Voyage AI Embedder

The VoyageAIEmbedder class is used to embed text data into vectors using the Voyage AI API. Get your key from here.

Usage

cookbook/embedders/voyageai_embedder.py

from bitca.agent import AgentKnowledge
from bitca.vectordb.pgvector import PgVector
from bitca.embedder.voyageai import VoyageAIEmbedder

embeddings = VoyageAIEmbedder().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="voyageai_embeddings",
        embedder=VoyageAIEmbedder(),
    ),
    num_documents=2,
)

Params

Parameter
Type
Default
Description

model

str

"voyage-2"

The name of the model used for generating embeddings.

dimensions

int

1024

The dimensionality of the embeddings generated by the model.

request_params

Optional[Dict[str, Any]]

-

Additional parameters to include in the API request. Optional.

api_key

str

-

The API key used for authenticating requests.

base_url

str

"https://api.voyageai.com/v1/embeddings"

The base URL for the API endpoint.

max_retries

Optional[int]

-

The maximum number of retries for API requests. Optional.

timeout

Optional[float]

-

The timeout duration for API requests. Optional.

client_params

Optional[Dict[str, Any]]

-

Additional parameters for configuring the API client. Optional.

voyage_client

Optional[Client]

-

An instance of the Client to use for making API requests. Optional.

Last updated