Self-Hosted Document AI: How to Run Document Intelligence On Your Own Infrastructure (2026)

Cloud-based document AI services are convenient — you send documents to an API, get structured data back, and pay by the page. They are also a non-starter for organizations whose work involves sensitive, confidential, or regulated documents that cannot leave their controlled environments.

Healthcare organizations covered by HIPAA cannot route patient records through third-party cloud services without extensive BAA negotiations and vendor security audits. Law firms operating under attorney-client privilege have clients who explicitly require their documents never be processed by external cloud services. Government contractors working with controlled unclassified information face federal restrictions on external data processing. Finance teams handling M&A deal documents work under confidentiality agreements that prohibit third-party cloud processing.

For these teams, the choice is not "cloud vs. self-hosted" based on cost or convenience. It is "self-hosted or no AI at all."

The dominant document AI platforms — Docsumo, Nanonets, Rossum, LlamaParse — are cloud-only. Enterprise platforms like Hyperscience and UiPath Document Understanding offer on-premise deployment, but at enterprise contract pricing — six-figure annual fees with dedicated implementation teams. This is not accessible to a 50-person law firm or a 100-person healthcare practice.

DokuBrain's self-hosted deployment mode is specifically designed to fill this gap — a full intelligent document processing platform that runs on your infrastructure via Docker Compose, accessible without an enterprise contract.

A capable self-hosted document AI deployment needs several components:

Document ingestion layer. Accepts files via upload, email, watched folder, or API. Stores raw documents in object storage. In the DokuBrain stack, MinIO provides S3-compatible object storage that runs locally.

Text extraction service. Converts documents to machine-readable text. For machine-generated PDFs, direct text extraction is fast and accurate. For scanned documents, OCR is required. DokuBrain's Python extractor service supports multiple backends: IBM Docling and Marker for local, on-premise OCR; LlamaParse and LLMWhisperer as optional cloud augmentation if you choose to enable them.

AI extraction and classification. Identifies document type and extracts structured fields using transformer-based models that run locally — extraction does not require sending documents to OpenAI or any external LLM provider unless you configure it to.

Vector database for semantic search. Enables RAG queries and hybrid search across your document library. Qdrant is an open-source vector database that runs in Docker with no cloud connectivity required.

Relational database and queue. PostgreSQL 16 for document metadata, extracted fields, workflow state, and audit logs. Redis for background job queuing.

The full stack runs via a single `docker compose up` command. On a properly sized server, initial setup takes 30-60 minutes for a technical user.

Minimum viable (development / low volume): - 8 CPU cores, 16GB RAM, 100GB SSD - Handles machine-generated PDFs at moderate volume - Not recommended for production with scanned documents

Recommended (production, SMB scale): - 16 CPU cores, 32-64GB RAM, 500GB+ NVMe SSD - Handles mixed document types at up to 10,000 pages/day - Supports concurrent users on the web interface

High-volume or GPU-accelerated: - 16+ CPU cores, 64GB+ RAM, NVIDIA GPU with 8GB+ VRAM - Handles 50,000+ pages/day, reduces OCR latency on scanned documents from seconds to sub-second

Storage sizing: Plan for 5-10x the raw document storage in system storage. A 1GB PDF library grows to 5-10GB when you account for extracted text, embeddings, thumbnails, and database overhead.

Network: Self-hosted deployments do not require internet connectivity for document processing. Outbound internet is optional — used only for LLM API calls if you configure cloud LLM providers. Air-gapped deployments work with local LLM models only.

The standard deployment path for a production DokuBrain self-hosted instance:

Step 1: Server preparation. Install Docker and Docker Compose on Ubuntu 22.04 LTS. Create a dedicated user for the deployment, configure firewall to allow only ports 80/443 (web) and 22 (SSH).

Step 2: Environment configuration. Copy `.env.example` to `.env`. Critical variables to configure: `DATABASE_URL` (strong password), `S3_ENDPOINT` (local MinIO), `JWT_SECRET` (generate with `openssl rand -base64 32`), `FRONTEND_URL` (your domain or IP), and LLM provider selection.

LLM configuration: The default uses OpenAI. For fully private deployments, configure Ollama for local inference: `LLM_PROVIDER=ollama`, `OLLAMA_BASE_URL=http://ollama:11434`, `LLM_MODEL=llama3.2:8b`. Local models are slower than OpenAI API calls and require substantial RAM (7-13GB for 8B models). For document extraction tasks, 8B models perform adequately on structured document types. Complex reasoning tasks benefit from larger models.

Step 3: Start the stack and initialize. `docker compose -f docker-compose.prod.yml up -d` `make db-migrate && make db-seed`

Step 4: Configure reverse proxy. Caddy handles automatic certificate provisioning from Let's Encrypt. Configure DNS pointing to your server, then: `documents.yourcompany.com { reverse_proxy localhost:3000 }`

Step 5: Test. Access your domain, register the first admin account, upload a test document, verify extraction runs successfully.

Beyond DokuBrain, the self-hosted document AI landscape is thin.

IBM Docling is an open-source Python library for document extraction — PDF parsing, table extraction, and text chunking. It is not a complete platform: no web interface, no multi-user access, no workflow automation, no search. It is a component that developers use to build pipelines.

Marker is an open-source PDF-to-Markdown converter that runs locally. Similar scope to Docling — excellent extraction quality, no platform features.

Enterprise on-premise options (Hyperscience, UiPath, ABBYY Vantage, Kofax) all offer on-premise deployment but exclusively through enterprise contracts with dedicated implementation and annual fees starting at $50,000-150,000.

The practical conclusion: for organizations that need a full document intelligence platform with AI extraction, classification, search, RAG, and workflow automation — self-hosted — DokuBrain is currently the only accessible option. Organizations willing to build their own stack can assemble components (Docling for extraction, Qdrant for vectors, PostgreSQL for storage), but this requires significant engineering investment to maintain.

Self-host if: - Your documents are covered by HIPAA, GDPR, attorney-client privilege, or industry regulations prohibiting third-party cloud processing - You have client confidentiality requirements that preclude cloud processing - You operate in an air-gapped or restricted network environment - Your document volumes are large enough that self-hosted infrastructure costs less than per-page cloud pricing (typically 50,000+ pages/month) - You have a technical team capable of managing Docker deployments and Linux servers

Use cloud if: - Your documents do not have data sovereignty requirements - You have no technical staff available for infrastructure management - Your volume is low and per-page costs are not material - You need to get started in hours rather than days

Security considerations for self-hosted deployments: Network isolation is critical — internal services (PostgreSQL, Redis, Qdrant, MinIO) should not be exposed to the internet. Enable disk encryption on the server. Configure daily automated backups of the PostgreSQL database and MinIO storage to a separate location. Pull updated Docker images regularly to receive security patches.

For most SMBs without compliance-driven requirements, DokuBrain's cloud deployment is simpler and immediately available. The self-hosted path is for teams where data sovereignty is non-negotiable, not a preference. For teams dealing with compliance obligations specifically, see document compliance software for small business.