# IM.Umbraco.AI.Local: local LLMs for Umbraco AI \| Idea Makers Canonical URL: A Local LLM provider for Umbraco AI. Run prompts, Copilot, agents and embeddings on Ollama, LM Studio, vLLM or LiteLLM on your own server. IM.Umbraco.AI.Local · Umbraco 17 # Local AI in the Umbraco backoffice A Local LLM provider for Umbraco AI. Prompts, agents, Copilot and embeddings run on a model on your own server, with no cloud account. [Get it on NuGet](https://www.nuget.org/packages/IM.Umbraco.AI.Local) [Umbraco Marketplace](https://marketplace.umbraco.com/) Package **Install:** dotnet add package IM.Umbraco.AI.Local **Version:** 17.1.3 **Umbraco:** 17.8+ · Umbraco AI 17.6.1+ **.NET:** 10 On this page - [Use cases](https://ideamakers.pl/en/nuget/im-umbraco-ai-local/#use-cases) - Servers - Background - Get started - In use - Support Use cases ## What you can do with a local model ### Meta descriptions and summaries A prompt reads the page and proposes an SEO description or a short summary. The editor chooses, edits and saves. Nothing is published without a person. ### Rewrite and translate drafts Shorten a paragraph, change the tone or prepare a first translation for the editor to check, right next to the field. ### Copilot for editors Editors ask about their content in the backoffice and get answers from the model on your server. ### Agents with backoffice tools Agents call tools to find and prepare content. Tool calls work with Ollama because the package rewrites their schemas. ### Search by meaning Embeddings from your own model can power semantic search and related-content lists. The search itself is built in your site. ### Content that must stay inside Intranets, member areas and regulated sectors: prompts and page content never leave your infrastructure. Works with ## Any OpenAI-compatible server you run 01 ### Ollama Simple local setup for open models. A good start on one machine. [Ollama](https://ollama.com/) 02 ### LM Studio Desktop app with a local API server, handy for trying models. [LM Studio](https://lmstudio.ai/) 03 ### vLLM High-throughput serving on your own GPUs. [vLLM](https://docs.vllm.ai/) 04 ### LiteLLM A gateway in front of several models, with its own keys. This is how ideamakers.pl is connected. [LiteLLM](https://docs.litellm.ai/) Background ## Cloud AI services and local servers differ Both speak the same OpenAI-compatible API, but they do not behave the same way. This is general background on how the two kinds of service work, not something specific to one site. ### A cloud AI service OpenAI, Anthropic, Google and similar. The built-in providers in Umbraco AI are written for these. - Access needs the vendor's API key, checked by the vendor - A fixed list of the vendor's own models - Accepts strict tool schemas and several system messages in one request ### A server you run Ollama, LM Studio, vLLM or a gateway such as LiteLLM, on your own hardware or network. - The server URL is often enough; a key is optional - Serves whichever models you have loaded - Many chat templates reject strict tool schemas or more than one system message What IM.Umbraco.AI.Local adjusts - Connects with a URL alone and treats the API key as optional\. - Shows every model the server returns, for chat and embeddings\. - Rewrites tool\-call schemas into a form local servers accept\. - Merges system messages into one, at the start of the conversation\. Get started ## Install, connect, use 01 ### Install - Add the NuGet package to your Umbraco 17 site\. - Umbraco finds the provider automatically\. - No changes in Program\.cs\. 02 ### Connect - In the AI section, add a Local LLM connection\. - Enter your server URL, for example http://localhost:11434/v1 for Ollama\. - Add an API key if your server needs one\. 03 ### Use - Create profiles for chat and embeddings\. - Add prompts to the fields your editors use\. - Turn on Copilot or agents when you are ready\. ``` dotnet add package IM.Umbraco.AI.Local ``` In use ## On our own site 01 · Prompt on the SEO description field ### SEO meta description The prompt reads the page and proposes three descriptions of 140 to 155 characters, in the language of the page. The editor picks one, edits it if needed and saves. Umbraco backoffice dialog SEO meta description with three English options for the Contact page 02 · Prompt on excerpt and description fields ### Page summary Two short summaries for listings, excerpts and leads, written by the same local model from the content of the page. Umbraco backoffice dialog Page summary with two summaries of the IM.Umbraco.AI.Local package page Screenshots from the ideamakers.pl backoffice on Umbraco 17.8. Both prompts run on a Qwen model on our own server, connected through IM.Umbraco.AI.Local. Support ## Questions, bugs and ideas On GitHub - [Issue tracker: bugs and feature requests](https://github.com/Idea-Makers/im-umbraco-ai-local/issues) - [Discussions: questions and setup help](https://github.com/Idea-Makers/im-umbraco-ai-local/discussions) - [Release notes for every version](https://github.com/Idea-Makers/im-umbraco-ai-local/releases) - [README: full documentation](https://github.com/Idea-Makers/im-umbraco-ai-local) ## Want AI in your backoffice, on your own server? We can set up the model server, the connection and the prompts with your team. You do not need a ready specification. - Umbraco 17 - Umbraco AI [Let’s talk](https://ideamakers.pl/en/contact.md) [All NuGet packages](https://ideamakers.pl/en/nuget.md) im-umbraco-ai-local