sentenceTransformar embedding model download locally to use

[praveshkumar1988]

No description provided.

[Copilot]

Pull Request Overview

This PR implements local downloading and usage of the sentence-transformers embedding model to avoid repeated downloads and improve performance. The changes move from environment-based configuration to .env file loading and add robust local model initialization with thread-safe singleton pattern.

• Add local sentence transformer model download and caching functionality
• Update Docker configuration to pre-download models and NLTK resources during build
• Refactor embedding model loading to use lazy initialization and remove global variables

Reviewed Changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
docker-compose.yml	Switch from environment variables to .env file configuration
backend/src/shared/common_fn.py	Add singleton pattern for local embedding model with download functionality
backend/src/ragas_eval.py	Improve NLTK resource downloading with better error handling
backend/src/make_relationships.py	Remove global embedding variables and use lazy loading
backend/src/document_sources/gcs_bucket.py	Add robust NLTK resource downloading with path configuration
backend/src/QA_integration.py	Move embedding initialization to point of use instead of global
backend/requirements.txt	Update sentence-transformers and ragas versions
backend/Dockerfile	Pre-download embedding model and NLTK resources during build

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
You can also share your feedback on Copilot code review for a chance to win a $100 gift card. Take the survey.}