Skip to content

fix(examples): migrate basics_colab and agents_colab notebooks from granite3.3 to granite4.1:8b #1540

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
BiswasNehaa wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(examples): migrate basics_colab and agents_colab notebooks from granite3.3 to granite4.1:8b #1540

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion python/examples/notebooks/agents_colab.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,7 @@
"outputs": [],
"source": [
"# Construct ChatModel\n",
"chat_model = ChatModel.from_name(\"ollama:granite3.3\")\n",
"chat_model = ChatModel.from_name(\"ollama:granite4.1:8b\")\n",

@gemini-code-assist gemini-code-assist Bot Jun 30, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

There is a mismatch between the model being pulled in the installation cell and the model instantiated here. The installation cell (around line 78) pulls granite3.3:8b (!ollama pull granite3.3:8b), but this cell instantiates granite4.1:8b. This will cause a runtime error or unexpected delay when running the notebook in Google Colab because the correct model is not pre-pulled. Please update the installation cell to pull granite4.1:8b as well.

"\n",
"# Construct Agent instance with the chat model\n",
"agent = RequirementAgent(llm=chat_model, tools=[], memory=UnconstrainedMemory())\n",
Expand Down
26 changes: 13 additions & 13 deletions python/examples/notebooks/basics_colab.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,13 +256,13 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Construct ChatModel\n",
"model = ChatModel.from_name(\"ollama:granite3.3\")\n",
"model = ChatModel.from_name(\"ollama:granite4.1:8b\")\n",

@gemini-code-assist gemini-code-assist Bot Jun 30, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

There is a mismatch between the model being pulled in the installation cell and the model instantiated here. The installation cell (around line 73) pulls granite3.3:8b (!ollama pull granite3.3:8b), but this cell instantiates granite4.1:8b. This will cause a runtime error or unexpected delay when running the notebook in Google Colab because the correct model is not pre-pulled. Please update the installation cell to pull granite4.1:8b as well.

"\n",
"question1 = \"Briefly explain quantum computing in simple terms with an example.\"\n",
"message = UserMessage(content=question1)\n",
Expand All @@ -274,10 +274,10 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"question2 = \"Hello! Can you tell me what is the capital of France?\"\n",
"message = UserMessage(content=question2)\n",
Expand Down Expand Up @@ -305,10 +305,10 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"memory = UnconstrainedMemory()\n",
"question3 = \"If you had to recommend one thing to do there, what would it be?\"\n",
Expand Down Expand Up @@ -341,10 +341,10 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Some context that the model will use to provide an answer. Source wikipedia: https://en.wikipedia.org/wiki/Ireland\n",
"context = \"\"\"The geography of Ireland comprises relatively low-lying mountains surrounding a central plain, with several navigable rivers extending inland.\n",
Expand Down Expand Up @@ -381,10 +381,10 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# The output structure definition, note the field descriptions that can help the LLM to understand the intention of the field.\n",
"class CharacterSchema(BaseModel):\n",
Expand Down Expand Up @@ -421,10 +421,10 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pirate_message = \"You are pirate. You always respond using pirate slang.\"\n",
"system_message = SystemMessage(content=pirate_message)\n",
Expand Down
Loading