Phidata uses OpenAIEmbedder as the default embeder for the vector database. The OpenAIEmbedder class is used to embed text data into vectors using the OpenAI API.

​
Usage

from phi.agent import Agent, AgentKnowledge
from phi.vectordb.pgvector import PgVector
from phi.embedder.openai import OpenAIEmbedder

# Create knowledge base
knowledge_base=AgentKnowledge(
    vector_db=PgVector(
        db_url=db_url,
        table_name=embeddings_table,
        embedder=OpenAIEmbedder(),
    ),
    # 2 references are added to the prompt
    num_documents=2,
),

# Add information to the knowledge base
knowledge_base.load_text("The sky is blue")

# Add the knowledge base to the Agent
agent = Agent(knowledge_base=knowledge_base)

​
Params

ParameterTypeDefaultDescription
modelstr"text-embedding-ada-002"The name of the model used for generating embeddings.
dimensionsint1536The dimensionality of the embeddings generated by the model.
encoding_formatLiteral['float', 'base64']"float"The format in which the embeddings are encoded. Options are “float” or “base64”.
userstr-The user associated with the API request.
api_keystr-The API key used for authenticating requests.
organizationstr-The organization associated with the API request.
base_urlstr-The base URL for the API endpoint.
request_paramsOptional[Dict[str, Any]]-Additional parameters to include in the API request.
client_paramsOptional[Dict[str, Any]]-Additional parameters for configuring the API client.
openai_clientOptional[OpenAIClient]-An instance of the OpenAIClient to use for making API requests.

Was this page helpful?

IntroductionOllama