AnythingLLM on Railway is here!

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.

This is a fully imaged version of the primary AnythingLLM repo!

⭐ Star on Github: https://github.com/Mintplex-Labs/anything-llm

Includes all features of the main app including:

• Private embeddings
• LLM Support
• built-in vector database
• external chatbot support
• multi-user authentication
• Admin controls

Supported LLMs:

• OpenAI
• Azure OpenAI
• Anthropic ClaudeV2
• Google Gemini Pro
• Ollama (chat models)
• LM Studio (all models)
• LocalAi (all models)
• Together AI (chat models)
• Mistral

Supported Embedding models:

• AnythingLLM Native Embedder (default)
• OpenAI
• Azure OpenAI
• LM Studio (all)
• LocalAi (all)

Supported Vector Databases:

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

Note: This image is updated often but is not always in sync with the latest tag on Docker for the master branch. If something is missing ping us on Discord!

LICENSE

AnythingLLM is MIT Licensed.