diff --git a/genai/README.md b/genai/README.md index 7d7f2eb..8d4036b 100644 --- a/genai/README.md +++ b/genai/README.md @@ -4,7 +4,8 @@ In this lab, we will go through LLM Chatbot AMP using Cloudera Machine Learning 1. On login, you will be taken to Trials Home Page 2. Click, **Start Trial** go to your Machine Learning Workspace -3. [Here](https://app.getreprise.com/launch/MXxjDe6/) is the Reprise demo with step by step tutorial for the LLM Chatbot +3. [Here](https://app.getreprise.com/launch/MXxjDe6/) is the Reprise demo with step by step tutorial for the LLM Chatbot +4. [Here](https://app.getreprise.com/launch/dyR7W26/) is the Reprise demo showcasing Cloudera AI Inference capabilities. [Here](https://github.com/cloudera/CML_AMP_LLM_Chatbot_Augmented_with_Enterprise_Data) is more detailed information of the LLM Chatbot diff --git a/genai/clouderaAIInferenceService.md b/genai/clouderaAIInferenceService.md new file mode 100644 index 0000000..28ac881 --- /dev/null +++ b/genai/clouderaAIInferenceService.md @@ -0,0 +1,14 @@ +# Cloudera AI Inference service + +[Here](https://app.getreprise.com/launch/dyR7W26/) is an interactive Reprise demo showcasing Cloudera AI Inference capabilities. + +In this lab, you'll explore how to leverage Cloudera's AI Inference service for enterprise-grade LLM deployment. The demo walks you through: + +1. Navigating the Model Hub to discover and select pre-optimized LLMs +2. Deploying a selected model in a secure, private environment using the AI Inference service +3. Configuring deployment settings for optimal performance and resource utilization +4. Connecting the deployed model to your AI Applications through standard APIs +5. Testing the model with sample queries to demonstrate performance and accuracy +6. Monitoring inference metrics and scaling resources as needed + +This demo highlights how Cloudera AI simplifies the process of bringing powerful LLMs into your production environment with enterprise-grade security, governance, and performance. \ No newline at end of file