Merge pull request #179 from rh-ai-quickstart/release/v0.2.42

Release v0.2.42

Author: sauagarwa

README.md

@@ -100,18 +100,6 @@ This QuickStart allows users to explore the capabilities of RAG by:
 | Generation  | `meta-llama/Meta-Llama-3-70B-Instruct` | A100 x2/HPU | p4d.24xlarge
 | Safety      | `meta-llama/Llama-Guard-3-8B`          | L4/HPU      | g6.2xlarge
 
-- Note: Developers can also use a remote LLM via the command line (see [Remote LLM Deployment](#remote-llm-deployment-example)) or by modifying the `rag-values.yaml` file directly:
-
-```yaml
-  global:
-    models:
-      remote-llm:
-        id: meta-llama/Llama-3.3-70B-Instruct
-        url: https://somedomain.com/v1
-        apiToken: fake-token
-        enabled: true
-```
-
 Note: the 70B model is NOT required for initial testing of this example. The safety/shield model `Llama-Guard-3-8B` is also optional.
 
 ### Installation Steps
@@ -250,7 +238,6 @@ make install NAMESPACE=llama-stack-rag LLM=llama-3-2-3b-instruct SAFETY=llama-gu
 
 # Xeon deployment
 make install NAMESPACE=llama-stack-rag LLM=llama-3-2-3b-instruct SAFETY=llama-guard-3-8b DEVICE=xeon
-
 ```
 
 **Remote LLM Deployment Example:**
@@ -259,23 +246,36 @@ To connect to a remote LLM endpoint instead of deploying a local model, use `LLM
 
 ```bash
 make install NAMESPACE=llama-stack-rag \
-  LLM=remote-llm \
+  LLM=remotellm \
   LLM_URL=https://my-model-endpoint.example.com/v1 \
-  LLM_API_TOKEN=my-api-token
+  LLM_API_TOKEN=my-api-token \
+  LLM_ID=llm_model_id
 ```
-
 | Parameter | Description |
 |-----------|-------------|
-| `LLM=remote-llm` | Indicates a remote model (no local vLLM deployment) |
+| `LLM=remotellm` | Indicates a remote model (no local vLLM deployment) |
 | `LLM_URL` | The base URL of the remote model endpoint |
 | `LLM_API_TOKEN` | Authentication token for the remote endpoint |
+| `LLM_ID` | The model of the llm you wish to use |
 
 This skips local model deployment and configures LlamaStack to use the remote inference endpoint directly. No GPU or HF token is required for the LLM.
 
 When prompted, enter your **[Hugging Face Token](https://huggingface.co/settings/tokens)**.
 
 Note: This process may take 10 to 30 minutes depending on the number and size of models to be downloaded.
 
+- Note: Developers can also use a remote LLM via the helm chart (see [Remote LLM Deployment](#remote-llm-deployment-example)) or by modifying the `rag-values.yaml` file directly:
+
+```yaml
+  global:
+    models:
+      remotellm:
+        id: meta-llama/Llama-3.3-70B-Instruct
+        url: https://llm-gateway.com/v1
+        apiToken: api-token
+        enabled: true
+```
+
 7. **Monitor Deployment**
 
 ```bash

deploy/helm/Makefile

@@ -270,7 +270,7 @@ help: ## Show this help message
 	@echo -e "    make install NAMESPACE=my-rag LLM=llama-3-2-3b-instruct LLM_TOLERATION=\"nvidia.com/gpu\""
 	@echo -e ""
 	@echo -e "  $(BLUE)Option 3:$(NC) Using command-line parameters with remote LLM"
-	@echo -e "    make install NAMESPACE=my-rag LLM=remote-llm LLM_URL=https://<<llm-url>>/v1 LLM_API_TOKEN=<<llm-api-token>>"
+	@echo -e "    make install NAMESPACE=my-rag LLM=remotellm LLM_URL=https://<<llm-url>>/v1 LLM_API_TOKEN=<<llm-api-token>>"
 
 # Dependency checks
 .PHONY: check-deps

deploy/helm/rag-values.yaml.example

@@ -103,7 +103,7 @@ global:
     # To configure LlamaStack with remote llm, replace the id,
     # url and apiToken value and set enabled to true
 
-    # remote-llm:
+    # remotellm:
     #   id: custom-model-id
     #   url: https://custom-server-url/v1
     #   apiToken: fake-token

deploy/helm/rag/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: rag
 description: A Helm chart for Kubernetes
 type: application
-version: 0.2.41
-appVersion: "0.2.41"
+version: 0.2.42
+appVersion: "0.2.42"
 
 dependencies:
   - name: pgvector

deploy/helm/rag/values.yaml

@@ -3,7 +3,7 @@ replicaCount: 1
 image:
   repository: quay.io/rh-ai-quickstart/llamastack-dist-ui
   pullPolicy: Always
-  tag: 0.2.41
+  tag: 0.2.42
 
 service:
   type: ClusterIP