The AwsBedrockEmbedder class is used to embed text data into vectors using the AWS Bedrock API. By default, it uses the Cohere Embed Multilingual V3 model for generating embeddings.

​
Setup

​
Set your AWS credentials

export AWS_ACCESS_KEY_ID = xxx
export AWS_SECRET_ACCESS_KEY = xxx
export AWS_REGION = xxx

By default, this embedder uses the cohere.embed-multilingual-v3 model. You must enable access to this model from the AWS Bedrock model catalog before using this embedder.

​
Run PgVector

docker run - d \
    - e POSTGRES_DB = ai \
    - e POSTGRES_USER = ai \
    - e POSTGRES_PASSWORD = ai \
    - e PGDATA = /var/lib/postgresql/data/pgdata \
    - v pgvolume: / var/lib/postgresql/data \
    - p 5532: 5432 \
    - -name pgvector \
    agnohq/pgvector: 16

​
Usage

cookbook/embedders/aws_bedrock_embedder.py

# Embed sentence in database
embeddings = AwsBedrockEmbedder().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 with a PDF knowledge base
knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    reader=PDFUrlReader(
        chunk_size=2048
    ),  # Required because Cohere model has a fixed size of 2048
    vector_db=PgVector(
        table_name="recipes",
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        embedder=AwsBedrockEmbedder(),
    ),
)
knowledge_base.load(recreate=False)

​
Params

ParameterTypeDefaultDescription
idstr"cohere.embed-multilingual-v3"The model ID to use. You need to enable this model in your AWS Bedrock model catalog.
dimensionsint1024The dimensionality of the embeddings generated by the model(1024 for Cohere models).
input_typestr"search_query"Prepends special tokens to differentiate types. Options: ‘search_document’, ‘search_query’, ‘classification’, ‘clustering’.
truncateOptional[str]NoneHow to handle inputs longer than the maximum token length. Options: ‘NONE’, ‘START’, ‘END’.
embedding_typesOptional[List[str]]NoneTypes of embeddings to return . Options: ‘float’, ‘int8’, ‘uint8’, ‘binary’, ‘ubinary’.
aws_regionOptional[str]NoneThe AWS region to use. If not provided, falls back to AWS_REGION env variable.
aws_access_key_idOptional[str]NoneThe AWS access key ID. If not provided, falls back to AWS_ACCESS_KEY_ID env variable.
aws_secret_access_keyOptional[str]NoneThe AWS secret access key. If not provided, falls back to AWS_SECRET_ACCESS_KEY env variable.
sessionOptional[Session]NoneA boto3 Session object to use for authentication.
request_paramsOptional[Dict[str, Any]]NoneAdditional parameters to pass to the API requests.
client_paramsOptional[Dict[str, Any]]NoneAdditional parameters to pass to the boto3 client.
clientOptional[AwsClient]NoneAn instance of the AWS Bedrock client to use for making API requests.

​
Developer Resources