{"slug": "graphrag-with-ollama-in-10-minutes-the-local-first-quickstart", "title": "GraphRAG with Ollama in 10 Minutes: The Local-First Quickstart", "summary": "A developer published a 10-minute quickstart for running GraphRAG entirely locally using Ollama and the open-source Chaos Cypher stack, requiring no cloud API keys. The walkthrough covers pulling the qwen3:30b-instruct model, launching the containerized service via Docker, uploading a document, and watching entity extraction build a knowledge graph that answers questions with click-through citations to specific source chunks.", "body_md": "You don't need a cloud API key to try GraphRAG. Ten minutes, one document, and a laptop with a decent GPU (or none at all, for the first few steps) is enough to see a full knowledge graph form and answer a question with a citation you can click through to the source page.\n\nThis is the fast version. If you want the reasoning behind running everything locally -- privacy, VRAM presets, multi-GPU load balancing -- that's in [Build a Private AI Knowledge Graph That Never Leaves Your Machine](https://chaoscypher.com/blog/local-ai-knowledge-graph). This post is the \"just show me\" version: install, upload, watch the graph build, ask a question, done.\n\nBy the end of this walkthrough you'll have:\n\nNothing leaves your machine. No OpenAI key, no Anthropic key, no usage bill.\n\nGrab Ollama from [ollama.com](https://ollama.com) for your platform, then pull the default chat/extraction model in a terminal:\n\n```\nollama pull qwen3:30b-instruct\n```\n\nThis is the long pole of the whole setup -- roughly 18-20 GB. Kick it off now and let it run in the background while you do the next steps; indexing and search don't need it, only extraction and chat do.\n\nIf you're on a smaller GPU or just want to see the pipeline move faster for this first run, point `ollama_chat_model` at a smaller `qwen3` tag instead -- you can always switch to the full model afterward from Settings.\n\n```\ndocker run -d --name chaoscypher \\\n  -p 80:80 \\\n  -p 443:443 \\\n  -v chaoscypher-data:/data \\\n  ghcr.io/chaoscypherinc/chaoscypher:latest\n```\n\nOn Linux Docker Engine (not Docker Desktop), add `--add-host=host.docker.internal:host-gateway` so the container can reach Ollama on your host -- Docker Desktop resolves this automatically.\n\nOpen [http://localhost](http://localhost). A startup page shows each service (Nginx, Cortex, Valkey, Neuron) coming online -- usually 30-60 seconds. Set a username and password on first run, and you land on the Dashboard.\n\nGo to **Sources** in the sidebar and drag in a PDF, DOCX, or text file -- a 10-20 page document is a good first run so you can watch the whole pipeline complete in a couple of minutes.\n\nIndexing starts immediately (chunking + embedding for search) and finishes in about 30 seconds per 100 pages -- this step downloads a small embedding model (~600 MB) the first time, but doesn't need Ollama at all. Once indexing finishes, a **Review** dialog proposes an extraction domain (technical, medical, legal, and so on) detected from the content. Click **Confirm** to queue entity extraction.\n\nIf the Ollama model pull from Step 1 is still running, the source will sit at **extracting** until it finishes -- indexing and search still work while you wait.\n\nOnce extraction commits, open **Graph** in the sidebar. You'll see nodes for the people, organizations, concepts, and events the model found in your document, connected by edges representing the relationships it inferred between them. For a 100-page document on a 30B-class model, expect roughly 5-10 minutes of extraction time.\n\nClick any node to see its properties, its connections, and the source text it was extracted from -- that link back to source evidence is the same mechanism the chat citations use in the next step.\n\nOpen **Chat**, start a new conversation, and ask something specific about the document you just uploaded. Chaos Cypher retrieves the relevant chunks and graph context, hands them to your local model, and streams back an answer with citations attached to the sentences that came from your source.\n\nClick a citation and it jumps straight to the exact chunk in the source document the sentence was grounded in -- not a link to \"the document,\" the specific paragraph. That's the difference between an AI answer you have to take on faith and one you can verify in a click.\n\nThat's the whole loop: install, upload, extract, ask, verify. A few directions once you're comfortable with it:\n\nIn plain English: you can run a real knowledge graph, end to end, on your own machine, in about the time it takes to read this post.", "url": "https://wpnews.pro/news/graphrag-with-ollama-in-10-minutes-the-local-first-quickstart", "canonical_source": "https://dev.to/chaoscypherinc/graphrag-with-ollama-in-10-minutes-the-local-first-quickstart-48h5", "published_at": "2026-09-28 14:50:48+00:00", "updated_at": "2026-09-28 15:21:16.394369+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "ai-infrastructure", "mlops", "developer-tools"], "entities": ["Ollama", "Chaos Cypher", "Qwen3", "Docker", "Nginx", "Valkey", "Neuron", "Cortex"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/graphrag-with-ollama-in-10-minutes-the-local-first-quickstart", "markdown": "https://wpnews.pro/news/graphrag-with-ollama-in-10-minutes-the-local-first-quickstart.md", "text": "https://wpnews.pro/news/graphrag-with-ollama-in-10-minutes-the-local-first-quickstart.txt", "jsonld": "https://wpnews.pro/news/graphrag-with-ollama-in-10-minutes-the-local-first-quickstart.jsonld"}}