OpenTech use ibm/granite4 instead of granite4

docs/opentech/agentstack/pre-work/README.md

@@ -35,13 +35,13 @@ To run models locally on your machine:
 2. Run or pull the Granite model:
 
    ```bash
-   ollama pull granite4:micro-h
+   ollama pull ibm/granite4:micro-h
    ```
 
    or
 
    ```bash
-   ollama run granite4:micro-h
+   ollama run ibm/granite4:micro-h
    ```
 
 ### Granite model links

docs/opentech/agentstack/run/README.md

@@ -62,7 +62,7 @@ agentstack ui
 ```
 
 You should be prompted to select a model provider and model if you did not already set these.
-For this lab, use Ollama and granite4:micro-h. for the language model.
+For this lab, use Ollama and `ibm/granite4:micro-h` for the language model.
 
 You should see the UI launch in your browser.
 

docs/opentech/beeaiframework/prework/README.md

@@ -21,15 +21,15 @@ Most users can simply download from the Ollama [website](https://ollama.com/down
 Please pull the models to be used in the workshop before arriving at the workshop!
 
 ```shell
-ollama pull granite4:micro-h
+ollama pull ibm/granite4:micro-h
 ```
 
 ## Chat with the model
 
 For a quick test, you can use the ollama CLI to ask the model a question.
 
 ```shell
-ollama run granite4:micro-h "what model am I chatting with and and who created you?"  
+ollama run ibm/granite4:micro-h "what model am I chatting with and and who created you?"  
 ```
 
 ## Install `uv`

docs/opentech/llm/lab-1/README.md

@@ -39,7 +39,7 @@ If you see something similar, Open-WebUI is installed correctly! Continue on, if
 
 Click *Getting Started*. Fill out the next screen and click the *Create Admin Account*. This will be your login for your local machine. Remember that this because it will be your Open-WebUI configuration login information if want to dig deeper into it after this workshop.
 
-You should see the Open-WebUI main page now, with `granite4:micro-h` right there in the center!
+You should see the Open-WebUI main page now, with `ibm/granite4:micro-h` right there in the center!
 
 ![main screen](../images/openwebui_main_screen.png)
 

docs/opentech/llm/lab-2/README.md

@@ -33,16 +33,16 @@ ollama list
 
 And you'll see a list similar to the following:
 
-```text
-ollama list
+```console
+$ ollama list
 NAME                         ID              SIZE      MODIFIED           
-granite4:micro-h             ba791654cc27    1.9 GB    23 hours ago
+ibm/granite4:micro-h         076afb3855dc    1.9 GB    About a minute ago
 ```
 
 Next, use Ollama to run one of the models:
 
 ```shell
-ollama run granite4:micro-h
+ollama run ibm/granite4:micro-h
 ```
 
 And ask it questions, like this:

docs/opentech/llm/lab-5/README.md

@@ -22,14 +22,14 @@ Open up [Open-WebUI](http://localhost:8080/), and you should see something like
 If you see this that means Open-WebUI is installed correctly, and we can continue configuration, if not, please find a workshop TA or
 raise your hand we'll be there to help you ASAP.
 
-Next as a sanity check, run the following command to confirm you have the [granite4:micro-h](https://ollama.com/library/granite4:micro-h)
+Next as a sanity check, run the following command to confirm you have the [ibm/granite4:micro-h](https://ollama.com/ibm/granite4:micro-h)
 model downloaded in `ollama`. This may take a bit, but we should have a way to copy it directly on your laptop.
 
 ```shell
-ollama pull granite4:micro-h
+ollama pull ibm/granite4:micro-h
 ```
 
-If you didn't know, the supported languages with `granite4:micro-h` now include:
+If you didn't know, the supported languages with `ibm/granite4:micro-h` now include:
 
 - English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. However, users may fine-tune this Granite model for languages beyond these 12 languages.
 
@@ -45,7 +45,7 @@ And the Capabilities also include:
 - Multilingual dialog use cases
 - Fill-In-the-Middle (FIM) code completions
 
-Next click on the down arrow at the top and select the "granite4:micro-h" if it's not already selected.
+Next click on the down arrow at the top and select the "ibm/granite4:micro-h" if it's not already selected.
 
 ![model selection](../images/openwebui_model_selection.png)
 

docs/opentech/llm/pre-work/README.md

@@ -38,15 +38,15 @@ Most users can simply download from the Ollama [website](https://ollama.com/down
 Please pull the models to be used in the workshop before arriving at the workshop!
 
 ```shell
-ollama pull granite4:micro-h
+ollama pull ibm/granite4:micro-h
 ```
 
 ## Chat with the model
 
 For a quick test, you can use the ollama CLI to ask the model a question.
 
 ```shell
-ollama run granite4:micro-h "what model am I chatting with and and who created you?"  
+ollama run ibm/granite4:micro-h "what model am I chatting with and and who created you?"  
 ```
 
 ## Install Open WebUI

docs/opentech/mellea/pre-work/README.md

@@ -37,13 +37,13 @@ Most users can simply download from the Ollama [website](https://ollama.com/down
 Please pull the models to be used in the workshop before arriving at the workshop!
 
 ```shell
-ollama pull granite4:micro-h
+ollama pull ibm/granite4:micro-h
 ```
 
 ## Chat with the model
 
 For a quick test, you can use the ollama CLI to ask the model a question.
 
 ```shell
-ollama run granite4:micro-h "what model am I chatting with and and who created you?"  
+ollama run ibm/granite4:micro-h "what model am I chatting with and and who created you?"  
 ```

opentech/agentstack/src/agent.py

@@ -84,7 +84,7 @@
 # Try several models to see how your agent performs. Note that you may need to modify the system prompt for each model, as they all have their own system prompt best practice.
 
 PROVIDER_ID = os.getenv("PROVIDER_ID", "ollama")
-MODEL_ID = os.getenv("MODEL_ID", "granite4:micro-h")
+MODEL_ID = os.getenv("MODEL_ID", "ibm/granite4:micro-h")
 MODEL_NAME = ":".join([PROVIDER_ID, MODEL_ID]) if PROVIDER_ID and MODEL_ID else None
 
 # Load the chat model

opentech/beeaiframework/notebooks/beeai.ipynb

@@ -171,50 +171,14 @@
    },
    "source": [
     "### *❗* Exercise: Select your Language Model Provider\n",
-    "\n",
+    "/\n",
     "Change the `provider` and `model` variables to your desired provider and model.\n",
     "\n",
     "If you select a provider that requires an API key URL or Project_ID, select the key icon on the left menu and set the variables to match those in the userdata.get() function.\n",
     "\n",
     "Try several models to see how your agent performs. Note that you may need to modify the system prompt for each model, as they all have their own system prompt best practice."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "YdDRJpoPhvrz"
-   },
-   "outputs": [],
-   "source": [
-    "load_dotenv()\n",
-    "\n",
-    "provider=\"ollama\"\n",
-    "\n",
-    "# Ollama - No parameters required\n",
-    "if provider==\"ollama\":\n",
-    "    model=\"granite4:micro-h\"  # model=\"granite4:tiny-h\"\n",
-    "    provider_model=provider+\":\"+model\n",
-    "    llm=ChatModel.from_name(provider_model, ChatModelParameters(temperature=0))\n",
-    "\n",
-    "# OpenAI - Place OpenAI API Key in Colab Secrets (key icon) as OPENAI_KEY\n",
-    "elif provider==\"openai\":\n",
-    "    model=\"gpt-5-mini\"\n",
-    "    provider_model=provider+\":\"+model\n",
-    "    api_key = userdata.get('OPENAI_KEY')             #Set secret value using key in left menu\n",
-    "    llm=ChatModel.from_name(provider_model, ChatModelParameters(temperature=1), api_key=api_key)\n",
-    "# WatsonX - Place Project ID, API Key and WatsonX URL in Colab Secrets (key icon)\n",
-    "elif provider==\"watsonx\":\n",
-    "    model=\"ibm/granite-3-8b-instruct\"\n",
-    "    provider_model=provider+\":\"+model\n",
-    "    project_id = userdata.get('WATSONX_PROJECT_ID')  #Set secret value using key in left menu\n",
-    "    api_key = userdata.get('WATSONX_APIKEY')         #Set secret value using key in left menu\n",
-    "    base_url = userdata.get('WATSONX_URL')           #Set secret value using key in left menu\n",
-    "    llm=ChatModel.from_name(provider_model, ChatModelParameters(temperature=0), project_id=project_id, api_key=api_key, base_url=base_url)\n",
-    "else:\n",
-    "  print(\"Provider \" + provider + \" undefined\")"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -252,6 +216,42 @@
     "Try modifying the system prompt. Customize the \"basic rules\" section to add your own. Note that changes to the system prompt will affect the performance of the model. Creating a great `System Prompt` is an art, not a science."
    ]
   },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "load_dotenv()\n",
+    "\n",
+    "provider=\"ollama\"\n",
+    "\n",
+    "# Ollama - No parameters required\n",
+    "if provider==\"ollama\":\n",
+    "    model=\"ibm/granite4:micro-h\"  # model=\"ibm/granite4:tiny-h\"\n",
+    "    provider_model=provider+\":\"+model\n",
+    "    llm=ChatModel.from_name(provider_model, ChatModelParameters(temperature=0))\n",
+    "\n",
+    "# OpenAI - Place OpenAI API Key in Colab Secrets (key icon) as OPENAI_KEY\n",
+    "elif provider==\"openai\":\n",
+    "    model=\"gpt-5-mini\"\n",
+    "    provider_model=provider+\":\"+model\n",
+    "    api_key = userdata.get('OPENAI_KEY')             #Set secret value using key in left menu\n",
+    "    llm=ChatModel.from_name(provider_model, ChatModelParameters(temperature=1), api_key=api_key)\n",
+    "# WatsonX - Place Project ID, API Key and WatsonX URL in Colab Secrets (key icon)\n",
+    "elif provider==\"watsonx\":\n",
+    "    model=\"ibm/granite-3-8b-instruct\"\n",
+    "    provider_model=provider+\":\"+model\n",
+    "    project_id = userdata.get('WATSONX_PROJECT_ID')  #Set secret value using key in left menu\n",
+    "    api_key = userdata.get('WATSONX_APIKEY')         #Set secret value using key in left menu\n",
+    "    base_url = userdata.get('WATSONX_URL')           #Set secret value using key in left menu\n",
+    "    llm=ChatModel.from_name(provider_model, ChatModelParameters(temperature=0), project_id=project_id, api_key=api_key, base_url=base_url)\n",
+    "else:\n",
+    "  print(\"Provider \" + provider + \" undefined\")"
+   ],
+   "metadata": {
+    "id": "YdDRJpoPhvrz"
+   },
+   "execution_count": 0
+  },
   {
    "cell_type": "code",
    "execution_count": null,