Terminal Error "Command not found: inference"

[Erik_Broberg]

• Project Type: Object Detection
• Operating System & Browser: macOS / Chrome
• Project Universe Link or Workspace/Project ID: spots-and-reference-detection (private)

I’m having an issue with deploying my workflow locally on my machine. Even though I have inference, inference-cli, and inference_sdk all installed properly in local bins, I still get the terminal error “command not found: inference” when I try to run a python file that imports InferenceHTTPClient from inference.

Additionally, when I tried to run “inference server start” through my terminal, it gave the same error message. I have the Roboflow Inference application and Docker installed.

Seeing as I’ve done and tried every solution I could find, does anyone have any idea what could be wrong?

[Grzegorz]

Hi @Erik_Broberg ,

I tried below:

# go somewhere where you don't have inference subfolder
cd /tmp
python3.12 -m venv venv
source venv/bin/activate
pip install inference inference_cli inference_sdk
# first call takes some time - for inference interpreter to build caches
inference --help
# below does not fail for me
inference benchmark python-package-speed --model_id yolov8n-640

Can you confirm if pip freeze | grep inference lists all 3 packages for you?

Thanks!
Grzegorz

[Erik_Broberg]

That seemed to do the trick! Thanks!