Deployment recipes

Stacks

Deployment recipes: a named objective, the components that meet it, the hardware it needs, the steps in order and the compliance notes that come with it. Every command is copied from the project’s own documentation, and every step names the page it came from.

Published: 12
Showing: 10

Self-hosted

10 stacks

Runs on hardware you own. No third party processes the content.

01Local LLM inference server (Ollama / vLLM)vLLM for throughput or Ollama for simplicity, one GPU, and LiteLLM in front as the gateway that issues per-team keys and records spend. The endpoint other recipes point at.Local LLMPrivate LLM2/5 difficulty6 steps
02Private ChatGPT on your own serverOllama serving an open-weight model on one GPU, Open WebUI in front of it for accounts, chats and admin controls, both in Docker on a single machine. Deliberately the smallest thing that works: no vector database, no connectors, no cluster.Private company ChatGPTPrivate LLMLocal LLMEmail drafting

2/5 difficulty6 steps

03AI coding assistant with private codeTabby for inline completion and Continue for in-editor chat, both pointed at a local model served by vLLM. Continue can be installed from a downloaded extension file and configured against local models for air-gapped environments; telemetry is switched off deliberately.AI coding assistant3/5 difficulty7 steps

04Document classification and OCR pipelineDocling (or Unstructured) converts and OCRs, embeddings plus rules classify, a local model reads only the documents that need reading, and Paperless-ngx gives the business a place to search and file. Starts CPU-only; a GPU is added when the volume justifies it.Document classificationOCRData extractionDocument Q&A3/5 difficulty6 steps

05Meeting and call transcription to CRM notesfaster-whisper or WhisperX transcribes and separates speakers on your own GPU, a local model writes the summary and the action items against a fixed schema, and n8n files the result against the right CRM record with a person approving before it is saved.Meeting transcriptionCall transcriptionCRM call summaries3/5 difficulty7 steps

06Private company knowledge base (self-hosted RAG)Open WebUI as the employee interface, vLLM serving a Qwen2.5-14B-Instruct model on a single 24 GB GPU, PostgreSQL with pgvector for chats and embeddings, and OIDC single sign-on — all in Docker on one server in your office or colocation rack. Ollama replaces vLLM for teams under about 20 users; a 48 GB GPU lets you run a 32B model for better answers.Internal company searchDocument Q&AKnowledge managementPrivate LLM3/5 difficulty11 steps

07Contract review and clause extractionDocling converts the contract to structured text with layout preserved; a 32B open-weight model on vLLM fills a JSON schema of clause fields under constrained decoding; results land in PostgreSQL with pgvector for search and precedent lookup; a reviewer approves in the UI.Contract reviewLegal researchDocument Q&AData extraction4/5 difficulty7 steps

08Customer-support agent with knowledge base and handoffDify self-hosted as the agent builder and knowledge base, a local model on vLLM behind it, pgvector or Qdrant for retrieval, and n8n for the handoff into your helpdesk. Scoped deliberately: a defined topic list, a refusal path, and a human queue.AI customer-support agentEmployee helpdeskHR knowledge assistant4/5 difficulty7 steps

09Invoice capture and extractionInvoices arrive by email or watched folder, Docling converts them (OCR included), a local vision-capable model fills a JSON schema under constrained decoding, code checks the arithmetic and the supplier against your master data, and n8n posts the clean ones while routing the rest to a person.Invoice extractionInvoice processing automationData extractionOCR4/5 difficulty7 steps

10Voice agent (telephony + STT + LLM + TTS)LiveKit Agents or Pipecat as the real-time orchestrator, a SIP trunk for telephony, faster-whisper for speech to text, a local model for the conversation, and a self-hosted TTS voice. Every hop counts against a latency budget of roughly a second.Voice agentAI customer-support agentCall transcription5/5 difficulty7 steps