Update NOTES.txt to improve Azimuth UI help text

charts/azimuth-chat/templates/NOTES.txt

@@ -0,0 +1,14 @@
+The LLM chatbot app allows users to deploy machine learning models from [HuggingFace](https://huggingface.co/models) and interact with them through a simple web interface.
+The models can also be interacted with via OpenAI API by other applications running on the same Kubernetes cluster using the in-cluster API address `http://{{ .Release.Name }}.{{ .Release.Namespace }}.svc` - see [here](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html) for available API endpoints.
+
+The target Kubernetes cluster must have a GPU worker node group configured, otherwise the app will remain in an 'Installing' state until a GPU node becomes available for scheduling.
+
+On deployment of a new model, the app must first download the model's weights from HuggingFace.
+This can take a significant amount of time depending on model choice and network speeds.
+Download progress can be monitored by inspecting the logs for the LLM API pod(s) via the Kubernetes Dashboard for the target cluster.
+
+The app uses [vLLM](https://docs.vllm.ai/en/latest/) as a model serving backend and [Gradio](https://github.com/gradio-app/gradio) + [LangChain](https://python.langchain.com/docs/get_started/introduction) to provide the web interface.
+
+The official list of HuggingFace models supported by vLLM can be found [here](https://docs.vllm.ai/en/latest/models/supported_models.html), though some of these may not be compatible with the LangChain prompt format.
+
+Release notes for the application can be found at https://github.com/stackhpc/azimuth-llm/releases

charts/azimuth-image-analysis/templates/NOTES.txt

@@ -0,0 +1,14 @@
+The LLM image analysis app allows users to deploy machine learning models from [HuggingFace](https://huggingface.co/models) and interact with them through a simple web interface.
+The models can also be interacted with via OpenAI API by other applications running on the same Kubernetes cluster using the in-cluster API address `http://{{ .Release.Name }}.{{ .Release.Namespace }}.svc` - see [here](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html) for available API endpoints.
+
+The target Kubernetes cluster must have a GPU worker node group configured, otherwise the app will remain in an 'Installing' state until a GPU node becomes available for scheduling.
+
+On deployment of a new model, the app must first download the model's weights from HuggingFace.
+This can take a significant amount of time depending on model choice and network speeds.
+Download progress can be monitored by inspecting the logs for the LLM API pod(s) via the Kubernetes Dashboard for the target cluster.
+
+The app uses [vLLM](https://docs.vllm.ai/en/latest/) as a model serving backend and [Gradio](https://github.com/gradio-app/gradio) to provide the web interface.
+
+The official list of HuggingFace models supported by vLLM can be found [here](https://docs.vllm.ai/en/latest/models/supported_models.html), though some of these may not be compatible with the LangChain prompt format.
+
+Release notes for the application can be found at https://github.com/stackhpc/azimuth-llm/releases

charts/azimuth-llm/templates/NOTES.txt

@@ -1,4 +1,5 @@
 The LLM chatbot app allows users to deploy machine learning models from [HuggingFace](https://huggingface.co/models) and interact with them through a simple web interface.
+The models can also be interacted with via OpenAI API by other applications running on the same Kubernetes cluster using the in-cluster API address `http://{{ .Release.Name }}.{{ .Release.Namespace }}.svc` - see [here](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html) for available API endpoints.
 
 The target Kubernetes cluster must have a GPU worker node group configured, otherwise the app will remain in an 'Installing' state until a GPU node becomes available for scheduling.
 
@@ -7,5 +8,7 @@ This can take a significant amount of time depending on model choice and network
 Download progress can be monitored by inspecting the logs for the LLM API pod(s) via the Kubernetes Dashboard for the target cluster.
 
 The app uses [vLLM](https://docs.vllm.ai/en/latest/) as a model serving backend and [Gradio](https://github.com/gradio-app/gradio) + [LangChain](https://python.langchain.com/docs/get_started/introduction) to provide the web interface.
+
 The official list of HuggingFace models supported by vLLM can be found [here](https://docs.vllm.ai/en/latest/models/supported_models.html), though some of these may not be compatible with the LangChain prompt format.
-See [this documentation](https://github.com/stackhpc/azimuth-llm/) for a non-exhaustive list of languange models against which the app has been tested.
+
+Release notes for the application can be found at https://github.com/stackhpc/azimuth-llm/releases