NVIDIA AI Foundation lets developers to experience state of the art LLMs accelerated by NVIDIA. Developers get free credits for 10K requests to any of the available models.
-
Navigate to https://catalog.ngc.nvidia.com/ai-foundation-models.
-
Find the Mixtral x7B model icon and click
Learn More
.
- Select the
API
navigation bar and click on theGenerate key
option..
- Save the generated API key.
- Clone the Generative AI examples Git repository.
⚠️ NOTE: This example requires Git Large File Support (LFS)
$ sudo apt -y install git-lfs
$ git clone git@github.com:NVIDIA/GenerativeAIExamples.git
Cloning into 'GenerativeAIExamples'...
$ cd GenerativeAIExamples/
$ git lfs pull
- Add your NGC API key to compose.env to use the NVIDIA endpoint.
$ cd GenerativeAIExamples
$ grep NVIDIA_API_KEY deploy/compose/compose.env
export NVIDIA_API_KEY="nvapi-*"
- Set the nv-ai-foundation example in compose.env.
export RAG_EXAMPLE="nvidia_ai_foundation"
- Deploy the developer RAG example via Docker compose.
$ source deploy/compose/compose.env ; docker compose -f deploy/compose/docker-compose-nv-ai-foundation.yaml build
$ docker compose -f deploy/compose/docker-compose-nv-ai-foundation.yaml up -d
$ docker ps --format "table {{.ID}}\t{{.Names}}\t{{.Status}}"
CONTAINER ID NAMES STATUS
70ef27ae4c91 llm-playground Up 56 seconds
4aacfbe89464 chain-server Up 56 seconds
- Follow steps 1 - 5 in the "Test" section of example 02.