{"slug": "my-hybrid-ai-system-in-obsidian-local-and-cloud-ai-integration", "title": "My Hybrid AI System in Obsidian: Local and Cloud AI Integration", "summary": "A writer detailed a hybrid AI setup in Obsidian that routes private notes and journals to a local model via Ollama while sending work documents to Google's Gemini 2.5 Flash through the Copilot for Obsidian community plugin, which supports both local and cloud providers. The setup uses a free Google AI Studio API key for Gemini and recommends a GPU for acceptable local-model performance. The approach separates sensitive personal data from cloud processing while keeping faster cloud queries for non-private material.", "body_md": "AI is rapidly gaining popularity across various fields, and I've found that integrating it into a personal knowledge management system like Obsidian offers far more benefits than one might initially expect.\n\nIn this article, I'll show you exactly how I've enabled both local AI and cloud AI within Obsidian, configuring them for different vaults to suit my specific needs.\n\n## How I Choose AI\n\nAI technology, while powerful, often comes with inherent privacy concerns.\n\nWhen you opt for a corporate AI solution, which typically offers faster queries and results, you're risking your privacy.\n\nOn the other hand, if you decide to use local AI, it can be quite taxing and slow, especially on moderate hardware.\n\nGiven this dilemma, I asked myself: why not use both? With Obsidian, setting up such a workflow is surprisingly easy.\n\nI personally use a local AI for my most private notes and journals, ensuring my personal thoughts remain entirely on my machine.\n\nFor my work-related documents and learning journeys, where speed and broader knowledge access are key, I leverage Gemini chat (because it's free). This approach gives me the best of both worlds: privacy where it matters most, and powerful cloud capabilities for everything else.\n\nIf you want more segregation, have separate vaults for your work and personal notes.\n\n## Use Copilot for Obsidian extension\n\nDon't go by the name. It's not exclusive to Microsoft Copilot.\n\nTo integrate AI directly into Obsidian, I rely on [Copilot for Obsidian](https://community.obsidian.md/plugins/copilot?ref=itsfoss.com), a fantastic [community extension](https://itsfoss.com/obsidian-plugins/). This plugin supports both local and cloud AI, and it even offers its own Plus features for those who want to enhance their experience further.\n\nHere's how to [install this extension in Obsidian](https://itsfoss.com/obsidian-use-plugin/):\n\nGo to the Obsidian settings by pressing `CTRL+,`. Inside the settings, go to **Community Plugins -> Browse**.\n\nSearch for Copilot and install the extension.\n\nEnable it right away using the **Enable** button.\n\n## Setting Gemini AI in Obsidian\n\nNow that Copilot for Obsidian is installed, let me show how I configure Gemini AI within Obsidian.\n\n### Create API Key\n\nGo to the [Google AI Studio website](https://aistudio.google.com/api-keys?ref=itsfoss.com). Click on Create API key button.\n\nHere, give the key a name and click on **Create a New Project**.\n\nGive the project a name and click on **Create Project**\n\nNow, click on **Create Key**.\n\nUse the **Copy key** button to copy the API key.\n\n### Configure Obsidian Copilot\n\nTo configure Copilot, open Obsidian and go to settings (`CTRL+,`). Here, in the sidebar, scroll down and select **Copilot**.\n\nIn the copilot settings, go to the **Basic** tab, click on **Set Keys** button.\n\nHere, paste the copied API key into the designated field and then select your preferred Gemini model from the dropdown. I have added the Gemini 2.5 Flash model in this particular setup.\n\nSet the default chat model to the added one.\n\nBy now, Copilot should be ready and available in the ribbon menu. Simply click on its icon there to open it in the right sidebar.\n\nFollow the same setup for other AI providers like Claude, GPT, etc.\n\n## Setting up Local AI\n\nThe Copilot plugin isn't just for cloud AI; it can also be used to set up local AI directly within Obsidian.\n\nHere, I'll explain how to get local AI working using Ollama.\n\n### Install Ollama\n\n[Ollama](https://itsfoss.com/ollama/) is a command-line tool that allows us to download and run open-source Large Language Models (LLMs) like Llama3, Phi-3, Mistral, CodeGamma, and many others, right on my local machine.\n\nTo run AI locally on Linux with Ollama, you should have a GPU on your system. While it's possible to run AI on a CPU, the experience won't be ideal. A GPU is highly recommended for better performance. If you have a TPU/NPU, that would be even better but I am not sure if Ollama would support all TPU/NPU.\n\nFor this tutorial, I'll be using the **Llama3.2 3B** model. Even though it can be taxing on a CPU-only machine, it still offers noticeably faster performance compared to larger models without a dedicated GPU.\n\nYou can, of course, choose other, heavier models based on your system's specifications.\n\nTo [install Ollama](https://itsfoss.com/ollama-setup-linux/), use the command:\n\n```\ncurl -fsSL https://ollama.com/install.sh | sh\n```\n\nOnce Ollama is installed, it's a good idea to check if it's running correctly. By default, it operates on a specific port number on localhost.\n\nTo verify its status, open a web browser and enter:\n\n```\nlocalhost:11434\n```\n\nIt should show the message, \"Ollama is running\".\n\n### Install llama3.2 3b model\n\nNow that you have Ollama up and running, install the `llama3.2 3b` model using the command:\n\n```\nollama run llama3.2:3b\n```\n\nThis will download almost 2GB+ data and enable the model. Once the command execution is completed, you will be automatically entered to a llama prompt, where you can chat with the model from terminal.\n\nTo exit the prompt, use the command:\n\n```\n/bye\n```\n\nTo stop the model, use the command:\n\n```\nollama stop llama3.2:3b\n```\n\n### Note the name of the AI\n\nIn a terminal, run the [ollama command](https://itsfoss.com/ollama-commands/):\n\n```\nollama list\n```\n\nThis will list the installed models in your system. Copy the name of the **llama3.2** model exactly as shown in the output.\n\n### Configure Obsidian Copilot\n\nOpen Obsidian and go to the Copilot settings as done for the Gemini method.\n\nHere, go to the **Model** tab and select **Add Model** button.\n\nFill the fields appropriately. The **Model Name**, marked with a red asterisk, should be exactly the name you copied in the last step.\n\nThe **Display name** can be any identifiable name you choose. Set the provider to Ollama, and you can leave the Base URL and API key fields as their default values; there's no need to add anything there.\n\nYou can enable **Vision** in **Model Capabilities** if you want to allow image additions to the chat.\n\nOnce you've filled everything out, you can press the **Test** button to check for any configuration errors. If no errors are reported, use the **Add Model** button to add this model to your available list.\n\nNow, go back to the **Basic** tab and set the default chat model to Llama.\n\nThat's it! From now on, you can use the local AI to chat with your notes.\n\n## Using the AI interface\n\nCopilot for Obsidian comes packed with a lot of cool features. Let's take a look at some of the cooler ones that you may find yourself using frequently.\n\n### Context aware chat\n\nAs we've seen, Copilot features a neat chat interface that appears in the right sidebar when enabled. This sidebar offers several cool options that can significantly improve your notes.\n\nFor example, by default, the current note is automatically selected as the context for your chat. However, by pressing the `@` symbol, I can easily select multiple notes to serve as context for my conversation, allowing for more comprehensive and interconnected AI interactions.\n\n### Send images in chat\n\nAt times, you may want to chat along with a screenshot. For example, when I am writing some configs, I can take a screenshot of an error and ask the LLM what the error is right then and there.\n\nIf the model supports processing images, you can do this directly via the sidebar interface. This is shown in the recording below.\n\n### Add chat to note\n\nWhat is the use of an AI assistant if it cannot add content directly to your notes? Copy and paste is not always a good solution.\n\nTo solve this, each result in the sidebar has an Insert/Replace at cursor button. Clicking on it immediately adds the chat result to the exact place where your cursor is currently located in your note or document, making the workflow incredibly seamless.\n\n### Chat backups\n\nCopilot extension adds all chat sessions to a dedicated folder (`copilot/copilot-conversations`) in your vault as standard Markdown documents. The chat file is cleanly structured in a simple format:\n\n```\nuser: user's prompt\nai: ai reply\n```\n\nThe best thing about this setup is that it is properly backlinked. A backlink to the chat note is available right within your active note, which is incredibly good for getting a quick refresh on your thought process later on.\n\n## Wrapping Up\n\nUsing AI in a note-taking application could be a controversial choice, and it is completely a user's personal choice. While AI can hallucinate and add wrong data, I never suggest someone use it for research purposes.\n\nThe core learning and note-taking should always be done manually, but you can leverage the power of AI to add some helpful context to your note. Also, you can use it to format your note into a better Personal Knowledge Management (PKM) format, as doing that completely manually is often just an unwanted burden.\n\nDo you prefer using AI in your Obsidian? Feel free to mention your thoughts in the comments section.\n\nIf this helped you, consider supporting It's FOSS\n\nIt's FOSS has been helping people use Linux for the past 14 years. Help us stay independent from big tech. Become a Plus member, enjoy ad-free reading and get 5 eBooks.\n\nSkip the AI slop and SEO spam in your Google results\n\nTell Google you prefer It's FOSS, and it will show our Linux news and tutorials, created by experienced Linux users, more often when you search. It takes just a click.\n\n[Set as preferred source](https://www.google.com/preferences/source?q=itsfoss.com)\n\nGet FOSS Weekly in your inbox", "url": "https://wpnews.pro/news/my-hybrid-ai-system-in-obsidian-local-and-cloud-ai-integration", "canonical_source": "https://feed.itsfoss.com/link/24361/17537415/obsidian-hybrid-ai-system", "published_at": "2026-11-22 05:18:03+00:00", "updated_at": "2026-11-22 07:13:35.303335+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "ai-products"], "entities": ["Obsidian", "Copilot for Obsidian", "Ollama", "Google AI Studio", "Gemini 2.5 Flash", "Google", "Llama3", "Mistral"], "also_reported_by": [], "takeaway": "Route private notes to a local Ollama model and non-sensitive work notes to a cloud model like Gemini 2.5 Flash through the Copilot for Obsidian plugin, using separate vaults for stricter segregation.", "recommendation": {"advice": "Use a free Google AI Studio API key with Gemini 2.5 Flash for non-private notes and a local Ollama model for sensitive ones; keep separate vaults to enforce the split.", "playbook": "llm-cost", "playbook_url": "https://wpnews.pro/playbooks/llm-cost"}, "alternates": {"html": "https://wpnews.pro/news/my-hybrid-ai-system-in-obsidian-local-and-cloud-ai-integration", "markdown": "https://wpnews.pro/news/my-hybrid-ai-system-in-obsidian-local-and-cloud-ai-integration.md", "text": "https://wpnews.pro/news/my-hybrid-ai-system-in-obsidian-local-and-cloud-ai-integration.txt", "jsonld": "https://wpnews.pro/news/my-hybrid-ai-system-in-obsidian-local-and-cloud-ai-integration.jsonld"}}