I have launchpad access with 8 NVIDIA H100 NVL GPUs. I am able to deploy and use VSS with nvila but unable to use gpt-4o model with VSS replacing nvila. I followed the instructions mentioned in Nvidia documentation( Configure the VLM — Video Search and Summarization Agent ). Attaching the images from…

Could you try that with our Python CLI command? We haven’t tried the Azure-OpenAI before. Could you also try interfacing azure openai using custom model interface - where you need to implement one python file by referring to our other-custom-models ?

Attached detailed logs for all pods which are not running

Warning FailedMount 2m10s (x2177 over 3d1h) kubelet MountVolume.SetUp failed for volume "secret-ngc-api-key-volume" : secret "ngc-api-key-secret" not found Have you created the ngc-api-key-secret secret?

Yes, I have created and used the NGC API KEY for deploying VSS with Nvila. I am able to deploy that successfully but when changing the model to gpt-4o then it’s failed to deploy. kubectl get secrets [image]

Could you check if your helm chart and the secret are deployed in the same namespace?

Yes, they are in same namespace. secrets [image] Pods: [image]

From the image you attached, there is no ngc-api-key-secret in your vsstest namespace.

Thanks for notifying that. It solved the error while deploying the services. Now I am able to access UI but when I am trying to use summarization API getting below error: [image] Attached logs for your reference. summary_logs.txt (761.7 KB) Response body for summarization: { "id": "418fe290-…

Hi @ikdwl , could you try with a sample video packaged inside VSS container? We have tried and it works well. Summarize the bridge video using gradio UI(To get the file added to the backend) From swagger UI execute GET /files API to get the asset id of the bridge file Then, use summarize API usin…

This is the response body I tried after removing api_type, Status is 200 but I am not getting content in response { "id": "fb796833-74f0-4fe5-b288-4b2af5fb0e10", "prompt": "Write a concise and clear dense caption for the provided warehouse video", "model": "gpt-4o", "response_format": { …

Unable to configure gpt-4o with VSS instead of vila using Openai-azure API key

Accelerated Computing Intelligent Video Analytics Visual AI Agent

yuweiw April 21, 2025, 6:46am 2

Could you refer to our FAQ and attach the detailed log information?

Topic		Replies	Views
Unable to configure gpt-4o with VSS instead of vila using Openai-azure API key Visual AI Agent nim	1	110	April 21, 2025
VSS issue - API Key Issue When Using OpenAI GPT-4o Instead of LLM-SVC in VSS Blueprint Visual AI Agent nvbugs , kubernetes , ngc , nim , llama-31-70b-instruct , nvidia-technologies , llama , blueprints	6	313	March 4, 2025
Is there any way to use different VLM models on single VSS instance? Visual AI Agent	2	170	October 20, 2025
VSS blueprint 2.2.0 - processing, percentage complete is 0.00 forever Visual AI Agent	8	282	March 6, 2025
Error: "No such model 'openai-compat'" when using VSS Engine with VLM_MODEL_TO_USE=openai-compat Visual AI Agent	2	176	July 7, 2025
VSS FAQ Visual AI Agent	11	916	August 3, 2026
VSS Installation Visual AI Agent	14	482	February 14, 2025
How to get VSS API for CV Pipeline Visual AI Agent cuda	1	133	July 15, 2025
How to get VSS API for CV Pipeline Visual AI Agent	12	436	September 17, 2025
VILA with VIA [New] Visual AI Agent demos-and-tutorials , llama	4	1371	December 24, 2024

Unable to configure gpt-4o with VSS instead of vila using Openai-azure API key

Related topics