The OllamaEmbedder can be used to embed text data into vectors locally using Ollama.

The model used for generating embeddings needs to run locally.

​
Usage

from phi.agent import Agent, AgentKnowledge
from phi.vectordb.pgvector import PgVector
from phi.embedder.ollama import OllamaEmbedder

# Create knowledge base
knowledge_base=AgentKnowledge(
    vector_db=PgVector(
        db_url=db_url,
        table_name=embeddings_table,
        embedder=OllamaEmbedder(),
    ),
    # 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"openhermes"The name of the model used for generating embeddings.
dimensionsint4096The dimensionality of the embeddings generated by the model.
hoststr-The host address for the API endpoint.
timeoutAny-The timeout duration for API requests.
optionsAny-Additional options for configuring the API request.
client_kwargsOptional[Dict[str, Any]]-Additional keyword arguments for configuring the API client. Optional.
ollama_clientOptional[OllamaClient]-An instance of the OllamaClient to use for making API requests. Optional.

Was this page helpful?

OpenAIVoyage AI