aws_bedrock_embeddings

beta

Available in: Cloud, Self-Managed

Generates vector embeddings from text prompts, using the AWS Bedrock API.

  • Common

  • Advanced

# Common config fields, showing default values
label: ""
aws_bedrock_embeddings:
  model: amazon.titan-embed-text-v1 # No default (required)
  text: "" # No default (optional)
# All config fields, showing default values
label: ""
aws_bedrock_embeddings:
  region: ""
  endpoint: ""
  credentials:
    from_ec2_role: false
    role: ""
    role_external_id: ""
  model: amazon.titan-embed-text-v1 # No default (required)
  text: "" # No default (optional)

This processor sends text prompts to your chosen large language model (LLM), which generates vector embeddings for them using the AWS Bedrock API.

For more information, see the AWS Bedrock documentation.

Fields

credentials

Manually configure the AWS credentials to use (optional). For more information, see the Amazon Web Services guide.

Type: object

credentials.from_ec2_role

Use the credentials of a host EC2 machine configured to assume an IAM role associated with the instance.

Type: bool

credentials.id

The ID of the AWS credentials to use.

Type: string

credentials.profile

The profile from ~/.aws/credentials to use.

Type: string

credentials.role

The role ARN to assume.

Type: string

credentials.role_external_id

An external ID to use when assuming a role.

Type: string

credentials.secret

The secret for the AWS credentials in use.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Manage Secrets before adding it to your configuration.

Type: string

credentials.token

The token for the AWS credentials in use. This is a required value for short-term credentials.

Type: string

endpoint

A custom endpoint URL for AWS API requests. Use this to connect to AWS-compatible services or local testing environments instead of the standard AWS endpoints.

Type: string

model

The ID of the LLM that you want to use to generate vector embeddings. For a full list, see the AWS Bedrock documentation.

Type: string

# Examples:
model: amazon.titan-embed-text-v1

# ---

model: amazon.titan-embed-text-v2:0

# ---

model: cohere.embed-english-v3

# ---

model: cohere.embed-multilingual-v3

region

The region in which your AWS resources are hosted.

Type: string

tcp

Configure TCP socket-level settings to optimize network performance and reliability. These low-level controls are useful for:

  • High-latency networks: Increase connect_timeout to allow more time for connection establishment

  • Long-lived connections: Configure keep_alive settings to detect and recover from stale connections

  • Unstable networks: Tune keep-alive probes to balance between quick failure detection and avoiding false positives

  • Linux systems with specific requirements: Use tcp_user_timeout (Linux 2.6.37+) to control data acknowledgment timeouts

Most users should keep the default values. Only modify these settings if you’re experiencing connection stability issues or have specific network requirements.

Type: object

tcp.connect_timeout

Maximum amount of time a dial will wait for a connect to complete. Zero disables.

Type: string

Default: 0s

tcp.keep_alive

TCP keep-alive probe configuration.

Type: object

tcp.keep_alive.count

Maximum unanswered keep-alive probes before dropping the connection. Zero defaults to 9.

Type: int

Default: 9

tcp.keep_alive.idle

Duration the connection must be idle before sending the first keep-alive probe. Zero defaults to 15s. Negative values disable keep-alive probes.

Type: string

Default: 15s

tcp.keep_alive.interval

Duration between keep-alive probes. Zero defaults to 15s.

Type: string

Default: 15s

tcp.tcp_user_timeout

Maximum time to wait for acknowledgment of transmitted data before killing the connection. Linux-only (kernel 2.6.37+), ignored on other platforms. When enabled, keep_alive.idle must be greater than this value per RFC 5482. Zero disables.

Type: string

Default: 0s

text

The prompt you want to generate a vector embedding for. The processor submits the entire payload as a string.

Type: string