Files
homelab-docker/office/paperless-gpt/docker-compose.yml

62 lines
2.7 KiB
YAML

services:
paperless-gpt:
# Use one of these image sources:
image: icereed/paperless-gpt:latest # Docker Hub
# image: ghcr.io/icereed/paperless-gpt:latest # GitHub Container Registry
environment:
PAPERLESS_BASE_URL: "http://192.168.2.102:8010"
PAPERLESS_API_TOKEN: "1aed46ed5666fbc215463032ce5f011cffdf78f6"
#PAPERLESS_PUBLIC_URL: "http://paperless.mydomain.com" # Optional
MANUAL_TAG: "paperless-gpt" # Optional, default: paperless-gpt
AUTO_TAG: "paperless-gpt-auto" # Optional, default: paperless-gpt-auto
# LLM Configuration - Choose one:
# Option 1: Standard OpenAI
LLM_PROVIDER: "openai"
LLM_MODEL: "gpt-4o"
OPENAI_API_KEY: "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"
# Optional LLM Settings
LLM_LANGUAGE: "German" # Optional, default: English
LLM_REQUESTS_PER_MINUTE: "60"
LLM_MAX_RETRIES: "3"
LLM_BACKOFF_MAX_WAIT: "30s"
TOKEN_LIMIT: "8000"
#GIN_MODE: release
# OCR Configuration - Choose one:
# Option 1: LLM-based OCR
OCR_PROVIDER: "llm" # Default OCR provider
VISION_LLM_PROVIDER: "openai" # openai or ollama
VISION_LLM_MODEL: "gpt-4o" # minicpm-v (ollama) or gpt-4o (openai)
# OCR Processing Mode
OCR_PROCESS_MODE: "image" # Optional, default: image, other options: pdf, whole_pdf
PDF_SKIP_EXISTING_OCR: "false" # Optional, skip OCR for PDFs with existing OCR
# Enhanced OCR Features
CREATE_LOCAL_HOCR: "false" # Optional, save hOCR files locally
LOCAL_HOCR_PATH: "/app/hocr" # Optional, path for hOCR files
CREATE_LOCAL_PDF: "false" # Optional, save enhanced PDFs locally
LOCAL_PDF_PATH: "/app/pdf" # Optional, path for PDF files
PDF_UPLOAD: "false" # Optional, upload enhanced PDFs to paperless-ngx
PDF_REPLACE: "false" # Optional and DANGEROUS, delete original after upload
PDF_COPY_METADATA: "true" # Optional, copy metadata from original document
PDF_OCR_TAGGING: "true" # Optional, add tag to processed documents
PDF_OCR_COMPLETE_TAG: "paperless-gpt-ocr-complete" # Optional, tag name
AUTO_OCR_TAG: "paperless-gpt-ocr-auto" # Optional, default: paperless-gpt-ocr-auto
OCR_LIMIT_PAGES: "5" # Optional, default: 5. Set to 0 for no limit.
LOG_LEVEL: "info" # Optional: debug, warn, error
volumes:
- prompts:/app/prompts # Mount the prompts directory
- hocr:/app/hocr # Only if CREATE_LOCAL_HOCR is true
- pdf:/app/pdf # Only if CREATE_LOCAL_PDF is true
ports:
- "8180:8080"
volumes:
prompts:
hocr:
pdf: