Aman Nalakath
7503a441c2
Some checks failed
tests / core (macos-latest, py3.11) (push) Has been cancelled
tests / core (macos-latest, py3.12) (push) Has been cancelled
tests / core (macos-latest, py3.13) (push) Has been cancelled
tests / core (ubuntu-latest, py3.11) (push) Has been cancelled
tests / core (ubuntu-latest, py3.12) (push) Has been cancelled
tests / core (ubuntu-latest, py3.13) (push) Has been cancelled
tests / doctor CLI smoke test (push) Has been cancelled
34 lines
708 B
Plaintext
34 lines
708 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
|
|
|
|
# Optional: Neo4j for `ocr-pipeline kg export -f neo4j`
|
|
NEO4J_URI=bolt://localhost:7687
|
|
NEO4J_USER=neo4j
|
|
NEO4J_PASSWORD=
|
|
|
|
# Optional: LLM provider keys for kg_ocr.rag (ask_wllm)
|
|
# OPENROUTER_API_KEY= |