[Tidy] Update model names and add PyCafe link (#853)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

vizro-ai/README.md

@@ -23,6 +23,7 @@ It serves as an extension to Vizro, leveraging natural language capabilities to
 
 | Platform     | Chart creation                                                                                                                                                                            | Dashboard creation                                                                                                                                                                            |
 | ------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| PyCafe       | https://py.cafe/app/vizro-official/vizro-ai-charts                                                                                                                                        |                                                                                                                                                                                               |
 | Google Colab | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mckinsey/vizro/blob/main/vizro-ai/examples/chart_by_vizro_ai.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mckinsey/vizro/blob/main/vizro-ai/examples/dashboard_by_vizro_ai.ipynb) |
 
 ## Why Vizro-AI?

vizro-ai/changelog.d/20241105_141708_lingyi_zhang_update_docs_to_reflect_changes.md

@@ -0,0 +1,48 @@
+<!--
+A new scriv changelog fragment.
+
+Uncomment the section that is right (remove the HTML comment wrapper).
+-->
+
+<!--
+### Highlights ✨
+
+- A bullet item for the Highlights ✨ category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Removed
+
+- A bullet item for the Removed category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Added
+
+- A bullet item for the Added category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Changed
+
+- A bullet item for the Changed category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Deprecated
+
+- A bullet item for the Deprecated category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Fixed
+
+- A bullet item for the Fixed category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->
+<!--
+### Security
+
+- A bullet item for the Security category with a link to the relevant PR at the end of your entry, e.g. Enable feature XXX ([#1](https://github.com/mckinsey/vizro/pull/1))
+
+-->

vizro-ai/docs/pages/explanation/safety-in-vizro-ai.md

@@ -26,7 +26,7 @@ It is necessary to approach the generated content with caution, especially when
 ### 3. Data privacy
 <!-- vale on -->
 Your data is sent to model vendors if you connect to LLMs via their APIs.
-For example, if you connect to the model "gpt-3.5-turbo-0613" from Open AI, your data will be sent to OpenAI via their API.
+For example, if you connect to the model from OpenAI, your data will be sent to OpenAI via their API.
 Users should be cautious about sharing or inputting any personal or sensitive information.
 
 <!-- vale off -->

vizro-ai/docs/pages/user-guides/chart-examples.md

@@ -1,6 +1,6 @@
 # Gallery of examples
 
-Take a look at some more advanced charts that can be created with Vizro-AI using data from [Plotly Express](https://plotly.com/python-api-reference/generated/plotly.express.data.html). The examples below use the OpenAI `"gpt-4o"` model as we are going to request specific updates to the layout of the charts, which are [more complex than the GPT 3.5 model can handle](./customize-vizro-ai.md).
+Take a look at some more advanced charts that can be created with Vizro-AI using data from [Plotly Express](https://plotly.com/python-api-reference/generated/plotly.express.data.html). The examples below use the OpenAI `"gpt-4o"` model as we are going to request specific updates to the layout of the charts.
 
 ### Polar bar chart
 

vizro-ai/docs/pages/user-guides/customize-vizro-ai.md

@@ -112,9 +112,9 @@ Passing an instantiated model to `VizroAI` lets you customize it, and additional
 
 ### Chart generation
 
-At the time of writing, we found that for chart creation, the leading vendor's "cheaper" models, for example OpenAI's `gpt-4o-mini` and `gpt-3.5` model series, are suitable for basic charting despite their relatively low price points.
+At the time of writing, we found that for chart creation, the leading vendor's "cheaper" models, for example OpenAI's `gpt-4o-mini`, are suitable for basic charting despite their relatively low price points.
 
-Consider upgrading to, in the case of OpenAI the `gpt-4o` and `gpt-4` model series, or in the case of Anthropic the `claude-3-5-sonnet-20240620` model series, for more demanding tasks. The downside of using these models is that they come at a higher cost.
+Consider upgrading to, in the case of OpenAI the `gpt-4o` and `gpt-4` model series, or in the case of Anthropic the `Claude 3.5` model series, for more demanding tasks. The downside of using these models is that they come at a higher cost.
 
 ### Dashboard generation
 

vizro-ai/examples/chart_by_vizro_ai.ipynb

@@ -298,7 +298,7 @@
     "\n",
     "# @markdown #### 1. Choose the LLM model\n",
     "\n",
-    "LLM = \"gpt-4o\"  # @param [\"gpt-4o\", \"gpt-3.5-turbo\", \"gpt-4-turbo\", \"gpt-4o-mini\"]\n",
+    "LLM = \"gpt-4o\"  # @param [\"gpt-4o\", \"gpt-4-turbo\", \"gpt-4o-mini\"]\n",
     "\n",
     "print(f\"Selected LLM: {LLM}\")\n",
     "\n",

vizro-ai/examples/dashboard_by_vizro_ai.ipynb

@@ -296,7 +296,7 @@
     "\n",
     "# @markdown #### 1. Choose the LLM model\n",
     "\n",
-    "LLM = \"gpt-4o\"  # @param [\"gpt-4o\", \"gpt-3.5-turbo\", \"gpt-4-turbo\", \"gpt-4o-mini\"]\n",
+    "LLM = \"gpt-4o\"  # @param [\"gpt-4o\", \"gpt-4-turbo\", \"gpt-4o-mini\"]\n",
     "\n",
     "\n",
     "# @markdown ---\n",

vizro-ai/examples/example.ipynb

@@ -11,7 +11,7 @@
     "llm = None\n",
     "# uncomment below to try out different models\n",
     "# llm = \"gpt-4o\"\n",
-    "# llm = \"claude-3-5-sonnet-20240620\"\n",
+    "# llm = \"claude-3-5-sonnet-latest\"\n",
     "# llm = \"mistral-large-latest\"\n",
     "\n",
     "# from langchain_openai import ChatOpenAI\n",
@@ -22,7 +22,7 @@
     "# import os\n",
     "# from langchain_anthropic import ChatAnthropic\n",
     "# llm = ChatAnthropic(\n",
-    "#         model=\"claude-3-5-sonnet-20240620\",\n",
+    "#         model=\"claude-3-5-sonnet-latest\",\n",
     "#         # api_key = os.environ.get(\"ANTHROPIC_API_KEY\"),\n",
     "#         # base_url= os.environ.get(\"ANTHROPIC_API_BASE\")\n",
     "#     )\n",

vizro-ai/src/vizro_ai/_llm_models.py

@@ -86,6 +86,6 @@ def _get_model_name(model: BaseChatModel) -> str:
 
 
 if __name__ == "__main__":
-    llm_chat_openai = _get_llm_model(model="gpt-3.5-turbo")
+    llm_chat_openai = _get_llm_model(model="gpt-4o-mini")
     print(repr(llm_chat_openai))  # noqa: T201
     print(llm_chat_openai.model_name)  # noqa: T201

vizro-ai/tests/integration/test_dashboard.py

@@ -27,8 +27,8 @@ def setup_test_environment():
 
 @pytest.mark.parametrize(
     "model_name",
-    ["gpt-3.5-turbo"],
-    ids=["gpt-3.5"],
+    ["gpt-4o-mini"],
+    ids=["gpt-4o-mini"],
 )
 @pytest.mark.filterwarnings("ignore::langchain_core._api.beta_decorator.LangChainBetaWarning")
 @pytest.mark.filterwarnings("ignore::UserWarning")