Amazon Bedrock

Amazon Bedrock is a managed foundation model platform on AWS. seekdb provides an AmazonBedrockEmbeddingFunction wrapper so you can generate embeddings via Bedrock and use them with seekdb collections.

tip

Using Amazon Bedrock service requires you to follow AWS's pricing rules and may incur corresponding fees. Before proceeding, please visit their official website or refer to relevant documentation to confirm and accept their pricing standards. If you do not agree, please do not proceed.

Dependencies and authentication

AmazonBedrockEmbeddingFunction uses boto3 to call the Bedrock embedding API. In practice, you typically need:

• An AWS account with Bedrock enabled and permission to invoke the target embedding model
• AWS credentials available via the standard boto3 credential chain (for example, environment variables, shared credentials file, or an IAM role)
• Python packages: pyseekdb and boto3

Example: create an Amazon Bedrock embedding function

import boto3
from pyseekdb.utils.embedding_functions import AmazonBedrockEmbeddingFunction

session = boto3.Session(profile_name="profile", region_name="us-east-1")

ef = AmazonBedrockEmbeddingFunction(
    session=session,
    model_name="amazon.titan-embed-text-v2",
)

Parameters

• session: a boto3.Session used for credentials and region configuration.
• model_name: the Bedrock embedding model ID (for example, amazon.titan-embed-text-v2).

tip

Model availability and supported regions may change over time. For details, see https://docs.aws.amazon.com/bedrock/.