AnythingLLM is a comprehensive full-stack application that empowers users to transform any document, resource (such as web links, audio, or video), or content snippet into contextual knowledge, enabling large language models (LLMs) to intelligently utilize these reference materials during conversations.
With AnythingLLM, users can leverage commercial or open-source LLMs and vector databases to build their own private ChatGPT that can run locally or be hosted remotely. This powerful tool allows for intelligent conversations with any provided documents.
Key Features
- Multi-user instance support and permissioning
- Agents inside your workspace (browse the web, run code, etc)
- 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
conversationandquery. 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!
Github: https://github.com/Mintplex-Labs/anything-llm
Supported LLMs, Embedder Models, Speech models, and Vector Databases
Language Learning Models:
- Any open-source llama.cpp compatible model
- OpenAI
- OpenAI (Generic)
- Azure OpenAI
- Anthropic
- Google Gemini Pro
- Hugging Face (chat models)
- Ollama (chat models)
- LM Studio (all models)
- LocalAi (all models)
- Together AI (chat models)
- Perplexity (chat models)
- OpenRouter (chat models)
- Mistral
- Groq
- Cohere
- KoboldCPP
- LiteLLM
- Text Generation Web UI
Embedder models:
- AnythingLLM Native Embedder (default)
- OpenAI
- Azure OpenAI
- LocalAi (all)
- Ollama (all)
- LM Studio (all)
- Cohere
Audio Transcription models:
- AnythingLLM Built-in (default)
- OpenAI
TTS (text-to-speech) support:
- Native Browser Built-in (default)
- OpenAI TTS
- ElevenLabs
STT (speech-to-text) support:
- Native Browser Built-in (default)
Vector Databases:
Use Cases
This versatile tool can be applied to various scenarios, including but not limited to:
Personal Assistant
Interact with personal documents via chat to retrieve information.
Enterprise Knowledge Management
Build an intelligent Q&A system within an enterprise to boost work efficiency.
Education and Research
Leverage AI to engage with academic materials and support learning.
Multi-User Collaboration
Support multi-user management and permission allocation, ideal for team collaboration.
Getting Started
Installation and Deployment
- Desktop: Visit useanything.com to download the desktop application for Mac, Windows, and Linux.
- Docker: Follow the Docker usage guide for deployment.
Creating and Managing Documents
- AnythingLLM organizes documents into objects called “workspaces,” which are similar to threads and can contain containerized documents.
- Manage documents in the vector database through a simple user interface.
Selecting LLMs and Embedding Models
- Support for various open-source and commercial LLMs, including OpenAI, Azure OpenAI, Anthropic, and more.
- Compatible with multiple embedding models and transcription models.
Chat Modes
- Two chat modes available: conversation and query
- Conversation mode retains previous questions and corrections
- Query mode provides simple Q&A for documents
Customization and Integration
- Customizable embedded chat window for integration into websites
- Comprehensive developer API for custom integrations
Development Setup
- Use
yarn setupto populate the required.envfiles. - Start the local server with
yarn dev:server. - Launch the local frontend using
yarn dev:frontend. - Run the document collector with
yarn dev:collector.
Telemetry and Privacy
AnythingLLM includes a telemetry feature that collects anonymous usage information to help improve the product. Users can opt out of telemetry by setting DISABLE_TELEMETRY to "true".
By harnessing the power of AnythingLLM, users can create intelligent, context-aware chatbots from any document or resource, revolutionizing the way we interact with and extract insights from information. Whether for personal use, enterprise knowledge management, education, or collaborative projects, AnythingLLM offers a user-friendly and highly customizable solution for leveraging the potential of AI-driven conversations.
