postgresml · montanalow · Jan 30, 2023 · Jan 30, 2023
diff --git a/pgml-docs/docs/user_guides/training/preprocessing.md b/pgml-docs/docs/user_guides/training/preprocessing.md
@@ -29,7 +29,7 @@ There are 3 steps to preprocessing data:
 These preprocessing steps may be specified on a per-column basis to the [train()](/user_guides/training/overview/) function. By default, PostgresML does minimal preprocessing on training data, and will raise an error during analysis if NULL values are encountered without a preprocessor. All types other than `TEXT` are treated as quantitative variables and cast to floating point representations before passing them to the underlying algorithm implementations.   
 
 ```postgresql title="pgml.train()"
-select pgml.train(
+SELECT pgml.train(
     project_name => 'preprocessed_model', 
     task => 'classification', 
     relation_name => 'weather_data',
@@ -52,6 +52,14 @@ In some cases, it may make sense to use multiple steps for a single column. For
 !!! note
     TEXT is used in this document to also refer to VARCHAR and CHAR(N) types.
 
+## Predicting with Preprocessors
+
+A model that has been trained with preprocessors should use a Postgres tuple for prediction, rather than a `FLOAT4[]`. Tuples may contain multiple different types (like `TEXT` and `BIGINT`), while an ARRAY may only contain a single type. You can use parenthesis around values to create a Postgres tuple.
+
+```postgresql title="pgml.predict()"
+    SELECT pgml.predict('preprocessed_model', ('jan', 'nimbus', 0.5, 7));
+```
+
 ## Categorical encodings
 Encoding categorical variables is an O(N log(M)) where N is the number of rows, and M is the number of distinct categories.   
 

diff --git a/pgml-docs/mkdocs.yml b/pgml-docs/mkdocs.yml
@@ -127,6 +127,7 @@ nav:
         - Training:
             - Training Overview: user_guides/training/overview.md
             - Algorithm Selection: user_guides/training/algorithm_selection.md
+            - Preprocessing Data:  user_guides/training/preprocessing.md
             - Hyperparameter Search: user_guides/training/hyperparameter_search.md
             - Joint Optimization: user_guides/training/joint_optimization.md
         - Predictions: