add bluprint examples for semantic search using cohere embed v4

[tkykenmt]

Description

add bluprint examples for semantic search using cohere embed v4

Related Issues

Resolves #4271

Check List

• New functionality includes testing.
• New functionality has been documented.
• API changes companion pull request created.
• Commits are signed per the DCO using --signoff.
• Public documentation issue/PR created.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

[mingshl]

@tkykenmt are you trying to write post processing function to tune the model output the same format as local model output?

[tkykenmt]

@mingshl

result of cohere embed v4 is different from v3, so existing post processing function does not work as well. So I write custom post processing function based on existing similar blueprint.

https://docs.opensearch.org/latest/tutorials/vector-search/vector-operations/semantic-search-byte-vectors/

It introduces using quantized vector from Cohere Embed v3, and can be adopted v4 with some changes.

[mingshl]

@tkykenmt will you consider making a new post processing function? That sounds convenient and also similar to previous blueprint

earlier, these are

            "pre_process_function": "connector.pre_process.cohere.embedding",
            "post_process_function": "connector.post_process.cohere.embedding"

but it doesn't work for v4 model.

how about creating an new set?

            "pre_process_function": "connector.pre_process.cohere.embedding_v4",
            "post_process_function": "connector.post_process.cohere.embedding_v4"

or please suggest new names?