[DOC] Document the request/response format required by neural search for data exchange facilitated by AI connectors

[dylan-tong-aws]

What do you want to do?

Document the request/response format required by neural search for data exchange facilitated by AI connectors.

• Request a change to existing documentation
• [ x] Add new documentation
• Report a technical problem with the documentation
• Other

Tell us about your request. Provide a summary of the request and all versions that are affected.

Document the request/response format required by neural search for data exchange facilitated by AI connectors.

Connectors that are designed for powering neural search will receive requests in a specific format. Neural search also requires a response in a specific format. Users need to know the format of the request and respond payload for various reasons like:

1. If I'm an integrator and I'm building a connector blueprint, I need to know the format to implement the appropriate pre/post processing logic
2. If I'm an application developer who wants to integrate a custom model via the Amazon SageMaker connector, I need to know the format so that I can write the appropriate pre/post processing logic in my model serving script.

What other resources are available? Provide links to related issues, POCs, steps for testing, etc.

[hdhalter]

@dylan-tong-aws - Can you please provide the format for the request/response?