docs: add azure callouts to use cases (#357)

nbs/docs/use-cases/1_forecasting_web_traffic.ipynb

@@ -120,6 +120,17 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 👍 Use an Azure AI endpoint\n",
+    "> \n",
+    "> To use an Azure AI endpoint, remember to set also the `base_url` argument:\n",
+    "> \n",
+    "> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -485,6 +496,21 @@
     "timegpt_cv_df.head()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.cross_validation(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

nbs/docs/use-cases/2_bitcoin_price_prediction.ipynb

@@ -452,6 +452,17 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 👍 Use an Azure AI endpoint\n",
+    "> \n",
+    "> To use an Azure AI endpoint, remember to set also the `base_url` argument:\n",
+    "> \n",
+    "> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -677,6 +688,21 @@
     "fcst.head()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.forecast(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -873,6 +899,21 @@
     "forecast.head()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.forecast(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -935,6 +976,21 @@
     "anomalies_df = nixtla_client.detect_anomalies(df)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.detect_anomalies(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

nbs/docs/use-cases/3_electricity_demand.ipynb

@@ -135,6 +135,17 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 👍 Use an Azure AI endpoint\n",
+    "> \n",
+    "> To use an Azure AI endpoint, remember to set also the `base_url` argument:\n",
+    "> \n",
+    "> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -406,6 +417,21 @@
     "print(f\"Time (TimeGPT): {timegpt_duration}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.forecast(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -617,11 +643,6 @@
     "\n",
     "Plus, TimeGPT took 7.7 seconds to generate forecasts, while N-HiTS took 67 seconds to fit and predict. TimeGPT is thus **88% faster** than using N-HiTS in this scenario. "
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": []
   }
  ],
  "metadata": {

nbs/docs/use-cases/4_intermittent_demand.ipynb

@@ -122,6 +122,17 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 👍 Use an Azure AI endpoint\n",
+    "> \n",
+    "> To use an Azure AI endpoint, remember to set also the `base_url` argument:\n",
+    "> \n",
+    "> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -503,6 +514,21 @@
     "print(f\"Time (TimeGPT): {timegpt_duration}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.forecast(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -1348,6 +1374,21 @@
     "print(f\"Time (TimeGPT): {timegpt_duration}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.forecast(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

nbs/docs/use-cases/5_what_if_pricing_scenarios_in_retail.ipynb

@@ -113,6 +113,17 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 👍 Use an Azure AI endpoint\n",
+    "> \n",
+    "> To use an Azure AI endpoint, remember to set also the `base_url` argument:\n",
+    "> \n",
+    "> `nixtla_client = NixtlaClient(base_url=\"you azure ai endpoint\", api_key=\"your api_key\")`"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -895,6 +906,21 @@
     "timegpt_fcst_df.head()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.forecast(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -993,6 +1019,21 @@
     "timegpt_fcst_df_minus = nixtla_client.forecast(df=df_train, X_df=future_ex_vars_df_minus, h=28)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 📘 Available models in Azure AI\n",
+    ">\n",
+    "> If you are using an Azure AI endpoint, please be sure to set `model=\"azureai\"`:\n",
+    ">\n",
+    "> `nixtla_client.forecast(..., model=\"azureai\")`\n",
+    "> \n",
+    "> For the public API, we support two models: `timegpt-1` and `timegpt-1-long-horizon`. \n",
+    "> \n",
+    "> By default, `timegpt-1` is used. Please see [this tutorial](https://docs.nixtla.io/docs/tutorials-long_horizon_forecasting) on how and when to use `timegpt-1-long-horizon`."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},