Paperless-GPT

Overview

paperless-gpt seamlessly pairs with paperless-ngx to generate AI-powered document titles and tags, saving you hours of manual sorting. While other tools may offer AI chat features, paperless-gpt stands out by supercharging OCR with LLMs-ensuring high accuracy, even with tricky scans. If you’re craving next-level text extraction and effortless document organization, this is your solution. Description of container variables: https://github.com/icereed/paperless-gpt?tab=readme-ov-file#configuration

Requirements

paperless-ngx
local ollama or AI cloud service (OpenAI, Google Document AI, Azure Document Intelligence)

Runtime arguments

Web UI: http://[IP]:[PORT:8080]
Network: bridge
Shell: sh
Privileged: false

Template configuration

Web UI PortPorttcp

Target: 8080
Default: 8080
Value: 8080

Prompt TemplatesPathrw

Custom Prompt Templates https://github.com/icereed/paperless-gpt?tab=readme-ov-file#custom-prompt-templates

Target: /app/prompts
Default: /mnt/user/appdata/paperless-gpt/prompts

PAPERLESS_BASE_URLVariable

URL of your paperless-ngx instance (e.g. http://paperless-ngx:8000).

Default: http://localhost:8000

PAPERLESS_API_TOKENVariable

API token for paperless-ngx. Generate one in paperless-ngx admin.

PAPERLESS_PUBLIC_URLVariable

Public URL for Paperless (if different from PAPERLESS_BASE_URL).

MANUAL_TAGVariable

Tag for manual processing.

Default: paperless-gpt

AUTO_TAGVariable

Tag for auto processing.

Default: paperless-gpt-auto

LLM_PROVIDERVariable

AI backend (openai or ollama).

LLM_MODELVariable

AI model name, e.g. gpt-4o, gpt-3.5-turbo, deepseek-r1:8b.

OPENAI_API_KEYVariable

OpenAI API key (required if using OpenAI).

OPENAI_BASE_URLVariable

OpenAI base URL (optional, if using a custom OpenAI compatible service like LiteLLM).

LLM_LANGUAGEVariable

Likely language for documents (e.g. English).

Default: English

OLLAMA_HOSTVariable

Ollama server URL (e.g. http://host.docker.internal:11434).

Default: http://localhost:11434

OCR_PROVIDERVariable

OCR provider to use (llm, azure, or google_docai).

Default: llm

VISION_LLM_PROVIDERVariable

(for OCR) - openai or ollama

Default: openai

VISION_LLM_MODELVariable

(for OCR) - minicpm-v (ollama example), gpt-4o (for openai), etc.

Default: gpt-4o

AZURE_DOCAI_ENDPOINTVariable

Azure Document Intelligence endpoint. Required if OCR_PROVIDER is azure.

AZURE_DOCAI_KEYVariable

Azure Document Intelligence API key. Required if OCR_PROVIDER is azure.

AZURE_DOCAI_MODEL_IDVariable

Azure Document Intelligence model ID. Optional if using azure provider.

Default: prebuilt-read

AZURE_DOCAI_TIMEOUT_SECONDSVariable

Azure Document Intelligence timeout in seconds.

Default: 120

GOOGLE_PROJECT_IDVariable

Google Cloud project ID. Required if OCR_PROVIDER is google_docai.

GOOGLE_LOCATIONVariable

Google Cloud region (e.g. us, eu). Required if OCR_PROVIDER is google_docai.

GOOGLE_PROCESSOR_IDVariable

Document AI processor ID. Required if OCR_PROVIDER is google_docai.

GOOGLE_APPLICATION_CREDENTIALSVariable

Path to the mounted Google service account key. Required if OCR_PROVIDER is google_docai.

AUTO_OCR_TAGVariable

Tag for automatically processing docs with OCR.

Default: paperless-gpt-ocr-auto

LOG_LEVELVariable

Application log level (info, debug, warn, error).

Default: info

AUTO_GENERATE_TITLEVariable

Generate titles automatically if paperless-gpt-auto is used. Default: true.

Default: true

AUTO_GENERATE_TAGSVariable

Generate tags automatically if paperless-gpt-auto is used. Default: true.

Default: true

AUTO_GENERATE_CORRESPONDENTSVariable

Generate correspondents automatically if paperless-gpt-auto is used. Default: true.

Default: true

AUTO_GENERATE_CREATED_DATEVariable

Generate the created dates automatically if paperless-gpt-auto is used.

Default: true

OCR_LIMIT_PAGESVariable

Limit the number of pages for OCR. Set to 0 for no limit.

Default: 5

TOKEN_LIMITVariable

Maximum tokens allowed for prompts/content. Set to 0 to disable limit. Useful for smaller LLMs.

CORRESPONDENT_BLACK_LISTVariable

A comma-separated list of names to exclude from the correspondents suggestions. Example: John Doe, Jane Smith.

Links

Template Support Docker Hub Project

Details

Repository

icereed/paperless-gpt:latest

Registry

https://hub.docker.com/r/icereed/paperless-gpt

Last Updated2026-03-29

First Seen2025-04-23

Run Paperless-GPT on Unraid.

Paperless-GPT is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.

Explore Unraid OS