Aman
a32b7508c7
PaddleOCR with preprocessing, scispaCy NER, figure/table detection, citation extraction, and chunked Markdown output with frontmatter. Includes watch mode and notebook reprocessing.
26 lines
507 B
Plaintext
26 lines
507 B
Plaintext
# OCR Pipeline Configuration
|
|
# Copy to .env and modify as needed
|
|
|
|
# Logging
|
|
LOG_LEVEL=INFO
|
|
LOG_FILE=./data/logs/ocr_pipeline.log
|
|
|
|
# Input paths (override config.yaml)
|
|
INPUT_PATHS=~/Pictures,/mnt/storage3/aman/screenshots
|
|
|
|
# Processing
|
|
WORKERS=4
|
|
OCR_ENGINE=paddleocr
|
|
USE_GPU=false
|
|
|
|
# Output
|
|
OUTPUT_DIR=./data/ocr_output
|
|
ORGANIZE_BY=date_run
|
|
|
|
# Watch mode
|
|
WATCH_ENABLED=true
|
|
WATCH_DB_PATH=./data/processed_files.db
|
|
|
|
# Optional: GROBID for citation parsing
|
|
GROBID_ENABLED=false
|
|
GROBID_URL=http://localhost:8070 |