Check the init and runtime parameters you can specify for AmazonBedrockDocumentEmbeder.
YAML Init Parameters
These are the parameters you can specify in pipeline YAML:
Parameter | Type | Possible values | Description |
---|---|---|---|
'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' | Secret | AWS 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' | Secret | AWS 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' | Secret | AWS 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' | Secret | AWS 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_size | Integer | Default: 32 | The number of documents to embed at once. Only Cohere models support batch inference. This parameter is ignored for Amazon Titan models. Required. |
progress_bar | Boolean | True False Default: True | Shows progress bar when creating the embeddings. Required. |
meta_fields_to_embed | List of strings | Default: None | A list of metadata fields you want to embed along with the document text. Optional. |
embedding_separator | String | Default: \n | The separator used to concatenate the metadata fields to the document text. Required. |