AnythingLLM: The all-encompassing AI app you've been looking for.

Product Overview

AnythingLLM is a full-stack application that allows you to build a private ChatGPT using off-the-shelf commercial biglanguage models or popular open-source biglanguage models, combined with a vector database solution, and no longer be constrained: you can run it locally or host it remotely, and be able to chat intelligently with any document you provide.

AnythingLLM divides your documents into groups calledworkspaces (workspace) objects. Workspaces function like threads with the added containerization of documents. Workspaces can share documents, but the contents of the workspaces do not interfere with or pollute each other, so you can keep the context of each workspace clear.

Some Cool Features of AnythingLLM

• 🆕 自定义AI代理
• 🆕 无代码AI代理构建器
• 🖼️ Multi-user instance support and privilege management (closed source and open source LLM support!)
• 👤 Multi-user instance support and privilege management Docker version only
• 🦾 Intelligent body Agents in the workspace (browsing the web, running code, etc.)
• 💬 为您的网站定制的可嵌入聊天窗口
• 📖 Support for multiple document types (PDF, TXT, DOCX, etc.)
• Manage documents in vector databases through a simple user interface
• Two modes of dialog:chatsrespond in singingconsult (a document etc). Chat mode keeps a record of previous conversations. Query mode does simple questions and answers about your documents
• The content of the referenced document will be provided in the chat
• 100% cloud deployment ready.
• "Deploying your own LLM model".
• Manage very large documents with high efficiency and low consumption. Embedding a huge document or transcript only once. Save 90% over other document chatbot solutions.
• Full developer API for custom integrations!

Supported LLMs, embedding models, transcription models and vector databases

Supported by LLM:

• 任何与llama.cpp兼容的开源模型
• OpenAI
• OpenAI (通用)
• Azure OpenAI
• Anthropic
• Google Gemini Pro
• Hugging Face (聊天模型)
• Ollama (聊天模型)
• LM Studio (所有模型)
• LocalAi (所有模型)
• Together AI (聊天模型)
• Fireworks AI (聊天模型)
• Perplexity (聊天模型)
• OpenRouter (聊天模型)
• Novita AI (聊天模型)
• Mistral
• Groq
• Cohere
• KoboldCPP
• PPIO (聊天模型)

Supported Embedding Models:

• AnythingLLM原生嵌入器(default)
• OpenAI
• Azure OpenAI
• LocalAi (全部)
• Ollama (全部)
• LM Studio (全部)
• Cohere

Supported transcription models:

• AnythingLLM内置 (default)
• OpenAI

TTS (Text to Speech) support:

• Browser built-in (default)
• PiperTTSLocal - 在浏览器中运行
• OpenAI TTS
• ElevenLabs
• Any OpenAI-compatible TTS service

STT (Speech to Text) support:

• Browser built-in (default)

Supported vector databases:

• LanceDB (default)
• Astra DB
• Pinecone
• Chroma
• Weaviate
• QDrant
• Milvus
• Zilliz

Technology Overview

This single library consists of three main parts:

• frontend: A viteJS + React front end that you can run to easily create and manage all the content LLM can use.
• server: A NodeJS express server that handles all interactions and does all vector database management and LLM interactions.
• docker: Docker commands and build process + information about building from source.
• collector: NodeJS express server for processing and parsing documents from the UI.