feat: web application multipage support

This commit is contained in:
2025-08-16 19:05:24 +02:00
parent 7b652d6999
commit 84f7d41a84
38 changed files with 765 additions and 507 deletions
+5 -2
View File
@@ -18,7 +18,8 @@ paths:
checkpoints_dir: "./data/checkpoints" # Directory for model checkpoints
# Pipeline stages
stages: # List of stages in the processing pipeline
# List of stages in the processing pipeline
stages:
- "data_cleaning" # Data cleaning stage
- "feature_extraction" # Feature extraction stage
- "ner_annotation" # NER-based annotation stage
@@ -36,6 +37,7 @@ processing:
- "utf-16"
- "latin1"
chunk_size: 100_000 # Size of data chunks to process in parallel
epochs: 2 # Number of Epochs for training
# Annotation settings
annotation:
@@ -72,8 +74,9 @@ data:
balance_by_sex: false # Should the dataset be balanced by sex when limiting the dataset size?
# Logging configuration
# Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
logging:
level: "INFO" # Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
level: "INFO"
format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
file_logging: true # Enable logging to file
console_logging: true # Enable logging to console