemini client
gemini_clientOptional[Client]-Optional pre-configured Gemini client instance