# clusterzx/paperless-ai

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/clusterzx-paperless-ai).**

5,238 stars · 255 forks · JavaScript · mit

## Links

- GitHub: https://github.com/clusterzx/paperless-ai
- Homepage: https://clusterzx.github.io/paperless-ai/
- awesome-repositories: https://awesome-repositories.com/repository/clusterzx-paperless-ai.md

## Topics

`ai` `automation` `gemma` `llama` `mistral` `ollama` `paperless` `paperless-ngx` `phi`

## Description

paperless-ai is an AI-powered assistant for Paperless-ngx that automates document classification, tagging, and natural language search. It connects directly to a Paperless-ngx instance, monitors for new or updated documents, and uses configurable AI models to assign titles, tags, types, and correspondents automatically. The tool also provides a real-time chat interface that lets users ask questions about any document and receive context-aware answers.

Beyond automated classification, paperless-ai offers several distinguishing capabilities. Every AI request, raw response, and applied metadata change is recorded in a local database, creating a full audit trail for review and compliance. Documents can be processed manually on demand through a web interface, and conversational document retrieval sends both the query and full document text to the language model in a single request, eliminating the need for a separate retrieval store. The system uses polling-based monitoring and exposes a REST API for integration, with template-based prompts that enforce consistent output formatting.

The assistant supports natural language document search that understands context beyond simple keywords, and allows users to select and customize different AI models and processing parameters to suit their specific needs.

## Tags

### Data & Databases

- [LLM-Based Document Classifiers](https://awesome-repositories.com/f/data-databases/document-classification/llm-based-document-classifiers.md) — Automatically classifies documents by assigning titles, tags, types, and correspondents using AI models.
- [Document Classification](https://awesome-repositories.com/f/data-databases/document-classification.md) — Automatically assigns titles, tags, types, and correspondents to documents using configurable AI models. ([source](https://cdn.jsdelivr.net/gh/clusterzx/paperless-ai@main/README.md))

### Artificial Intelligence & ML

- [AI Integration APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/ai-integration-apis.md) — Integrates with external AI services via HTTP to send document content and receive structured AI responses.
- [Document Management Assistants](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-assistants/document-management-assistants.md) — Automates document classification, tagging, and natural language search within document management systems using configurable AI models.
- [Natural Language Querying](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/language-tools/natural-language-querying.md) — Enables querying document content using natural language that understands context beyond keyword matching. ([source](https://cdn.jsdelivr.net/gh/clusterzx/paperless-ai@main/README.md))
- [AI Model Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-model-configurations.md) — Allows users to select AI models and configure processing parameters for document analysis. ([source](https://clusterzx.github.io/paperless-ai/))
- [Custom AI Models](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-ai-models.md) — Allows selection and configuration of different AI models for tailored document analysis.

### Part of an Awesome List

- [Document Interaction](https://awesome-repositories.com/f/awesome-lists/ai/document-interaction.md) — Enables real-time AI conversation with any document to extract insights and answer queries.
- [Document Question Answering](https://awesome-repositories.com/f/awesome-lists/ai/document-question-answering.md) — Provides a conversational interface to query document content using natural language beyond simple keyword matching.

### System Administration & Monitoring

- [AI Interaction Audit Logs](https://awesome-repositories.com/f/system-administration-monitoring/logging/application-logging-configurations/centralized-logging-architectures/ai-interaction-audit-logs.md) — Records every AI decision and metadata change to a local database for full traceability and compliance review.
- [Document Polling Monitors](https://awesome-repositories.com/f/system-administration-monitoring/polling-based-health-monitors/document-polling-monitors.md) — Continuously polls a document management API to detect new or updated documents for automated AI processing.
- [Reasoning Audit Logs](https://awesome-repositories.com/f/system-administration-monitoring/security-audit-logs/guardrail-audit-logs/reasoning-audit-logs.md) — Records every AI decision and interaction for review and compliance documentation.

### User Interface & Experience

- [Documentation Chat Interfaces](https://awesome-repositories.com/f/user-interface-experience/web-chat-interfaces/documentation-chat-interfaces.md) — Provides a real-time chat interface for conversational interactions with documents.
- [AI Interaction](https://awesome-repositories.com/f/user-interface-experience/visual-page-builders/audit-trails/ai-interaction.md) — Records every AI decision and interaction for review and compliance in document processing.

### Business & Productivity Software

- [Interaction Logs](https://awesome-repositories.com/f/business-productivity-software/spend-tracking-tools/ai-usage-analytics/compliance-auditing/interaction-logs.md) — Persists every AI request, response, and metadata change to a local database for full auditability. ([source](https://clusterzx.github.io/paperless-ai/))

### Content Management & Publishing

- [Conversational Retrieval](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/conversational-retrieval.md) — Answers user questions by sending document text and query together to a language model for context-aware retrieval.
