made multiple fixes to the AI PODs workshop

Author: dmitchsplunk

content/en/ninja-workshops/14-cisco-ai-pods/6-deploy-llm.md

@@ -61,6 +61,14 @@ Let's create a new namespace:
 oc create namespace weaviate
 ```
 
+Run the following command to allow Weaviate to run a privileged container:
+
+> Note: this approach is not recommended for production 
+
+``` bash
+oc adm policy add-scc-to-user privileged -z default -n weaviate
+```
+
 Then deploy Weaviate: 
 
 ``` bash
@@ -196,7 +204,7 @@ A job is used rather than a pod to ensure that this process runs only once:
 
 ``` bash
 oc create namespace llm-app
-oc apply -f k8s-job.yaml
+oc apply -f ./load-embeddings/k8s-job.yaml
 ```
 
 > Note: to build a Docker image for the Python application that loads the embeddings 

content/en/ninja-workshops/14-cisco-ai-pods/8-deploy-vector-db.md

@@ -43,7 +43,7 @@ Then run the following command to send a question to the LLM:
 
 ``` bash
 curl -X "POST" \
- 'http://llm-app.llm-app:8080/askquestion"' \
+ 'http://llm-app.llm-app.svc.cluster.local:8080/askquestion' \
   -H 'Accept: application/json' \
   -H 'Content-Type: application/json' \
   -d '{
@@ -55,7 +55,7 @@ curl -X "POST" \
 {{% tab title="Example Output" %}}
 
 ``` bash
-TBD
+The NVIDIA H200 graphics card has 5536 MB of GDDR6 memory.
 ```
 
 {{% /tab %}}

content/en/ninja-workshops/14-cisco-ai-pods/9-deploy-llm-app.md

@@ -3,6 +3,7 @@
 import openlit
 
 from flask import Flask, request
+from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings
 from langchain_nvidia_ai_endpoints import ChatNVIDIA
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.runnables import RunnablePassthrough
@@ -29,7 +30,7 @@
         "You are a helpful and friendly AI!"
         "Your responses should be concise and no longer than two sentences."
         "Do not hallucinate. Say you don't know if you don't have this information."
-        # "Answer the question using only the context"
+        "Answer the question using only the context"
         "\n\nQuestion: {question}\n\nContext: {context}"
     ),
     ("user", "{question}")
@@ -52,9 +53,11 @@ def ask_question():
     )
 
     # connect with the vector store that was populated earlier
-    vector_store = Weaviate(
+    vector_store = WeaviateVectorStore(
         client=weaviate_client,
-        embedding=embeddings_model
+        embedding=embeddings_model,
+        index_name=None,
+        text_key="text"
     )
 
     chain = (

workshop/cisco-ai-pods/llm-app/app.py

@@ -46,11 +46,11 @@ spec:
             - name: EMBEDDINGS_MODEL_URL
               value: "http://llama-32-nv-embedqa-1b-v2.nim-service:8000/v1"
             - name: WEAVIATE_HTTP_HOST
-              value: "weaviate.weaviate.svc.cluster.local"
+              value: "weaviate-headless.weaviate.svc.cluster.local"
             - name: WEAVIATE_HTTP_PORT
-              value: "80"
+              value: "8080"
             - name: WEAVIATE_GRPC_HOST
-              value: "weaviate.weaviate.svc.cluster.local"
+              value: "weaviate-headless.weaviate.svc.cluster.local"
             - name: WEAVIATE_GRPC_PORT
               value: "50051"
           resources: {}

workshop/cisco-ai-pods/llm-app/k8s-manifest.yaml

@@ -17,11 +17,11 @@ spec:
             - name: EMBEDDINGS_MODEL_URL
               value: "http://llama-32-nv-embedqa-1b-v2.nim-service:8000/v1"
             - name: WEAVIATE_HTTP_HOST
-              value: "weaviate.weaviate.svc.cluster.local"
+              value: "weaviate-headless.weaviate.svc.cluster.local"
             - name: WEAVIATE_HTTP_PORT
-              value: "80"
+              value: "8080"
             - name: WEAVIATE_GRPC_HOST
-              value: "weaviate.weaviate.svc.cluster.local"
+              value: "weaviate-headless.weaviate.svc.cluster.local"
             - name: WEAVIATE_GRPC_PORT
               value: "50051"
       restartPolicy: Never # Ensure the job only runs once

workshop/cisco-ai-pods/load-embeddings/k8s-job.yaml

@@ -1,5 +1,5 @@
 #!/bin/bash
 
-oc get csv -n nvidia-gpu-operator gpu-operator-certified.v25.3.0 -ojsonpath={.metadata.annotations.alm-examples} | jq .[0] > clusterpolicy.json
+oc get csv -n nvidia-gpu-operator gpu-operator-certified.v25.3.4 -ojsonpath={.metadata.annotations.alm-examples} | jq .[0] > clusterpolicy.json
 oc apply -f clusterpolicy.json