feat: implement unified configuration loading and logging setup across entry points

2025-08-06 22:17:02 +02:00
parent d7aa24a935
commit 9338d6eab8
11 changed files with 263 additions and 128 deletions
@@ -31,12 +31,14 @@ llm:
  max_concurrent_requests: 4
  enable_rate_limiting: true

-# Production data settings
+# Development data settings - limited dataset for faster testing
 data:
  split_evaluation: true
  split_by_gender: true
  evaluation_fraction: 0.2
  random_seed: 42
+  max_dataset_size: 10_000  # Limit to 10k records for development/testing
+  balance_by_sex: true     # Balance male/female samples when limiting

 # Enhanced logging for development
 logging:
@@ -37,6 +37,8 @@ data:
  split_by_gender: true
  evaluation_fraction: 0.2
  random_seed: 42
+  max_dataset_size: null
+  balance_by_sex: false

 # Production logging (less verbose)
 logging:
@@ -58,6 +58,8 @@ data:
  split_by_gender: true
  evaluation_fraction: 0.2
  random_seed: 42
+  max_dataset_size: null
+  balance_by_sex: false

 # Logging configuration
 logging: