AmazonBedrockDocumentEmbedder Parameters

Check the init and runtime parameters you can specify for AmazonBedrockDocumentEmbeder.

YAML Init Parameters

These are the parameters you can specify in pipeline YAML:

ParameterTypePossible valuesDescription
'model'Literal"amazon.titan-embed-text-v1"
"cohere.embed-english-v3"
"cohere.embed-multilingual-v3"
The embedding model to use. The model must be specified in the format outlined in the Amazon Bedrock documentation.
Required.
'aws_access_key_id'Secret`AWS access key ID.
(Loaded automatically from the environment or the AWS configuration file if the AWS environment is configured correctly).
Not needed if deepset Cloud is connected to Bedrock.
Optional.
'aws_secret_access_key'SecretAWS secret access key.
(Loaded automatically from the environment or the AWS configuration file if the AWS environment is configured correctly).
Not needed if deepset Cloud is connected to Bedrock.
Optional.
'aws_session_token'SecretAWS session token.
(Loaded automatically from the environment or the AWS configuration file if the AWS environment is configured correctly).
Not needed if deepset Cloud is connected to Bedrock.
Optional.
'aws_region_name'SecretAWS region name.
(Loaded automatically from the environment or the AWS configuration file if the AWS environment is configured correctly).
Not needed if deepset Cloud is connected to Bedrock.
Optional.
'aws_profile_name'SecretAWS profile name.
(Loaded automatically from the environment or the AWS configuration file if the AWS environment is configured correctly).
Not needed if deepset Cloud is connected to Bedrock.
Optional.
'kwargs'Dictionary-Additional parameters to pass for model inference. For example, input_type and truncate for Cohere models. For a list of parameters, see AWS documentation .
Optional.
batch_sizeIntegerDefault: 32The number of documents to embed at once. Only Cohere models support batch inference. This parameter is ignored for Amazon Titan models.
Required.
progress_barBooleanTrue
False
Default: True
Shows progress bar when creating the embeddings.
Required.
meta_fields_to_embedList of stringsDefault: NoneA list of metadata fields you want to embed along with the document text.
Optional.
embedding_separatorStringDefault: \nThe separator used to concatenate the metadata fields to the document text.
Required.