Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallYou can set up Microsoft GraphRAG around models served by Ollama, but treat the 10-minute framing as a quickstart goal—not a promise that indexing will finish in that time. GraphRAG uses LiteLLM for model calls, and Microsoft says some users route those calls through Ollama; it also warns that malformed responses, especially JSON, can interfere with the workflow. Start with a small text sample, confirm your model returns the structured output GraphRAG expects, and only then index a larger collection.
What you need before starting
- Python 3.10–3.12, the versions listed in the GraphRAG getting-started guide.
- Ollama installed and a local model available to serve the model calls you configure.
- A small set of text documents for a first indexing run. Microsoft’s guide uses a text copy of A Christmas Carol as its example.
There is no documented hardware minimum or guaranteed indexing time for this setup. Microsoft cautions that “GraphRAG can consume a lot of LLM resources!” and recommends beginning with its tutorial dataset and fast or inexpensive models before attempting a large indexing job.
| # | Preview | Product | Price | |
|---|---|---|---|---|
| 1 |
|
MINISFORUM MS-02 Ultra Workstation Mini PC, Intel Core Ultra 9 285HX (24C/24T, up to 5.5GHz), PCIe... | $1,659.00 | Buy on Amazon |
| 2 |
|
GMKtec EVO-X2 AI Mini PC Ryzen Al Max+ 395 Superchip 128GB LPDDR5X 2TB SSD | $3,649.99 | Buy on Amazon |
As an Amazon Associate I earn from qualifying purchases.
How do I run GraphRAG with Ollama locally?
1. Create the project and Python environment
In a terminal, create and enter a project directory, create a virtual environment, activate it, then install GraphRAG:
Free tools Windows power users keep installed
One-click scans. No signup required.
mkdir my-graphrag-project
cd my-graphrag-project
python -m venv .venv
Activate the environment using the command for your shell, then run:
#1 Best Overall
- High-Performance AI Processor：The MS-02 Ultra features an Intel Core Ultra 9 285HX (24C/24T, up to 5.5 GHz, 13 TOPS NPU), delivering fast and efficient performance for AI inference, algorithm development, and media workloads. A PCIe x16 expansion slot supports desktop-class GPU upgrades for advanced model training and accelerated computing tasks. It's ideal for creators, engineers, and teams handling intensive parallel workloads.
- 4 × M.2 PCIe 4.0 + 4 × DDR5 SODIMM slots:Four DDR5 SODIMM slots support up to 256 GB of memory, while ECC helps maintain data integrity in mission-critical environments. Four PCIe 4.0 M.2 slots support up to 24 TB of storage, supporting RAID 0/1/5/10, combining high-speed performance with data protection. It allows for the creation of independent scratch disks, media libraries, and project drives, providing high-throughput for production workflows.
- PCIe & USB 4.0 v2: Up to three PCIe slots can be equipped, including a dual-slot x16 GPU. The main slot supports PCIe 5.0, meeting the needs of high-bandwidth creative and computing workloads. USB 4.0 v2 (80Gbps) supports high-bandwidth external storage and displays.
- Ultra-fast Networking: Wi-Fi 7 further enhances wireless performance with next-generation speeds and low-latency stability. Intelligent bandwidth switching optimizes throughput in different network environments, ensuring optimal performance for enterprise or local networks. Dual 25GbE ports (providing up to approximately 3.125 GB/s bandwidth, about 25 times faster than traditional 1GbE), enabling seamless large-scale file transfers and parallel computing. 10GbE and 2.5GbE ports, with support for Intel vPro technology, ensure enterprise-grade remote management and deployment flexibility.
- Server-grade thermal architecture: Utilizing a dedicated CPU/GPU airflow design, equipped with a 6-pipe dual-fan cooler, it maintains stable performance even under sustained loads, delivering up to 140W Turbo power while maintaining a 100W TDP, and operating with noise levels as low as 36 dB. An integrated 350W power supply ensures stable and reliable output for demanding computing tasks and fully loaded extended configurations.
python -m pip install graphrag
graphrag initThe initialization command creates .env, settings.yaml, and an input directory. For platform-specific environment activation and current installation details, follow the official getting-started instructions.
2. Add a small document and configure model calls
Put one or a few text files in the generated input directory. Open settings.yaml and configure GraphRAG’s model calls using its current model-selection guidance and LiteLLM provider instructions. GraphRAG’s documented non-OpenAI route uses LiteLLM; Microsoft says users have used Ollama and LiteLLM Proxy Server to route calls, but the reviewed documentation does not supply a complete, version-pinned Ollama YAML recipe. Use the current GraphRAG model configuration documentation and LiteLLM Ollama provider instructions to choose the provider, model name, API base, and any required credentials for your particular setup.
Do not assume that every Ollama model will work simply because it can answer ordinary chat prompts. GraphRAG expects structured results, including JSON-shaped output in relevant stages. Microsoft specifically cautions that Ollama/proxy configurations can produce malformed output. Test on the small corpus and inspect errors or malformed results before committing to a larger index. See Microsoft’s model configuration guidance for the current requirements.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
3. Choose an embedding model deliberately
GraphRAG also needs embeddings. Ollama’s embedding-model overview, dated April 8, 2024, gives mxbai-embed-large (334M parameters), nomic-embed-text (137M), and all-minilm (23M) as examples. These sizes are parameter counts published by Ollama—not GraphRAG compatibility certifications, speed tests, or a ranking of which model to use. Confirm that your chosen model is available locally and configure it as the embedding model using the current GraphRAG settings documentation.
How do I index my documents and ask questions?
Index the input directory
Once the model and embedding settings are in place, run:
Rank #2
- EVOLUTION RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 128GB pool, which is perfect for running LLMs such as Deepseek 70B Q8, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 12% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
graphrag indexIndexing extracts information from the input documents and builds the graph and related outputs used for retrieval. It can take substantial LLM resources; the command is not evidence of a guaranteed duration. Review the generated output and any warnings or errors before moving on.
Run a query against the index
The quickstart demonstrates both a broad global-search question and a focused local-search question. Use the CLI syntax shown by your installed GraphRAG version and the current quickstart; examples of the questions are:
- Global: “What are the top themes in this story?” This is suited to an overall view of a document or corpus.
- Local: “Who is Scrooge and what are his main relationships?” This targets a particular entity and its connections in the source material.
The GraphRAG CLI also documents drift and basic query methods. Consult the CLI reference for the commands and options available in your installed version rather than assuming examples from another release have identical syntax.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Which indexing method should I use?
Standard GraphRAG uses an LLM for entity and relationship extraction and for summarization. FastGraphRAG replaces some LLM reasoning with NLP and co-occurrence-based extraction. Microsoft describes FastGraphRAG as faster and cheaper, with a noisier graph and less directly useful extracted descriptions. It is a tradeoff: lower resource use can come at the cost of graph quality, so try it on representative documents and examine the output before choosing it for a larger corpus. See the indexing-method documentation.
Which query method fits the question?
- Local search: Choose this for a question about a named person, concept, or other entity. It uses graph entities as entry points and combines connected entities, relationships, community information, and relevant source-text chunks into context for the answer.
- Global search: Choose this for broad questions about themes across the text, as in Microsoft’s quickstart example.
- Drift or basic: These are additional CLI query methods. Check the CLI reference for their current behavior and usage before incorporating them into a workflow.
What to check when a local run fails
- Model-call or provider errors: Recheck the provider, model identifier, API base, and credentials in the model configuration against the current GraphRAG and LiteLLM instructions.
- Malformed structured output: Confirm the configured model can reliably produce the structured formats GraphRAG expects. Try a different model or configuration and re-run on a small input set.
- Unexpected index results: Inspect the generated files and compare standard indexing with FastGraphRAG only if its cost-and-noise tradeoff suits your needs.
- Query command mismatch: Use the CLI reference corresponding to the installed GraphRAG version; query method names and options are version-sensitive.
GraphRAG was built and tested with OpenAI models, which Microsoft identifies as its most tested and supported models. Ollama is a locally served integration route through LiteLLM that users have used, not a blanket guarantee of equal compatibility or output quality across local models. Refer to the live model configuration documentation as its instructions evolve.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
