resolving conflict

docs/api/models/adapters/adapters.md

@@ -0,0 +1,8 @@
+# `timecopilot.models.adapters`
+
+
+::: timecopilot.models.adapters.sktime
+    options:
+        members:
+            - SKTimeAdapter
+

docs/contributing.md

@@ -77,6 +77,14 @@ All documentation files should use **kebab-case** (e.g., `model-hub.md`, `foreca
 
 For further reference, see the [Google Developer Documentation Style Guide on file names](https://developers.google.com/style/filenames).
 
+### Adding Models & Adapters
+
+In order for new models and adapters to show up in TimeCopilot's documentation properly there are a couple steps to take:
+
+- Add the model/adapter in its own file or the appropriate file in `docs/api/models` or the appropriate subdirectory. For adapters, it may also be good to create an example notebook in `docs/examples` and add it to the `Examples` section of [mkdocs.yml](https://github.com/TimeCopilot/timecopilot/blob/main/mkdocs.yml).
+    - when creating a new file in `docs/api/models` for this step, add that file in the API Reference section of [mkdocs.yml](https://github.com/TimeCopilot/timecopilot/blob/main/mkdocs.yml)
+- A docstring should be present for the new model/adapter with an example in the `forecast()` method in a similar style to the [TimeCopilot agent query method](https://timecopilot.dev/api/agent/#timecopilot.agent.TimeCopilot.query). Note: when adding an adapter with its own dependencies you may need to add those dependencies as dev dependencies with `uv add new_dep --group dev`.
+
 ## Adding New Datasets
 
 The datasets utilized in our documentation are hosted on AWS at `https://timecopilot.s3.amazonaws.com/public/data/`. If you wish to contribute additional datasets for your changes, please contact [@AzulGarza](http://github.com/AzulGarza) for guidance.
@@ -115,4 +123,4 @@ TimeCopilot uses some forked Python packages, maintained under custom names on P
 - **uni2ts**:
     - Forked from: [SalesforceAIResearch/uni2ts](https://github.com/SalesforceAIResearch/uni2ts)
     - TimeCopilot fork: [AzulGarza/uni2ts](https://github.com/AzulGarza/uni2ts)
-    - Published on PyPI as: [`timecopilot-uni2ts`](https://pypi.org/project/timecopilot-uni2ts/)
+    - Published on PyPI as: [`timecopilot-uni2ts`](https://pypi.org/project/timecopilot-uni2ts/)

docs/examples/aws-bedrock.ipynb

@@ -88,7 +88,7 @@
    "id": "9c4c7220",
    "metadata": {},
    "source": [
-    "If you store your environment variablesles in a `.env` file, you can use the following load them into your environment from the file:"
+    "If you store your environment variables in a `.env` file, you can use the following load them into your environment from the file:"
    ]
   },
   {
@@ -189,7 +189,6 @@
     "\n",
     "model = BedrockConverseModel(\n",
     "    'us.anthropic.claude-3-5-sonnet-20241022-v2:0'\n",
-    "    \n",
     ")\n",
     "tc = TimeCopilot(\n",
     "    llm=model,\n",
@@ -322,30 +321,6 @@
     "print(result.output.tsfeatures_analysis)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "1fe2ed8a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The time series analysis reveals strong seasonal and trend components:\n",
-      "1. High seasonal strength (0.98) indicates pronounced yearly patterns\n",
-      "2. Strong positive autocorrelation (x_acf1: 0.95) suggests strong trend\n",
-      "3. Significant Holt-Winters seasonality (hw_gamma: 0.75) confirms seasonal importance\n",
-      "4. High stability (0.93) indicates consistent patterns\n",
-      "5. Non-stationary series (KPSS: 2.74) confirms strong trend\n",
-      "6. Clear seasonal peaks (July) and troughs (November)\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(result.output.tsfeatures_analysis)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 9,