How to Install and Use AnythingLLM: A Private ChatGPT to Chat with Anything

AnythingLLM is a full-stack application where you can use commercial off-the-shelf LLMs or popular open source LLMs and vectorDB solutions to build a private ChatGPT with no compromises that you can run locally as well as host remotely and be able to chat intelligently with any documents you provide it.

AnythingLLM is a full-stack application that enables you to turn any document, resource, or piece of content into context that any LLM can use as references during chatting. This application allows you to pick and choose which LLM or Vector Database you want to use as well as supporting multi-user management and permissions.

- Multi-user instance support and permissioning

- New Custom Embeddable Chat widget for your website

- Multiple document type support (PDF, TXT, DOCX, etc)

- Manage documents in your vector database from a simple UI

- Two chat modes conversation and query. Conversation retains previous questions and amendments. Query is simple QA against your documents

- In-chat citations

- 100% Cloud deployment ready.

- "Bring your own LLM" model.

- Extremely efficient cost-saving measures for managing very large documents. You'll never pay to embed a massive document or transcript more than once. 90% more cost effective than other document chatbot solutions.

- Full Developer API for custom integrations!

This monorepo consists of three main sections:

- frontend: A viteJS + React frontend that you can run to easily create and manage all your content the LLM can use.

- server: A NodeJS express server to handle all the interactions and do all the vectorDB management and LLM interactions.

- docker: Docker instructions and build process + information for building from source.

- collector: NodeJS express server that process and parses documents from the UI.

- Python 3.8+ (for data collection)

- yarn/npm, Node16+ (for local server)

- Ollama, or OpenAI API key (for embedding + chatting)

- Locally running vector storage instance, or Pinecone DB API Key

Visit the AnythingLLM download page to download the installation package suitable for your platform. Here we Download AnythingLLM for Windows.

Click the downloaded AnythingLLMDesktop.exe installation package file to install. After the installation is completed, click the AnythingLLM icon on the desktop. You will see the interface after AnythingLLM is started as follows.

Select LLM Preference and set LLM Provider to AnythingLLM or Ollama. Here we choose the former. Then select a Model, click Save changes, and wait for the software to automatically download the model and update the related environment.

Return to the main interface and enter a message at the bottom to start your chat with the document.