Update Blog “build-your-first-ai-chatbot-on-hpe-private-cloud-ai-using-flowise-and-hpe-mlis”

Author: santosh-hpe

content/blog/build-your-first-ai-chatbot-on-hpe-private-cloud-ai-using-flowise-and-hpe-mlis.md

@@ -17,7 +17,7 @@ This blog post walks you through deploying Flowise on HPE PCAI to build a modern
 
 ## HPE Private Cloud AI
 
-[HPE Private Cloud AI (HPE PCAI)](https://developer.hpe.com/platform/hpe-private-cloud-ai/home/) offers a comprehensive, turnkey AI solution designed to address key enterprise challenges, from selecting the appropriate large language models (LLMs) to efficiently hosting and deploying them. Beyond these core functions, HPE PCAI empowers organizations to take full control of their AI adoption journey by offering a curated set of pre-integrated *NVIDIA NIM* LLMs, along with a powerful suite of AI tools and frameworks for *Data Engineering*, *Analytics*, and *Data Science*.
+[HPE Private Cloud AI (HPE PCAI)](https://developer.hpe.com/platform/hpe-private-cloud-ai/home/) offers a comprehensive, turnkey AI solution designed to address key enterprise challenges, from selecting the appropriate large language models (LLMs) to efficiently hosting and deploying them. Beyond these core functions, HPE PCAI empowers organizations to take full control of their AI adoption journey by offering a curated set of pre-integrated *NVIDIA Inference Microservices (NIM)* LLMs, along with a powerful suite of AI tools and frameworks for *Data Engineering*, *Analytics*, and *Data Science*.
 
 HPE Machine Learning Inference Software is a user-friendly solution designed to simplify and control the deployment, management, and monitoring of machine learning (ML) models, including LLMs, at any scale.
 
@@ -87,18 +87,14 @@ HPE MLIS is accessed by clicking on 'HPE MLIS' tile in *Tools & Frameworks / Dat
 
 ![](/img/mlis.jpg)
 
-To deploy a pre-packaged LLM(Meta/Llama3-8b-instruct) in HPE MLIS, Add 'Registry', 'Packaged models' and create 'Deployments'. 
-
-
+To deploy a pre-packaged LLM (Meta/Llama3-8b-instruct) in HPE MLIS, Add 'Registry', 'Packaged models' and create 'Deployments'. 
 
 ### 1. Add 'Registry'
 
-Add a new registry of type 'NGC', which can be used to access pre-packaged LLMs. 
+Add a new registry of type 'NVIDIA GPU Cloud' (NGC), which can be used to access pre-packaged LLMs. 
 
 ![](/img/mlis-registry.jpg)
 
-
-
 ### 2. Add 'Packaged Model'
 
 Create a new Packaged Model by clicking 'Add new model' tab, and fill-in the details as shown in screen shots. 
@@ -119,8 +115,6 @@ Newly created packaged model appears in the UI.
 
 ![](/img/package-model-final.jpg)
 
-
-
 ### 3. Create 'Deployment'
 
 Using the 'packaged Model' created in previous step, create a new deployment by clicking on 'Create new deployment'
@@ -143,8 +137,6 @@ The LLM is now deployed and can be accessed using the 'Endpoint', and correspond
 
 ![](/img/deployment-6.jpg)
 
-
-
 ## Create AI Chatbot in Flowise
 
 Use Flowise's drag-and-drop interface to design your chatbot’s conversational flow. Integrate with HPE MLIS by adding an LLM node and configuring it to use the MLIS inference endpoint.