nvidianim Skill
NVIDIA NIM on AKS with GPU — vector embeddings and chat completions from SQL Server 2025 T-SQL using GPU-accelerated inference. Use when: deploying NIM containers on AKS, creating AKS GPU node pools, testing NIM endpoints, creating external models for NIM embeddings, Azure Local edge AI pattern, working in nvidianim/. Published by microsoft in bobsql.
What is nvidianim Skill?
NVIDIA NIM on AKS with GPU — vector embeddings and chat completions from SQL Server 2025 T-SQL using GPU-accelerated inference. Use when: deploying NIM containers on AKS, creating AKS GPU node pools, testing NIM endpoints, creating external models for NIM embeddings, Azure Local edge AI pattern, working in nvidianim/. Published by microsoft in bobsql. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Testing
- Database workflows
- Deployment
- Testing use cases
- Database workflows use cases
Technical details
- Install or run with Copy skill directory
When to use nvidianim Skill
- Use it for testing.
- Use it for database workflows.
- Use it for deployment.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/bobsql
- Skill file: demos/sqlserver2025/zavahealth/zavahospital/nvidianim/SKILL.md
What it does
NVIDIA NIM on AKS with GPU — vector embeddings and chat completions from SQL Server 2025 T-SQL using GPU-accelerated inference. Use when: deploying NIM containers on AKS, creating AKS GPU node pools, testing NIM endpoints, creating external models for NIM embeddings, Azure Local edge AI pattern, working in nvidianim/.
Skill instructions
NVIDIA NIM + AKS + SQL Server 2025 Demo Architecture - AKS cluster in westus2 with 2x NC4asT4v3 GPU nodes (1x NVIDIA T4 16GB each) - NIM chat: meta/llama-3.2-3b-instruct on dedicated T4 - NIM embeddings: nvidia/nv-embedqa-e5-v5 (1024 dims) on dedicated T4 - SQL Server 2025 localhost, Windows auth, FoundryLocalTest database - TLS: Self-signed cert (CN=nim-aks.local) via AKS Web Application Routing (managed NGINX ingress) - Hostname: nim-aks.local via Windows hosts file → AKS ingress IP (get with kubectl get ingress -n nim) - Content-Type fix: NGINX annotation proxysetheader Content-Type "application/json" strips charset suffix that NIM rejects - NGC API key required to pull NIM containers from nvcr.io Flow SQL Server 2025 → HTTPS → AKS Ingress (TLS termination) → HTTP → NIM pods (port 8000) Setup Sequence 1. Create AKS cluster: .\create-aks-cluster.ps1 2. Deploy NIM containers: .\deploy-nim.ps1 (requires $env:NGCAPIKEY) 3. Wait for pods + ingress ready 4. Switch to local hostname: .\swi
Explore related resources
Frequently asked questions
What is nvidianim?
nvidianim is a open-source AI agent skill with Copy skill directory. NVIDIA NIM on AKS with GPU — vector embeddings and chat completions from SQL Server 2025 T-SQL using GPU-accelerated inference.
Who is nvidianim best for?
nvidianim is best for reusing agent instructions, scripts, and references, testing workflows, database workflows, deployment workflows.
How do I install nvidianim?
Install or run nvidianim using Copy skill directory. Check nvidianim for the latest setup command.
Is nvidianim actively maintained?
nvidianim may need a closer maintenance check before production use.
Auto-fetched from GitHub.
