Feat: Add functionality to calculate intra-cluster distances and compare them between original and fine-tuned models

[Devasy23]

This pull request adds functionality to calculate intra-cluster distances and compare them between the original and fine-tuned models. It includes code changes to load the fine-tuned model, extract faces, calculate embeddings, and calculate intra-cluster distances. The results are outputted, including the shift in intra-cluster distances, mean distance change, positive and negative impact, and average effects. This functionality will provide valuable insights into the performance of the fine-tuned model compared to the original model.

• Add vector_search function for pipeline aggregation
• Added Vector Search
• chore: Add error handling for no match found in face recognition
• Refactor face recognition code to use the Facenet512 model for better accuracy
• Code added for recognize_face API
• temp commit to resolve merge
• Updated gitignore

Co-authored-by: Devansh Shah devanshnshah11@gmail.com @devansh-shah-11

[sonarcloud[bot]]

Quality Gate failed

Failed conditions
37.8% Coverage on New Code (required ≥ 80%)
E Security Rating on New Code (required ≥ A)

See analysis details on SonarCloud

Catch issues before they fail your Quality Gate with our IDE extension SonarLint