perf: Move SentenceTransformer to module level to prevent reload on every query

[24f3005089]

Fixes #178

Summary

This PR fixes a performance issue where the SentenceTransformer model was being reloaded from disk on every search request, causing 500ms-2s latency per call.

Changes

• Moved encoder = SentenceTransformer(EMBEDDING_MODEL) initialization from inside milvus_search() function to module level
• Applied fix to both server/app.py and server-https/app.py
• Model is now loaded once at startup and reused for all queries

Impact

• Eliminates 500ms-2s model loading overhead on every query
• Particularly beneficial in agentic RAG workflows where search_kubeflow_docs may be invoked multiple times per conversation turn
• Improves overall system responsiveness and reduces resource usage

Testing

Code change only - verified syntax and logic. The model initialization now happens at module import time, and the encoder variable is reused across all function calls.

[google-oss-prow]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please assign franciscojavierarceo for approval. For more information see the Kubernetes Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment