add missing operator_cache decorator (#80)

mssing decorator and doc updates

docs/configurations.rst

@@ -21,8 +21,8 @@ Using the Settings module
 Configurable Parameters
 --------------------------
 
-1. enable_message_cache: 
-    * Description: Enables or Disables cahcing mechanisms
+1. enable_cache: 
+    * Description: Enables or Disables caching mechanisms
     * Default: False
     * Parameters: 
         - cache_type: Type of caching (SQLITE or In_MEMORY)
@@ -31,6 +31,12 @@ Configurable Parameters
     * Note: It is recommended to enable caching
 .. code-block:: python
 
+    import pandas as pd
+
+    import lotus
+    from lotus.models import LM
+    from lotus.cache import CacheFactory, CacheConfig, CacheType
+    
     cache_config = CacheConfig(cache_type=CacheType.SQLITE, max_size=1000)
     cache = CacheFactory.create_cache(cache_config)
 

lotus/sem_ops/sem_dedup.py

@@ -4,6 +4,7 @@
 import pandas as pd
 
 import lotus
+from lotus.cache import operator_cache
 
 
 @pd.api.extensions.register_dataframe_accessor("sem_dedup")
@@ -19,6 +20,7 @@ def _validate(obj: Any) -> None:
         if not isinstance(obj, pd.DataFrame):
             raise AttributeError("Must be a DataFrame")
 
+    @operator_cache
     def __call__(
         self,
         col_name: str,

lotus/sem_ops/sem_index.py

@@ -3,6 +3,7 @@
 import pandas as pd
 
 import lotus
+from lotus.cache import operator_cache
 
 
 @pd.api.extensions.register_dataframe_accessor("sem_index")
@@ -19,6 +20,7 @@ def _validate(obj: Any) -> None:
         if not isinstance(obj, pd.DataFrame):
             raise AttributeError("Must be a DataFrame")
 
+    @operator_cache
     def __call__(self, col_name: str, index_dir: str) -> pd.DataFrame:
         """
         Index a column in the DataFrame.

lotus/sem_ops/sem_partition_by.py

@@ -2,6 +2,8 @@
 
 import pandas as pd
 
+from lotus.cache import operator_cache
+
 
 @pd.api.extensions.register_dataframe_accessor("sem_partition_by")
 class SemPartitionByDataframe:
@@ -16,6 +18,7 @@ def _validate(obj: Any) -> None:
         if not isinstance(obj, pd.DataFrame):
             raise AttributeError("Must be a DataFrame")
 
+    @operator_cache
     def __call__(
         self,
         partition_fn: Callable[[pd.DataFrame], list[int]],