diff --git a/.github/workflows/deploy-website.yml b/.github/workflows/deploy-website.yml
index 4ca9d8f9d..3d816d98f 100644
--- a/.github/workflows/deploy-website.yml
+++ b/.github/workflows/deploy-website.yml
@@ -28,7 +28,7 @@ jobs:
       - name: pydoc-markdown install
         run: |
           python -m pip install --upgrade pip
-          pip install pydoc-markdown
+          pip install pydoc-markdown==4.5.0
       - name: pydoc-markdown run
         run: |
           pydoc-markdown
@@ -64,7 +64,7 @@ jobs:
       - name: pydoc-markdown install
         run: |
           python -m pip install --upgrade pip
-          pip install pydoc-markdown
+          pip install pydoc-markdown==4.5.0
       - name: pydoc-markdown run
         run: |
           pydoc-markdown
diff --git a/README.md b/README.md
index 6408ca2cb..ad2294aa6 100644
--- a/README.md
+++ b/README.md
@@ -33,7 +33,7 @@ FLAML requires **Python version >= 3.6**. It can be installed from pip:
 pip install flaml
 ```
 
-To run the [`notebook example`](https://github.com/microsoft/FLAML/tree/main/notebook),
+To run the [`notebook examples`](https://github.com/microsoft/FLAML/tree/main/notebook),
 install flaml with the [notebook] option:
 
 ```bash
@@ -43,7 +43,7 @@ pip install flaml[notebook]
 ## Quickstart
 
 * With three lines of code, you can start using this economical and fast
-AutoML engine as a scikit-learn style estimator.
+AutoML engine as a [scikit-learn style estimator](https://microsoft.github.io/FLAML/docs/Use-Cases/Task-Oriented-AutoML).
 
 ```python
 from flaml import AutoML
@@ -52,19 +52,29 @@ automl.fit(X_train, y_train, task="classification")
 ```
 
 * You can restrict the learners and use FLAML as a fast hyperparameter tuning
-tool for XGBoost, LightGBM, Random Forest etc. or a customized learner.
+tool for XGBoost, LightGBM, Random Forest etc. or a [customized learner](https://microsoft.github.io/FLAML/docs/Use-Cases/Task-Oriented-AutoML#estimator-and-search-space).
 
 ```python
 automl.fit(X_train, y_train, task="classification", estimator_list=["lgbm"])
 ```
 
-* You can also run generic hyperparameter tuning for a custom function.
+* You can also run generic hyperparameter tuning for a [custom function](https://microsoft.github.io/FLAML/docs/Use-Cases/Tune-User-Defined-Function).
 
 ```python
 from flaml import tune
 tune.run(evaluation_function, config={…}, low_cost_partial_config={…}, time_budget_s=3600)
 ```
 
+* [Zero-shot AutoML](https://microsoft.github.io/FLAML/docs/Use-Cases/Zero-Shot-AutoML) allows using the existing training API from lightgbm, xgboost etc. while getting the benefit of AutoML in choosing high-performance hyperparameter configurations per task.
+
+```python
+from flaml.default import LGBMRegressor
+# Use LGBMRegressor in the same way as you use lightgbm.LGBMRegressor.
+estimator = LGBMRegressor()
+# The hyperparameters are automatically set according to the training data.
+estimator.fit(X_train, y_train)
+```
+
 ## Documentation
 
 You can find a detailed documentation about FLAML [here](https://microsoft.github.io/FLAML/) where you can find the API documentation, use cases and examples.