ollama

Section: standalone-ai Subsystem: ai-services Port: 11434 Deploy type: image-copy Health: http://ollama:11434/api/tags Compose: ollama/docker-compose.yml

Fragile: Models must be pulled manually: `docker exec ollama ollama pull <model>`. Check available models before routing traffic.

Description

Local LLM inference server (Ollama)

Role

Runs local LLM models; used by llm-gateway as an inference backend option

Dependencies

None configured

Runbooks

None

Behavioral Assertions

None

Diagnostic Tools

None

Recent Issues

No issues on record