SentenceTransformers Embedder

The SentenceTransformerEmbedder class is used to embed text data into vectors using the SentenceTransformers library.

Usage

sentence_transformer_embedder.py

from agno.knowledge.knowledge import Knowledge
from agno.vectordb.pgvector import PgVector
from agno.knowledge.embedder.sentence_transformer import SentenceTransformerEmbedder

# Embed sentence in database
embeddings = SentenceTransformerEmbedder().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 = Knowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="sentence_transformer_embeddings",
        embedder=SentenceTransformerEmbedder(),
    ),
    max_results=2,
)

Params

Parameter	Type	Default	Description
id	str	sentence-transformers/all-MiniLM-L6-v2	The name of the SentenceTransformers model to use
dimensions	int	384	The dimensionality of the generated embeddings
sentence_transformer_client	Optional[SentenceTransformer]	None	Optional pre-configured SentenceTransformers client instance
prompt	Optional[str]	None	Optional prompt to prepend to input text
normalize_embeddings	bool	False	Whether to normalize returned vectors to have length 1

Developer Resources

• View Cookbook