The MistralEmbedder class is used to embed text data into vectors using the Mistral API. Get your key from here.

​
Usage

cookbook/embedders/mistral_embedder.py
from agno.agent import AgentKnowledge
from agno.vectordb.pgvector import PgVector
from agno.embedder.mistral import MistralEmbedder

# Embed sentence in database
embeddings = MistralEmbedder().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="mistral_embeddings",
        embedder=MistralEmbedder(),
    ),
    num_documents=2,
)

​
Params

ParameterTypeDefaultDescription
modelstr"mistral-embed"The name of the model used for generating embeddings.
dimensionsint1024The dimensionality of the embeddings generated by the model.
request_paramsOptional[Dict[str, Any]]-Additional parameters to include in the API request. Optional.
api_keystr-The API key used for authenticating requests.
endpointstr-The endpoint URL for the API requests.
max_retriesOptional[int]-The maximum number of retries for API requests. Optional.
timeoutOptional[int]-The timeout duration for API requests. Optional.
client_paramsOptional[Dict[str, Any]]-Additional parameters for configuring the API client. Optional.
mistral_clientOptional[MistralClient]-An instance of the MistralClient to use for making API requests. Optional.

​
Developer Resources

HuggingFaceFastEmbed