AnythingLLM, the all-in-one open source document chatbot and RAG application, preinstalled as a system service with the workspace UI published on port 80 behind an nginx proxy. A built-in local embedder and vector database make it RAG-ready on launch, with a unique admin password generated on first boot. Bring your own LLM provider. Backed by 24/7
Overview
AnythingLLM is an all-in-one, open source application for chatting with your documents using any large language model. It turns any document, resource or piece of content into context that a chatbot can reference during conversation, with a clean workspace based UI, retrieval augmented generation, AI agents and a built-in vector database. This image delivers AnythingLLM fully installed and configured as a system service, so a production grade private document chatbot is running within minutes of launch.
Application Stack
AnythingLLM built bare-metal from source on Node.js 22 LTS and run by a dedicated unprivileged service account. The application server and the document collector run as separate systemd services that start on boot and restart on failure. All customer state, the application database, the vector store, the embedder model cache and your uploaded documents, is stored on a dedicated data disk so it is independently resizable and survives instance replacement. An nginx reverse proxy publishes the workspace UI on port 80 with WebSocket support for streaming chat.
RAG-Ready Out Of The Box
The image ships with a built-in local embedding model and a built-in local vector database, so document upload, chunking, embedding and semantic search all work on a fresh launch with no external service to configure. Create a workspace, drag in PDFs, text, Office documents or web pages, and AnythingLLM embeds them locally so your private content never leaves the instance for indexing. Retrieval augmented generation grounds every answer in your own documents.
Bring Your Own LLM
AnythingLLM is provider agnostic. Choose your preferred large language model provider, a hosted API such as OpenAI, Anthropic or Azure OpenAI, or a local model server such as Ollama, and supply your key once in Settings to enable chat. You stay in full control of which model answers and where your prompts go.
Secure First Boot
On the first boot of your instance a one shot service generates a fresh admin password, unique to that instance, seeds it into the application database as a bcrypt hash, enables multi-user mode so the instance requires a login, regenerates the cryptographic signing secrets and writes the password to a root only file. The application binds to loopback only and is never exposed without authentication. No shared or default credentials ship in the image.
cloudimg Support
24/7 technical support by email and chat. Help with deployment, workspace and document configuration, embedding and vector database tuning, LLM provider setup, AI agents, API keys, TLS and runtime tuning.
Use Cases
Private document question and answer over internal knowledge bases. Customer support assistants grounded in product documentation. Research and literature review over large PDF collections. Contract and policy search. Internal chatbots that keep sensitive content on your own infrastructure.
All product and company names are trademarks or registered trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.