GRPC error: Unimplemented - CPU support only

[hanserasmus]

Hi All

First off, thank you for this awesome project. This seems like exactly what I am looking for to start learning the vast world of AI.

I am trying to run a docker AIO but with CPU support only. My compose file looks like this:

version: "3.9"
services:
  api:
    image: localai/localai:latest-aio-cpu
    # For a specific version:
    # image: localai/localai:v2.23.0-aio-cpu
    # For Nvidia GPUs decomment one of the following (cuda11 or cuda12):
    # image: localai/localai:v2.23.0-aio-gpu-nvidia-cuda-11
    # image: localai/localai:v2.23.0-aio-gpu-nvidia-cuda-12
    # image: localai/localai:latest-aio-gpu-nvidia-cuda-11
    # image: localai/localai:latest-aio-gpu-nvidia-cuda-12
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
      interval: 1m
      timeout: 20m
      retries: 5
    ports:
      - 8080:8080
    environment:
      - DEBUG=true
      # ...
    volumes:
      - ./models:/build/models:cached
    # decomment the following piece if running with Nvidia GPUs
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]

LocalAI version:
Docker latest.

Environment, CPU architecture, OS, and Version:
Ubuntu 22.04 VM running on Proxmox V8.2.4. VM running with "host" cpu configuration. Host CPU: Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz

Describe the bug
I cannot use any chat function. See the full docker logs (with debug) for more information.

To Reproduce
Use my docker compose file, run docker compose up -d and try to use the functionality.

Expected behavior
I should get a response from the bot.

Logs
Pastebin link

[hanserasmus]

It would seem I needed to rebuild the docker images. Added the REBUILD = true flag in my compose file, based on info I got from here and now i am able to use the chat prompt. It is horribly slow, but I suspected that on my VERY old hardware.