[FLINK-38572][model] Support controlling randomness and format of Chat Model Function

[yunfengzhou-hub]

What is the purpose of the change

This PR proposes to pass several OpenAI API parameters through model function parameter, in order to better support controlling the randomness and format of Chat Model Function.

Brief change log

The following parameters are proposed to be passed

• presence-penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
• n: How many chat completion choices to generate for each input message.
• seed: the random seed to generate results
• response-format: The format of the response, e.g., 'text' or 'json_object'.

Verifying this change

Unit tests are added to OpenAIChatModelTest to verify the newly introduced parameters.

Does this pull request potentially affect one of the following parts:

• Dependencies (does it add or upgrade a dependency): yes
• The public API, i.e., is any changed class annotated with @Public(Evolving): no
• The serializers: no
• The runtime per-record code paths (performance sensitive): yes
• Anything that affects deployment or recovery: JobManager (and its components), Checkpointing, Kubernetes/Yarn, ZooKeeper: no
• The S3 file system connector: no

Documentation

• Does this pull request introduce a new feature? yes
• If yes, how is the feature documented? docs

[flinkbot]

CI report:

• e21e4f9 Azure: SUCCESS

Bot commands

The @flinkbot bot supports the following commands:

• @flinkbot run azure re-run the last Azure build

[Sxnan]

Thanks for the PR! LGTM