What is AnythingLLM?
AnythingLLM is an open-source application that lets you chat with your documents using any LLM. Upload PDFs, text files, or web pages, and AnythingLLM chunks, embeds, and stores them in a vector database. When you ask a question, it retrieves relevant context and sends it to the LLM. With 57,000 GitHub stars, it is one of the most popular RAG applications.
AnythingLLM supports custom OpenAI-compatible LLM providers. Add EUrouter as a provider in the settings, and every LLM call, including the ones that carry your document context, routes through EU servers. If you are working with sensitive documents subject to GDPR, this keeps the entire RAG pipeline within European jurisdiction.
Quick to integrate
A few lines of code is all it takes. Swap your base URL and you are routed through EUrouter.
1// Settings > LLM Provider > Generic OpenAI
2{
3 "Base URL": "https://api.eurouter.ai/v1",
4 "API Key": "eur-...",
5 "Model": "gpt-4o"
6}Get started in minutes
Follow these steps to connect your application to EUrouter.
Install AnythingLLM
Download the desktop app or deploy via Docker.
1docker pull mintplexlabs/anythingllmSet the LLM provider
Go to Settings > LLM Provider and select "Generic OpenAI". Enter the EUrouter base URL and API key.
Upload documents and chat
Create a workspace, upload your documents, and start chatting. All LLM calls route through EU infrastructure.
Why use AnythingLLM with EUrouter
Document chat with EU compliance
When you chat with documents in AnythingLLM, your document chunks are sent as context to the LLM. With EUrouter, that context routes through EU servers. Sensitive internal documents never leave European jurisdiction during AI processing.
- Document context and queries route through EUrouter's EU servers
- Suitable for confidential business documents subject to GDPR
- RAG pipeline stays within European jurisdiction end to end
- Full audit trail for compliance reporting
Any model for your knowledge base
Through EUrouter, AnythingLLM can use GPT-4o, Claude, Mistral, and all other supported models. Switch models to find the best fit for your document types. One API key covers everything.
- Access all EUrouter models from the AnythingLLM model selector
- Try different models for different document workspaces
- One API key and one bill for all usage
- Embedding models also available through EUrouter
Self-hosted and private
AnythingLLM runs on your machine or server. Your documents stay local. With EUrouter handling the LLM calls through EU infrastructure, the only data that leaves your environment goes to EU-based servers. No US processing.
- Documents stored locally on your infrastructure
- Only LLM queries leave your environment, routed through EU servers
- Desktop app available for individual use, Docker for team deployments
- Full control over data retention and document lifecycle