[{"data":1,"prerenderedAt":114},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-en-private-gpt":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"key":7,"data":8},"marketplace-app-en-private-gpt",{"slug":9,"slugs":10,"categorySlugs":11,"name":16,"description":17,"phase":18,"unavailableReason":19,"docsUrl":20,"logo":21,"github":21,"tagline":22,"longDescription":23,"features":24,"useCases":31,"steps":41,"faq":60,"specs":76,"compatibleOs":86,"relatedApps":87,"relatedPosts":108,"category":111},"private-gpt",{"fr":9,"en":9,"ar":9,"es":9},{"fr":12,"en":13,"ar":14,"es":15},"ia","artificial-intelligence","الذكاء-الاصطناعي","inteligencia-artificial","PrivateGPT","Local document RAG assistant: ask questions of your PDFs, contracts and team notes — LLM and embeddings run on your VPS, zero data leaving the server.",2,"awaiting_qa","https:\u002F\u002Fservorbit.com\u002Fblog\u002Fhow-to-host-privategpt-on-a-vps",null,"100% local AI document assistant — RAG on your files, no cloud, no data leak.","PrivateGPT is an open-source RAG (Retrieval-Augmented Generation) platform that lets you chat with your own documents — PDFs, DOCX, spreadsheets and emails — using a local large language model. Unlike cloud-based AI assistants, PrivateGPT never sends your data outside the server: ingestion, vectorization, storage and inference all happen on your VPS. Powered by an embedded vector store and connected to any OpenAI-compatible inference server (Ollama, llama.cpp, vLLM), it gives you a full RAG pipeline under your control.\n\nDeployed on a ServOrbit VPS alongside Ollama, PrivateGPT becomes a self-contained private AI workspace: upload your contracts, technical documentation or meeting notes, and query them in natural language. Each answer cites the source passage and file name, so you know exactly where it came from. The OpenAI-compatible API at port 8080 lets you integrate the same document intelligence into your internal tools or build custom agents on top of the same indexed corpus.",[25,26,27,28,29,30],"Full offline RAG pipeline — ingest PDFs, DOCX, TXT and CSV; query with your local LLM, zero cloud calls","Source citations on every answer — each response includes the passage and file name that supported it","OpenAI-compatible API at port 8080 — drop-in replacement for the OpenAI client in your existing tools","Connects to any OpenAI-compatible server — Ollama, llama.cpp, vLLM, or the real OpenAI API","Embedded vector store — semantic chunking and embedding stored on-disk, persistent across restarts","Apache-2.0 licence — fully auditable, no telemetry, air-gap capable, 57 k+ GitHub stars",[32,35,38],{"title":33,"body":34},"Legal and HR document intelligence","Upload contracts, employment agreements and HR files to PrivateGPT. Ask 'What are the termination clauses in contract X?' and get a cited answer without any data leaving the VPS — fully compliant with GDPR Article 28.",{"title":36,"body":37},"Internal knowledge base","Index your team's technical documentation, runbooks and meeting notes. Every team member gets a natural-language interface to the corpus, with answers pointing to the exact source passage so they can verify and go deeper.",{"title":39,"body":40},"Private code and security review","Feed proprietary source code or security audit reports into PrivateGPT. Ask questions about architecture, find undocumented functions, or cross-reference CVE descriptions against your own codebase — without a single line of source code leaving the server.",[42,45,48,51,54,57],{"title":43,"body":44},"Order a ServOrbit VPS","Allocate at least 8 GB of RAM: Ollama needs 4–6 GB for a 7B model (Q4_K_M), PrivateGPT itself takes around 500 MB, and you need headroom for document ingestion. A 16 GB VPS is the comfortable choice. The machine ships with Ubuntu 24.04 and Docker pre-installed.",{"title":46,"body":47},"Deploy from the Marketplace","In your ServOrbit client area: Marketplace → Artificial Intelligence → PrivateGPT → Deploy. The stack starts two containers: PrivateGPT (web UI + API on port 8080, bound to 127.0.0.1) and an Ollama sidecar (internal only, not reachable from the internet). Both share a private Docker network — only port 8080 is exposed on the loopback.",{"title":49,"body":50},"Pull your first model","Once the stack is up, pull a language model into Ollama via SSH: `docker exec ollama ollama pull qwen2.5:7b`. For a lightweight start on 8 GB RAM, `qwen2.5:3b` (2.3 GB) is a good entry point. For richer answers on long documents, `mistral:7b` or `llama3.1:8b` are recommended. For embeddings, `nomic-embed-text` improves retrieval quality.",{"title":52,"body":53},"Open the web UI","PrivateGPT's interface is at `http:\u002F\u002F127.0.0.1:8080\u002Fui` (loopback only). Open an SSH tunnel from your workstation: `ssh -L 8080:127.0.0.1:\u003Cport> root@\u003Cvps-ip>` (replace `\u003Cport>` with the port shown in your client area), then go to `http:\u002F\u002Flocalhost:8080\u002Fui` in your browser.",{"title":55,"body":56},"Ingest your documents","Use the Upload button in the UI or the `\u002Fv1\u002Fingest\u002Ffile` API endpoint to upload your documents. PrivateGPT splits each file into chunks, computes embeddings via Ollama, and stores them in the local vector store. Ingestion of a 50-page PDF typically takes 30–90 seconds on CPU.",{"title":58,"body":59},"Query your corpus","Type your question in the chat. PrivateGPT retrieves the most relevant chunks from the vector store, passes them as context to the LLM, and returns an answer with source passages cited below. The `\u002Fv1\u002Fchat\u002Fcompletions` endpoint is OpenAI-compatible for API clients.",[61,64,67,70,73],{"q":62,"a":63},"Does PrivateGPT require a GPU?","No. CPU-only inference works out of the box via Ollama. A modern server CPU handles a 7B Q4_K_M model at 2–5 tokens\u002Fsec — usable for document Q&A where accuracy matters more than speed. For faster inference on larger models, a GPU-equipped VPS accelerates throughput 10–30×.",{"q":65,"a":66},"Which LLM models work best with PrivateGPT?","For general document Q&A on CPU: `qwen2.5:7b` or `mistral:7b` (Q4_K_M, ~4–5 GB). For longer legal or technical documents: `llama3.1:8b`. For a lightweight setup on 8 GB RAM: `qwen2.5:3b` (~2.3 GB). For embeddings: `nomic-embed-text` (270 MB) provides strong semantic retrieval quality.",{"q":68,"a":69},"Can I use the OpenAI API instead of a local Ollama model?","Yes. Set the `OPENAI_API_BASE` environment variable to `https:\u002F\u002Fapi.openai.com\u002Fv1` and provide your `OPENAI_API_KEY`. The RAG pipeline will then use OpenAI for both embeddings and generation, while your documents remain indexed locally on the VPS.",{"q":71,"a":72},"Does PrivateGPT include a vector database?","Yes. PrivateGPT ships with an embedded vector store that persists your indexed chunks on disk in the `private-gpt-data` Docker volume. You do not need to run a separate Qdrant or ChromaDB container. The index survives container restarts.",{"q":74,"a":75},"How do I access PrivateGPT without a domain name?","Open an SSH tunnel: `ssh -L 8080:127.0.0.1:\u003Cport> root@\u003Cvps-ip>` (replace `\u003Cport>` with the port shown in your ServOrbit client area), then navigate to `http:\u002F\u002Flocalhost:8080\u002Fui`. For a permanent public URL, attach a domain in your client area — nginx will proxy to PrivateGPT and provision a TLS certificate automatically.",{"ram":77,"cpu":78,"disk":79,"stack":80,"port":85},"8 GB","2 vCPU","30 GB",[81,82,83,84],"Docker","Python","Ollama","Vector store","8080",[],[88,96,102],{"name":89,"slug":90,"categorySlug":13,"categoryName":91,"categoryColor":92,"logo":93,"tagline":94,"description":95},"AnythingLLM","anything-llm","Artificial Intelligence","text-purple-400 bg-purple-500\u002F10","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fanythingllm.svg","Private AI workspace with RAG and agents — your documents, your models, your server.","Open-source AI workspace with built-in RAG, AI agents, and multi-model chat. Connect your own documents, use any LLM — hosted privately on your VPS.",{"name":97,"slug":98,"categorySlug":13,"categoryName":91,"categoryColor":92,"logo":99,"tagline":100,"description":101},"Open WebUI","open-webui","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fopen-webui.svg","Web interface for your LLMs — Ollama, OpenAI, Mistral — hosted on your own server.","Web interface to interact with your local or remote LLMs. Your data stays on your infrastructure — no third party involved.",{"name":103,"slug":104,"categorySlug":13,"categoryName":91,"categoryColor":92,"logo":105,"tagline":106,"description":107},"Dify","dify","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fdify.svg","Build LLM applications with drag-and-drop — chatbots, agents, RAG pipelines — no backend required.","Build LLM applications visually: chatbots, RAG agents, pipelines — without writing any backend code.",[109,110],"heberger-privategpt-vps","privategpt-documents-confidentiels-vps",{"key":12,"slug":13,"name":91,"objective":112,"icon":113,"color":92},"Build, host and run AI solutions.","ai",1790177409649]