Skip to content
Wombat

aws_bedrock_embeddings

Computes vector embeddings on text, using the AWS Bedrock API.

Introduced in version 4.37.0.

# Common config fields, showing default values
label: ""
aws_bedrock_embeddings:
  model: amazon.titan-embed-text-v1 # No default (required)
  text: "" # No default (optional)

This processor sends text to your chosen large language model (LLM) and computes vector embeddings, using the AWS Bedrock API. For more information, see the AWS Bedrock documentation.

Examples

Compute embeddings for some generated data and store it within Clickhouse

input:
  generate:
    interval: 1s
    mapping: |
      root = {"text": fake("paragraph")}
pipeline:
  processors:
  - branch:
      request_map: |
        root = this.text
      processors:
      - aws_bedrock_embeddings:
          model: amazon.titan-embed-text-v1
      result_map: |
        root.embeddings = this
output:
  sql_insert:
    driver: clickhouse
    dsn: "clickhouse://localhost:9000"
    table: searchable_text
    columns: ["id", "text", "vector"]
    args_mapping: "root = [uuid_v4(), this.text, this.embeddings]"

Fields

region

The AWS region to target.

Type: string

endpoint

Allows you to specify a custom endpoint for the AWS API.

Type: string

credentials

Optional manual configuration of AWS credentials to use. More information can be found in xref:guides:cloud/aws.adoc[].

Type: object

credentials.profile

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

Type: string

credentials.id

The ID of credentials to use.

Type: string

credentials.secret

The secret for the credentials being used.

Type: string

credentials.token

The token for the credentials being used, required when using short term credentials.

Type: string

credentials.from_ec2_role

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

Type: bool

Requires version 4.2.0 or newer

credentials.role

A role ARN to assume.

Type: string

credentials.role_external_id

An external ID to provide when assuming a role.

Type: string

model

The model ID to use. 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

text

The prompt you want to generate a response for. By default, the processor submits the entire payload as a string.

Type: string