sentenceTransformar embedding model download locally to use

[praveshkumar1988]

No description provided.

[Copilot]

Pull Request Overview

This PR implements local downloading and caching of the sentence-transformers embedding model to improve performance and reduce dependency on external model downloads. The changes replace the previous approach of downloading models on each use with a local caching mechanism.

• Implements a singleton pattern for embedding model initialization with thread-safe access
• Adds local model downloading and caching functionality using a specified local path
• Removes global embedding model initialization in favor of lazy loading where needed

Reviewed Changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

File	Description
backend/src/shared/common_fn.py	Adds local model downloading, caching, and singleton pattern for embedding model access
backend/src/make_relationships.py	Removes global embedding initialization and moves to lazy loading pattern
backend/src/QA_integration.py	Removes global embedding initialization and adds lazy loading where needed
backend/requirements.txt	Updates sentence-transformers version from 4.1.0 to 5.0.0

Comments suppressed due to low confidence (1)

backend/requirements.txt:56

• The sentence-transformers version 5.0.0 does not exist. As of my knowledge cutoff in January 2025, the latest available version is in the 3.x series. Please verify the correct version number.

sentence-transformers==5.0.0