# GenAI Stack

A starter stack combining LangChain, Neo4j and Ollama with Docker, meant as a template and set of demo applications for building a GenAI application.

GenAI Stack is configured through a `.env` file copied from `env.example`, with variables for the Ollama API URL, the Neo4j connection, the LLM to use, and the embedding model.

The LLM variable accepts any Ollama model tag or GPT-4 and GPT-3.5, and the embedding model can be a sentence-transformer, OpenAI, AWS, Ollama, or Google GenAI embedding. On macOS, Ollama runs separately with `ollama serve`; on Linux, it can run inside the stack using a dedicated Docker Compose profile. Optional environment variables enable LangSmith tracing.

It is licensed under CC0-1.0.

Website: https://github.com/docker/genai-stack