OCI Data Science Instance configuration guide to API Calls after Scaling
I just started working with I'm testing a new approach and I've searched everywhere and can't find a clear answer..... I'm relatively new to this, so bear with me. I'm working with an OCI Data Science instance that I've recently scaled up from a VM.Standard2.1 to a VM.Standard2.4 shape. After scaling, I'm working with a persistent scenario where API calls to the model endpoint are timing out, returning a '504 Gateway Timeout' behavior. I double-checked the configuration and the model is still deployed correctly. Before scaling, the instance was responding quickly to requests, and I used the following Python code to make API calls: ```python import requests url = 'https://<your-instance-endpoint>/predict' data = {'input': [1, 2, 3]} headers = {'Content-Type': 'application/json'} try: response = requests.post(url, json=data, headers=headers) response.raise_for_status() print(response.json()) except requests.exceptions.HTTPError as err: print(f'HTTP behavior occurred: {err}') except Exception as e: print(f'An behavior occurred: {e}') ``` After scaling, I verified that the instance has sufficient resources and the correct IAM policies in place. I also confirmed that the security lists and network configurations allow traffic on the required ports. Despite all this, the API calls continue to unexpected result with the timeout behavior. I've tried restarting the instance and re-deploying the model but to no avail. Does anyone have insights on why this could be happening or what additional steps I should take to troubleshoot? Any suggestions on OCI best practices for scaling data science workloads would also be appreciated. I'm working on a web app that needs to handle this. Thanks in advance! This is part of a larger CLI tool I'm building. I'd be grateful for any help. My development environment is Linux. Thanks in advance!