Dev -> Main

.gitignore

@@ -183,7 +183,7 @@ deploy/helm/secrets
 # RAG Stack Configuration
 # User-specific configuration file (contains sensitive data)
 deploy/helm/rag-values.yaml
-deploy/helm/rag/Chart.lock
 deploy/helm/values.yaml
 deploy/helm/bootstrap-values.yaml
 tenant/bootstrap/bootstrap-values.yaml
+tenant/bootstrap-values.yaml

deploy/helm/rag/Chart.lock

@@ -10,12 +10,12 @@ dependencies:
   version: 0.5.6
 - name: ingestion-pipeline
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
-  version: 0.7.0
+  version: 0.7.3
 - name: llama-stack
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
-  version: 0.7.1
+  version: 0.7.3
 - name: mcp-servers
   repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
   version: 0.5.15
-digest: sha256:0dbca435d7b3b408321cb33489ad8f099b4ae64501cde761cb47ea9c8e0abc20
-generated: "2026-03-06T14:32:40.986363-05:00"
+digest: sha256:ac4d12af3cc62bd462293d89f20fbe01a7c67fd7ce50ab78a1fe0ff27dfebb55
+generated: "2026-03-16T16:48:25.929533-04:00"

deploy/helm/rag/Chart.yaml

@@ -19,11 +19,11 @@ dependencies:
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: configure-pipeline.enabled
   - name: ingestion-pipeline
-    version: 0.7.0
+    version: 0.7.3
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: ingestion-pipeline.enabled
   - name: llama-stack
-    version: 0.7.1
+    version: 0.7.3
     repository: https://rh-ai-quickstart.github.io/ai-architecture-charts
     condition: llama-stack.enabled
   - name: mcp-servers

deploy/local/Makefile

@@ -19,7 +19,7 @@ PROJECT_NAME := rag
 OLLAMA_MODEL := llama3.2:3b-instruct-fp16
 
 # UI Build Configuration
-VERSION ?= 0.5.1
+VERSION ?= 0.6.0
 TAVILY_SEARCH_API_KEY ?= ""
 CONTAINER_REGISTRY ?= quay.io/rh-ai-quickstart
 DIST_UI_DIR := $(abspath ../../frontend)

frontend/llama_stack_ui/distribution/ui/page/playground/agent.py

@@ -363,8 +363,7 @@ def agent_process_prompt(prompt, state, config):
         "temperature": config.sampling.temperature,
         "max_infer_iters": config.sampling.max_infer_iters,
         "stream": True,
-       # "max_output_tokens": config.sampling.max_tokens,
-
+        "max_output_tokens": config.sampling.max_tokens,
     }
 
     # Add tools if available

frontend/pyproject.toml

@@ -10,10 +10,10 @@ requires-python = ">=3.12"
 dependencies = [
     "streamlit",
     "pandas",
-	"llama-stack-client==0.5.1",
+	"llama-stack-client==0.6.0",
     "requests",
     "streamlit-option-menu",
-    "llama-stack==0.5.1",
+    "llama-stack==0.6.0",
     "fire",
     "asyncpg",
 ]