OCR-to-RAG pipeline for life science screenshots

PaddleOCR with preprocessing, scispaCy NER, figure/table detection,
citation extraction, and chunked Markdown output with frontmatter.
Includes watch mode and notebook reprocessing.

.env.example

@@ -0,0 +1,26 @@
+# 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