clusterzx /paperless-ai
An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.
★ 6,031⑂ 333👁 37⑃ 192● 534▤ 59
+8
Daily
6,031
stars
333
forks
37
watchers
192
prs
534
issues
59
releases
README
📄 Paperless-AI Paperless-AI is an AI extension for Paperless-ngx. It analyzes your documents and fills in title, tags, correspondent, document type, date and custom fields – and lets you ask questions about your whole archive in natural language, with answers that cite their sources. Works with Paperless-ngx 2.x and 3.x, OpenAI, Anthropic (Claude), Ollama (fully local), Azure OpenAI and every OpenAI-compatible API (DeepSeek, OpenRouter, LiteLLM, vLLM, LM Studio, Gemini, Together, Perplexity, …). [!IMPORTANT] Security notice for 3.x: in all Paperless-AI versions before 4.0, the setup wizard can be used without logging in. Anyone who can reach such an instance can replace its user account and its configuration (Paperless token, AI provider), and this is being exploited. Update to 4.0 – it is not affected. If your 3.x instance was reachable from the internet, read Upgrading from 3.x before you migrate. 💡 Just ask: “When did I sign my rental agreement?” “What was the amount of the last electricity bill?” “Which documents mention my health insurance?” !Dashboard --- ✨ What's new in 4.0 – a complete rewrite Version 4 is rebuilt from scratch with a focus on reliability, speed and low resource usage. | | 3.x | 4.0 | | --- | --- | --- | | Architecture | Node.js + separate Python service (Torch, ChromaDB, NLTK) | One Node.js process (TypeScript) | | Docker image | several GB | ~135 MB compressed | | RAM in idle | 1–2 GB | ≈ 80–150 MB (embedding model loaded on demand) | | RAG retrieval | one embedding of the first ~100 words per document | chunked passages, hybrid BM25 + vector search, metadata boosts | | RAG answers | not streamed, no references | streamed, cited sources [1], follow-up questions | | Index updates | full re-crawl & re-embed | incremental (changed/deleted documents only) | | Settings | written to .env, container restart required | validated, applied instantly – no restart | | Paperless-ngx | 2.x | 2.x and 3.x (API version negotiated automatically, verified against 2.14, 2.20 and 3.2) | | Undo | only “forget processing state” | real undo – restores the original values in Paperless | | Interface | server-rendered pages | new design: single-page app, command menu, light/dark + accent colours | Upgrading from 3.x is automatic: your data/.env, user account, processing state, history and token statistics are migrated on first start (the old files are kept untouched) – see Upgrading from 3.x. 🚀 Features Automatic processing - Detects new documents (schedule and/or instantly via a Paperless workflow webhook) - Title, tags, correspondent, document type, document date and custom fields (text, long text, number, monetary, date, boolean, URL, select) - AI providers: OpenAI, Anthropic (Claude), Ollama, any OpenAI-compatible API (DeepSeek, OpenRouter, LiteLLM, vLLM, LM Studio, Gemini …) and Azure OpenAI – reasoning/thinking models included - Structured JSON output (JSON schema) with automatic fallback for providers without suppor
Discussions
#977Paperless-ai webhook option to reset a document for reprocessing?5 comments · 2026-09-18#929Stale Project - announcing paperless-ai-next1 comments · 2026-04-01#928Too few user-defined fields0 comments · 2026-04-01#910Why did development stop?2 comments · 2026-03-20#888Image sizes0 comments · 2026-03-10#881How connect to Ollama1 comments · 2026-03-01#851Unprocessed negative value -671 comments · 2026-02-10#832Any way to disable processing on container startup?0 comments · 2026-01-23
Latest release
Paperless-AI 4.0 – a complete rewrite v4.0.0 2026-11-10One Node.js process instead of Node.js + Python, a much smaller image (~135 MB instead of several GB), a new web interface and much better search in your archive. ⚠️ Security notice for 3.x In all versions before 4.0, the setup wizard can be used without logging in, which allows anyone who can reach an instance to replace its account and configuration. This is being exploited. Please update. If your 3.x instance was reachable from the internet, read Upgrading from 3.x before you migrate. Highlights - Title, tags, correspondent, document type, date and custom fields (incl. long text a