Skip to main content
The CohereEmbedder class is used to embed text data into vectors using the Cohere API. You can get started with Cohere from here Get your key from here.

​
Usage

cookbook/embedders/cohere_embedder.py
from agno.agent import AgentKnowledge
from agno.vectordb.pgvector import PgVector
from agno.embedder.cohere import CohereEmbedder

# Add embedding to database
embeddings = CohereEmbedder().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_base = AgentKnowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="cohere_embeddings",
        embedder=CohereEmbedder(),
    ),
    num_documents=2,
)

​
Params

ParameterTypeDefaultDescription
modelstr"embed-english-v3.0"The name of the model used for generating embeddings.
input_typestrsearch_queryThe type of input to embed. You can find more details here
embedding_typesOptional[List[str]]-The type of embeddings to generate. Optional.
api_keystr-The Cohere API key used for authenticating requests.
request_paramsOptional[Dict[str, Any]]-Additional parameters to include in the API request. Optional.
client_paramsOptional[Dict[str, Any]]-Additional parameters for configuring the API client. Optional.
cohere_clientOptional[CohereClient]-An instance of the CohereClient to use for making API requests. Optional.

​
Developer Resources