Pull Request Summary

This pull request introduces a new, powerful feature for analyzing and responding to user queries using a Large Language Model (LLM), alongside significant enhancements to the CI/CD pipeline. Additionally, it addresses the need to restore critical performance features that were not present in the initial branch.

New Features & Enhancements

• LLM-Powered Query Analysis:

  • A new Python-based backend has been integrated (, ) to process natural language queries. analyze_query.py``prompt_runner.py
  • This system can detect the user's intent, handle complex and multi-part questions, and generate relevant responses by leveraging an LLM.

• Real-time Streaming Support:

  • The new enables Server-Sent Events (SSE) for real-time, streaming responses to the user, creating a more interactive experience. StreamingWrapper.py
  • Includes robust error and connection handling to ensure stability.

• CI/CD Automation:

  • The workflow has been updated to fully automate the Docker image build-and-push process. prod-build.yml
  • On any change to the Dockerfile in the main or iuneracustomizations branches, the workflow will automatically extract the version, build the image, push it to the registry, and create a corresponding Git tag.

• Dockerfile Improvements:

  • The Dockerfile is now configured for non-interactive builds and the application VERSION has been updated to 2.9.0.

Reinstatement of Performance Features

It was noted that crucial performance-related features were missing from this branch. This PR will also focus on restoring the following functionalities to ensure the application remains fast and efficient:

1. Caching: The caching layer will be re-implemented to store and serve frequently accessed data, reducing database load and improving response times.
2. Query Tuning: The logic for optimizing and tuning database queries will be restored to ensure maximum efficiency.
3. Enhanced DB Load: The mechanisms for faster and more reliable data loading from the database will be re-integrated.

By combining the new LLM capabilities with these critical performance optimizations, this pull request delivers a significantly more powerful and efficient application.