NIM service

Accelerate Your AI Deployment With NVIDIA NIM Microservices

Part of NVIDIA AI Enterprise, NVIDIA NIM microservices are a set of easy-to-use microservices for accelerating the deployment of foundation models on any cloud or data center and helps keep your data secure. NIM microservices have production-grade runtimes including on-going security updates. Run your business applications with stable APIs backed by enterprise-grade support.

for more information check out this link:
https://docs.nvidia.com/nim/index.html

• NVIDIA has a NIM service which can run anywhere and is compatible with any AI (which is allowed by them)

  • An example of how to use this service

    • https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-8b
      

    • https://build.nvidia.com/deepseek-ai/deepseek-r1

In this Service via a Service Action named NIM_SA, this action calls the NVIDIA Chat PostCompletion API which contains the following request and response structures:

• Request: PostComplestionsRequest structure
  
• Response: PostCompletionsResponse structure.
  
  
  

Here are a few tips you help to with the integration and testing.

1) You need a Bearer Token which you can get from NVIDIA.

Can sign up via these links
https://build.nvidia.com/meta/llama-3_1-8b-instruct?signin=true&integrate_nim=true
or here 
https://build.nvidia.com/deepseek-ai/deepseek-r1?signin=true&integrate_nim=true

- If you wish to play around first with the meta llama model via NVIDIA check out this link https://build.nvidia.com/meta/llama-3_1-8b-instruct

- More information about the Meta llama model and the NVIDIA API:

See https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-8b-infer

2) Once you get your API Key from NVIDIA, you can follow the following steps:

• You can either configure it like as a site property (or save it in an Entity)

  • Go to the Data tab 

    • Right-click on the site property folder

      • 

    • Create a Site Property and call it API_Key in the component, 
      you need to access the module Meta_Nvidia_AI, you can add a default value here
      if you wish.

    • Go to the OnBeforeRequest of the NVIDIA API method and click on 
      ListAppend_Header_Auth_API_Key

      • Afterwards, set the Value of your Authorization header to 

        • “Bearer “+Site.API_Key

          • And yes, there is a space after the word Bearer. Be aware of this.

          • 
            

      • The best practice would be to use a site property, 
        set as a secret and edit the site properties value in the Service Center.

Check out this link as well as another example on how to use this service https://www.outsystems.com/forge/component-overview/19584/meta-nvidia-ai-o11