[Feature][Transform] Support single/batch mode vectorization using Amazon Titan & cohere embedding model

[SEZ9]

Purpose of this pull request

Does this PR introduce any user-facing change?

Description
Add support for Amazon Titan model in the embedding model_provider configuration;
Implement batch inference support in the embedding process, and send data to the model API in batches at one time;
Support successful detection of batch sending and perform fault tolerance.
Usage Scenario
In large-scale text vectorization and storage in vector databases, users need to vectorize text data efficiently and at low cost and store it in vector databases. For example:

User's reviews analysis scenario, it is necessary to transfer millions or tens of millions of rows of data at one time for vectorization.
Image search scenario, users often have hundreds of thousands or millions of images vectorized into the database for subsequent vector approximation retrieval

How was this patch tested?

Check list

• If any new Jar binary package adding in your PR, please add License Notice according
  New License Guide
• If necessary, please update the documentation to describe the new feature. https://github.com/apache/seatunnel/tree/dev/docs
• If you are contributing the connector code, please check that the following files are updated:
  1. Update plugin-mapping.properties and add new connector information in it
  2. Update the pom file of seatunnel-dist
  3. Add ci label in label-scope-conf
  4. Add e2e testcase in seatunnel-e2e
  5. Update connector plugin_config
• Update the release-note.

[Copilot]

Copilot reviewed 5 out of 6 changed files in this pull request and generated no comments.

Files not reviewed (1)

• seatunnel-transforms-v2/pom.xml: Language not supported

[hailin0]

https://github.com/apache/seatunnel/pull/9120/checks?check_run_id=40108495922

[hailin0]

Please update docs

https://github.com/apache/seatunnel/blob/dev/docs/en/transform-v2/embedding.md
https://github.com/apache/seatunnel/blob/dev/docs/zh/transform-v2/embedding.md

[SEZ9]

updated doc both en and cn

[corgy-w]

Whether Amazon e2e tests are missing

[corgy-w]

Please update EmbeddingTransformFactory config

[SEZ9]

updated EmbeddingTransformFactory ,add Amazon model config

[SEZ9]

updated Amazon e2e tests in embedding_transform.conf

[corgy-w]

Is region not here

[SEZ9]

AWS region is a required parameter when calling the Amazon model.

[SEZ9]

Hi @hailin0 @corgy-w . Is there anything else I need to do before this PR can be merged?

[hailin0]

You need to fix the ci error

[corgy-w]

@SEZ9 Hi, You need to see what is wrong with the CI. Sometimes the error is obvious, and you can correct it according to his guidance

[Copilot]

Pull Request Overview

This pull request adds support for single and batch mode vectorization using Amazon Titan and Cohere embedding models. It introduces new test cases for request JSON generation, implements the BedrockModel for Amazon Bedrock integration, and updates configuration and documentation to support the new model provider.

Reviewed Changes

Copilot reviewed 8 out of 10 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
seatunnel-transforms-v2/src/test/java/org/apache/seatunnel/transform/embedding/EmbeddingRequestJsonTest.java	Adds tests for BedrockModel request JSON generation for both Titan and Cohere.
seatunnel-transforms-v2/src/main/java/org/apache/seatunnel/transform/nlpmodel/embedding/remote/amazon/BedrockModel.java	Implements Amazon Bedrock embedding model support with handling for Titan and Cohere.
seatunnel-transforms-v2/src/main/java/org/apache/seatunnel/transform/nlpmodel/embedding/EmbeddingTransformFactory.java	Extends option rules to include Amazon Bedrock options.
seatunnel-transforms-v2/src/main/java/org/apache/seatunnel/transform/nlpmodel/embedding/EmbeddingTransform.java	Updates the embedding transform to initialize BedrockModel for the AMAZON provider.
seatunnel-transforms-v2/src/main/java/org/apache/seatunnel/transform/nlpmodel/ModelTransformConfig.java	Adds AWS region configuration option for Amazon Bedrock.
seatunnel-transforms-v2/src/main/java/org/apache/seatunnel/transform/nlpmodel/ModelProvider.java	Adds the AMAZON provider with corresponding metadata.
docs/zh/transform-v2/embedding.md	Updates documentation to include Amazon Bedrock and region configuration.
docs/en/transform-v2/embedding.md	Updates documentation to include Amazon Bedrock and region configuration.

Files not reviewed (2)

• seatunnel-e2e/seatunnel-transforms-v2-e2e/seatunnel-transforms-v2-e2e-part-1/src/test/resources/embedding_transform.conf: Language not supported
• seatunnel-transforms-v2/pom.xml: Language not supported