Merge branch 'Merged20250805' into Merged20250811

Merge pull request #14 from YanBoChen0928/Jeff

Enhance evaluation framework with comprehensive metrics and improved query complexity analysis, temp bug fixing about metric 7-8

Update query file references for full evaluation and improve user prompts in evaluation scripts (before optimized_general_pipeline)

Refactor evaluation modules and add hospital chart generation

Add RAG vs Direct Latency Comparison Chart Generator for performance analysis

Enhance direct LLM evaluation with retry mechanism for 504 timeouts and improved guidance format

Add comprehensive evaluation reports and execution time breakdown for Hospital Customization System

Update query file references for full evaluation and correct typo in pre_user_query_evaluate.txt for pre-test.

Merge branch 'newbranchYB-newest' into Merged20250805

Add adaptive relevance thresholds for query complexity in PrecisionMRRAnalyzer; fix typo in condition mapping for postpartum hemorrhage

Update threshold values in latency evaluator and coverage chart generator; enhance precision and MRR analysis with corrected thresholds and new chart generator for detailed metrics visualization.

Refactor relevance calculation and update thresholds in latency evaluator; enhance precision and MRR analyzer with angular distance metrics; increase timeout for primary generation in fallback configuration.

Enhance Direct LLM Evaluator and Judge Evaluator:

feat(evaluation): add visualization generators for generating png files

feat(evaluation): add comprehensive hospital customization evaluation system

Add multi-system evaluation support for clinical actionability and evidence quality metrics

Before Run the 1st Evalation: Add Precision & MRR Chart Generator and a sample test query

feat: Add Extraction, LLM Judge, and Relevance Chart Generators

Add extraction and relevance evaluators for condition extraction and retrieval relevance analysis

Add latency and relevance evaluators for medical query analysis (evaluatoin)

feat(evaluation): add seventh evaluation metric for multi-level fallback efficiency and early interception rate

fix(evaluation): improve evaluation instructions and add structured assessment phases

fix(mild bug): enhance user query prompts (more robust dealing process with .txt or .json) and add postpartum hemorrhage condition mapping

Add evaluation instructions and user query prompts for clinical model assessment