Fix: prevent double embedding in mem0.add (fixes #3723)

[Sbboss]

Description

• Reuse precomputed embeddings when infer=False (sync/async) so mem0.add no longer calls the embedder twice.
• Allow _create_memory to accept provided embeddings; avoids redundant API calls.
• Update Azure AI Search vector query to use k (current SDK) and adjust the test accordingly.
• Add regression test to ensure infer=False embeds once and uses the main vector store.

Fixes #3723

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)

How Has This Been Tested?

MEM0_DIR=$PWD/.mem0 pytest -p no:rerunfailures tests/

Please delete options that are not relevant.

• Unit Test

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published in downstream modules
• I have checked my code and corrected any misspellings

Maintainer Checklist

• closes #xxxx (Replace xxxx with the GitHub issue number)
• Made sure Checks passed

[CLAassistant]

All committers have signed the CLA.

[Sbboss]

@parthshr370 pls review this