GenAI Stack

The GenAI Stack will get you started building your own GenAI application in no time.

Configure

Available variables:

Variable Name	Default value	Description
OLLAMA_BASE_URL	http://host.docker.internal:11434	REQUIRED - URL to Ollama LLM API
WEAVIATE_URL	weaviate cluster url	OPTIONAL - URL to weaviate cluster
WEAVIATE_API_KEY	weaviate token	OPTIONAL - Weaviate token
LLM	llama2	REQUIRED - Can be any Ollama model tag
EMBEDDING_MODEL	sentence_transformer	REQUIRED - Can be sentence_transformer or ollama

LLM Configuration

MacOS and Linux users can use any LLM that's available via Ollama. Check the "tags" section under the model page you want to use on https://ollama.ai/library and write the tag for the value of the environment variable LLM= in the .env file.

MacOS Install Ollama on MacOS and start it before running docker compose up.

Linux No need to install Ollama manually, it will run in a container as part of the stack when running with the Linux profile: run docker compose --profile linux up. Make sure to set the OLLAMA_BASE_URL=http://llm:11434 in the .env file when using Ollama docker container.

To use the Linux-GPU profile: run docker compose --profile linux-gpu up. Also change OLLAMA_BASE_URL=http://llm-gpu:11434 in the .env file.

Windows Not supported by Ollama, so Windows users need to generate an OpenAI API key and configure the stack to use gpt-3.5 or gpt-4 in the .env file.

Develop

Warning

There is a performance issue that impacts python applications in the 4.24.x releases of Docker Desktop. Please upgrade to the latest release before using this stack.

To start everything

docker compose up

If changes to build scripts have been made, rebuild.

docker compose up --build

To enter watch mode (auto rebuild on file changes). First start everything, then in new terminal:

docker compose watch

Shutdown If health check fails or containers don't start up as expected, shutdown completely to start up again.

docker compose down

Applications

Name	Main files	Compose name	URLs	Description
Support Bot	bot.py	bot	http://localhost:8501	Main usecase. Fullstack Python application.

The database can be explored at http://localhost:7474.

App - Agent Bot

UI: http://localhost:8501 DB client: http://localhost:7474

• answer support question based on recent entries
• provide summarized answers with sources

---