Connection Refused ([Errno 111]) When Using Ollama with AutoGPT

reno_rita

I'm following this tutorial to integrate Ollama (http://localhost:11434/) with AutoGPT (http://localhost:3000) using Docker Compose. However, I encounter the following error when trying to connect: Error calling LLM: [Errno 111] Connection refused I ensured that: Ollama is running. $ curl http://localhost:11434/ Ollama is running The host and port are correct (Ollama defaults to port 11434). Error Details: Connection Refused: Make sure Ollama is...

Originally asked by efremidze on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

Solution: Instead of using localhost , replace it with host.docker.internal in the connection string: http://host.docker.internal:11434/ Background: Docker containers have their own network namespace, so localhost inside a container refers to the container itself—not the host. As a result, services running on the host aren't accessible via localhost from within the container. Reference: This workaround is discussed in this GitHub issue: Ollama Issue #703 .

Full answer by efremidze: https://stackoverflow.stackexchange.com/a/79376932 (CC BY-SA 4.0).

Need it done for your business? UphillTech.