IBM · markstur · Nov 20, 2025 · Nov 19, 2025
diff --git a/docs/opentech/llm/images/History_of_IBM_summary.png b/docs/opentech/llm/images/History_of_IBM_summary.png
diff --git a/docs/opentech/llm/images/ceo_list_with_rag.png b/docs/opentech/llm/images/ceo_list_with_rag.png
diff --git a/docs/opentech/llm/images/openwebui_main_screen.png b/docs/opentech/llm/images/openwebui_main_screen.png
diff --git a/docs/opentech/llm/images/openwebui_model_selection.png b/docs/opentech/llm/images/openwebui_model_selection.png
diff --git a/docs/opentech/llm/images/openwebui_open_screen.png b/docs/opentech/llm/images/openwebui_open_screen.png
diff --git a/docs/opentech/llm/images/openwebui_rag_source.png b/docs/opentech/llm/images/openwebui_rag_source.png
diff --git a/docs/opentech/llm/images/openwebui_who_is_batman.png b/docs/opentech/llm/images/openwebui_who_is_batman.png
diff --git a/docs/opentech/llm/images/rag_doc_added.png b/docs/opentech/llm/images/rag_doc_added.png
diff --git a/docs/opentech/llm/images/small_llm_ceo_list.png b/docs/opentech/llm/images/small_llm_ceo_list.png
diff --git a/docs/opentech/llm/lab-4/README.md b/docs/opentech/llm/lab-4/README.md
@@ -183,10 +183,9 @@ hire me for a role with both my current skill set
 and previous experience.
 ```
 
-![](../images/anythingllm_resume.png)
-
-The response I received has room for improvement, but gives me something to work with!
+The response I received below has room for improvement, but gives me something to work with!
 </details>
+![resume](../images/anythingllm_resume.png)
 
 Try to build and modify this blurb using the principles of prompt engineering you learned until you're happy with the quality of the response you receive. Think outside of the box!
 

diff --git a/docs/opentech/llm/pre-work/README.md b/docs/opentech/llm/pre-work/README.md
@@ -65,4 +65,4 @@ DATA_DIR=~/.open-webui uvx --python 3.11 open-webui@latest serve
 $env:DATA_DIR="C:\open-webui\data"; uvx --python 3.11 open-webui@latest serve
 ```
 
-Once the downloads, install, and start are complete, you will have a fancy Open WebUI "get started" page at localhost:8080.  You can now kill the server with Control-C back in the terminal. We'll do the setup during the workshop.
+Once the downloads, install, and start are complete, you will have a fancy Open WebUI "get started" page at [http://localhost:8080/](http://localhost:8080/).  You can now kill the server with Control-C back in the terminal. We'll do the setup during the workshop.
diff --git a/docs/opentech/llm/setup/README.md b/docs/opentech/llm/setup/README.md
diff --git a/docs/opentech/mellea/lab-1/README.md b/docs/opentech/mellea/lab-1/README.md
@@ -70,7 +70,7 @@ Open up a terminal and run the following uv command from the `beeai-workshop/ope
     ```python
     import mellea
 
-    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro")
+    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro-h")
     print(m.chat("tell me some fun trivia about IBM and the early history of AI.").content)
     ```
 
@@ -83,7 +83,7 @@ Open up a terminal and run the following uv command from the `beeai-workshop/ope
 
     ```python
     import mellea
-    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro")
+    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro-h")
 
     email = m.instruct("Write an email inviting interns to an office party at 3:30pm.")
     print(str(email))
@@ -93,7 +93,7 @@ Open up a terminal and run the following uv command from the `beeai-workshop/ope
 
     ```python
     import mellea
-    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro")
+    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro-h")
 
     def write_email(m: mellea.MelleaSession, name: str, notes: str) -> str:
         email = m.instruct(
@@ -123,7 +123,7 @@ Open up a terminal and run the following uv command from the `beeai-workshop/ope
 
     ```python
     import mellea
-    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro")
+    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro-h")
 
     def write_email_with_requirements(
         m: mellea.MelleaSession, name: str, notes: str
@@ -190,7 +190,7 @@ The first `instruct-validate-repair` pattern is as follows:
         else:
             return email_candidate.sample_generations[0].value
 
-    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro")
+    m = mellea.start_session(backend_name="ollama", model_id="ibm/granite4:micro-h")
     print(
         write_email(
             m,

diff --git a/docs/opentech/mellea/pre-work/README.md b/docs/opentech/mellea/pre-work/README.md
@@ -11,6 +11,7 @@ These are the required applications and general installation notes for this work
 - [uv](#install-uv) - Provides Python, packages, and virtual environments.
 - [Ollama](#install-ollama) - Allows you to locally host LLM models on your computer.
 - [Models](#pull-models-with-ollama) - Pull models to run with Ollama.
+- [Workshop Code](#get-the-workshop-code) - Git clone the workshop
 
 ## Install `uv`
 
@@ -47,3 +48,21 @@ For a quick test, you can use the ollama CLI to ask the model a question.
 ```shell
 ollama run ibm/granite4:micro-h "what model am I chatting with and and who created you?"  
 ```
+
+## Get the workshop code
+
+**Option A: Clone with Git (recommended):**
+
+```bash
+git clone https://github.com/IBM/beeai-workshop.git
+```
+
+**Option B: Download ZIP:**
+
+If you're not comfortable with Git, [download the ZIP](https://github.com/IBM/beeai-workshop/archive/refs/heads/main.zip) file and extract it to your desired location.
+
+Then:
+
+```bash
+cd beeai-workshop/opentech
+```
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -27,7 +27,7 @@ nav:
       - Prework: opentech/prework/README.md
       - Open Source AI Labs:
         - Overview: opentech/llm/overview/README.md
-        - Setup: opentech/llm/setup/README.md
+        - Pre-work: opentech/llm/pre-work/README.md
         - Lab 1: opentech/llm/lab-1/README.md
         - Lab 2: opentech/llm/lab-2/README.md
         - Lab 3: opentech/llm/lab-3/README.md