WL#17088 Formatting ML SDK [POSTFIX]

Issue:
AI package formatting and type hints are flagged in some build pipelines

Solution:
Fix formatting

Change-Id: If7cda8d86fd8f434a92765dd91608dfa4d8c5232

Author: GregorySHowe

mysql-connector-python/lib/mysql/ai/genai/__init__.py

@@ -26,6 +26,13 @@
 # along with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA
 
+"""GenAI package for MySQL Connector/Python.
+
+Performs optional dependency checks and exposes public classes:
+- MyEmbeddings
+- MyLLM
+- MyVectorStore
+"""
 from mysql.ai.utils import check_dependencies as _check_dependencies
 
 _check_dependencies(["GENAI"])

mysql-connector-python/lib/mysql/ai/genai/embedding.py

@@ -26,11 +26,19 @@
 # along with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA
 
+"""Embeddings integration utilities for MySQL Connector/Python.
+
+Provides MyEmbeddings class to generate embeddings via MySQL HeatWave
+using ML_EMBED_TABLE and ML_EMBED_ROW.
+"""
+
 from typing import Dict, List, Optional
 
 import pandas as pd
 
 from langchain_core.embeddings import Embeddings
+from pydantic import PrivateAttr
+
 from mysql.ai.utils import (
     atomic_transaction,
     execute_sql,
@@ -40,8 +48,6 @@
     sql_table_to_df,
     temporary_sql_tables,
 )
-from pydantic import PrivateAttr
-
 from mysql.connector.abstracts import MySQLConnectionAbstract
 
 
@@ -134,7 +140,13 @@ def embed_documents(self, texts: List[str]) -> List[List[float]]:
             temporary_tables.append((self.schema_name, table_name))
 
             # ML_EMBED_TABLE expects input/output columns and options as parameters
-            embed_query = f"CALL sys.ML_EMBED_TABLE('{qualified_table_name}.text', '{qualified_table_name}.embeddings', {self.options_placeholder})"
+            embed_query = (
+                "CALL sys.ML_EMBED_TABLE("
+                f"'{qualified_table_name}.text', "
+                f"'{qualified_table_name}.embeddings', "
+                f"{self.options_placeholder}"
+                ")"
+            )
             execute_sql(cursor, embed_query, params=self.options_params)
 
             # Read back all columns, including "embeddings"

mysql-connector-python/lib/mysql/ai/genai/generation.py

@@ -26,6 +26,11 @@
 # along with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA
 
+"""GenAI LLM integration utilities for MySQL Connector/Python.
+
+Provides MyLLM wrapper that issues ML_GENERATE calls via SQL.
+"""
+
 import json
 
 from typing import Any, List, Optional
@@ -34,9 +39,9 @@
     from langchain_core.language_models.llms import LLM
 except ImportError:
     from langchain.llms.base import LLM
-from mysql.ai.utils import atomic_transaction, execute_sql, format_value_sql
 from pydantic import PrivateAttr
 
+from mysql.ai.utils import atomic_transaction, execute_sql, format_value_sql
 from mysql.connector.abstracts import MySQLConnectionAbstract
 
 
@@ -50,7 +55,8 @@ class MyLLM(LLM):
     agentic queries.
 
     Attributes:
-        _db_connection (MySQLConnectionAbstract): The underlying MySQL connector database connection.
+        _db_connection (MySQLConnectionAbstract):
+            Underlying MySQL connector database connection.
     """
 
     _db_connection: MySQLConnectionAbstract = PrivateAttr()
@@ -138,7 +144,8 @@ def _identifying_params(self) -> dict:
         Return a dictionary of params that uniquely identify this LLM instance.
 
         Returns:
-            dict: Dictionary of identifier parameters (should include model_name for tracing/caching).
+            dict: Dictionary of identifier parameters (should include
+                model_name for tracing/caching).
         """
         return {
             "model_name": "mysql_heatwave_llm",

mysql-connector-python/lib/mysql/ai/genai/vector_store.py

@@ -26,6 +26,12 @@
 # along with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA
 
+"""MySQL-backed vector store for embeddings and semantic document retrieval.
+
+Provides a VectorStore implementation persisting documents, metadata, and
+embeddings in MySQL, plus similarity search utilities.
+"""
+
 import json
 
 from typing import Any, Iterable, List, Optional, Sequence, Union
@@ -35,6 +41,8 @@
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
 from langchain_core.vectorstores import VectorStore
+from pydantic import PrivateAttr
+
 from mysql.ai.genai.embedding import MyEmbeddings
 from mysql.ai.utils import (
     VAR_NAME_SPACE,
@@ -48,9 +56,7 @@
     source_schema,
     table_exists,
 )
-
 from mysql.connector.abstracts import MySQLConnectionAbstract
-from pydantic import PrivateAttr
 
 BASIC_EMBEDDING_QUERY = "Hello world!"
 EMBEDDING_SOURCE = "external_source"
@@ -78,7 +84,8 @@ class MyVectorStore(VectorStore):
         db_connection (MySQLConnectionAbstract): Active MySQL database connection.
         embedder (Embeddings): Embeddings generator for computing vector representations.
         schema_name (str): SQL schema for table storage.
-        table_name (Optional[str]): Name of the active table backing the store (or None until created).
+        table_name (Optional[str]): Name of the active table backing the store
+            (or None until created).
         embedding_dimension (int): Size of embedding vectors stored.
         next_id (int): Internal counter for unique document ID generation.
     """
@@ -116,8 +123,11 @@ def __init__(
         self._db_connection = db_connection
         self._table_name: Optional[str] = None
 
-        # Embedding dimension determined using an example call. Assumes embeddings have fixed length.
-        self._embedding_dimension = len(self._embedder.embed_query(BASIC_EMBEDDING_QUERY))
+        # Embedding dimension determined using an example call.
+        # Assumes embeddings have fixed length.
+        self._embedding_dimension = len(
+            self._embedder.embed_query(BASIC_EMBEDDING_QUERY)
+        )
 
     def _get_ids(self, num_ids: int) -> list[str]:
         """
@@ -174,7 +184,7 @@ def _make_vector_store(self) -> None:
 
                 self._table_name = table_name
 
-    def delete(self, ids: Optional[Sequence[str]] = None, **kwargs: Any) -> None:
+    def delete(self, ids: Optional[Sequence[str]] = None, **_: Any) -> None:
         """
         Delete documents by ID. Optionally deletes the vector table if empty after deletions.
 
@@ -190,7 +200,8 @@ def delete(self, ids: Optional[Sequence[str]] = None, **kwargs: Any) -> None:
                 If an operational error occurs during execution.
 
         Notes:
-            If the backing table is empty after deletions, the table is dropped and table_name is set to None.
+            If the backing table is empty after deletions, the table is dropped and
+            table_name is set to None.
         """
         with atomic_transaction(self._db_connection) as cursor:
             if ids:
@@ -221,7 +232,7 @@ def add_texts(
         texts: Iterable[str],
         metadatas: Optional[list[dict]] = None,
         ids: Optional[List[str]] = None,
-        **kwargs: dict,
+        **_: dict,
     ) -> List[str]:
         """
         Add a batch of text strings and corresponding metadata to the vector store.
@@ -312,7 +323,7 @@ def add_documents(
         """
         if ids and len(ids) != len(documents):
             msg = (
-                f"ids must be the same length as documents. "
+                "ids must be the same length as documents. "
                 f"Got {len(ids)} ids and {len(documents)} documents."
             )
             raise ValueError(msg)
@@ -357,7 +368,8 @@ def similarity_search(
         Args:
             query: String query to embed and use for similarity search.
             k: Number of top documents to return.
-            kwargs: options to pass to ML_SIMILARITY_SEARCH. Currently supports distance_metric, max_distance, percentage_distance, and segment_overlap
+            kwargs: options to pass to ML_SIMILARITY_SEARCH. Currently supports
+                distance_metric, max_distance, percentage_distance, and segment_overlap
 
         Returns:
             List of Document objects, ordered from most to least similar.
@@ -399,8 +411,14 @@ def similarity_search(
             similarity_search_query = f"""
             CALL sys.ML_SIMILARITY_SEARCH(
                 @{VAR_EMBEDDING},
-                JSON_ARRAY('{self._schema_name}.{self._table_name}'),
-                JSON_OBJECT("segment", "content", "segment_embedding", "embed", "document_name", "id"),
+                JSON_ARRAY(
+                    '{self._schema_name}.{self._table_name}'
+                ),
+                JSON_OBJECT(
+                    "segment", "content",
+                    "segment_embedding", "embed",
+                    "document_name", "id"
+                ),
                 {k},
                 %s,
                 NULL,
@@ -425,13 +443,17 @@ def similarity_search(
             for context in context_maps:
                 execute_sql(
                     cursor,
-                    f"SELECT id, content, metadata FROM {self._schema_name}.{self._table_name} WHERE id =%s",
+                    (
+                        "SELECT id, content, metadata "
+                        f"FROM {self._schema_name}.{self._table_name} "
+                        "WHERE id = %s"
+                    ),
                     params=(context["document_name"],),
                 )
-                id, content, metadata = cursor.fetchone()
+                doc_id, content, metadata = cursor.fetchone()
 
                 doc_args = {
-                    "id": id,
+                    "id": doc_id,
                     "page_content": content,
                 }
                 if metadata is not None:
@@ -450,8 +472,10 @@ def __enter__(self) -> "VectorStore":
             The current MyVectorStore object, allowing use within a `with` statement block.
 
         Usage Notes:
-            - Intended for use in a `with` statement to ensure automatic cleanup of resources.
-            - No special initialization occurs during context entry, but enables proper context-managed lifecycle.
+            - Intended for use in a `with` statement to ensure automatic
+              cleanup of resources.
+            - No special initialization occurs during context entry, but enables
+              proper context-managed lifecycle.
 
         Example:
             with MyVectorStore(db_connection, embedder) as vectorstore:
@@ -468,7 +492,8 @@ def __exit__(
         exc_tb: Union[object, None],
     ) -> None:
         """
-        Exit the runtime context for the vector store, ensuring all storage resources are cleaned up.
+        Exit the runtime context for the vector store, ensuring all storage
+        resources are cleaned up.
 
         Args:
             exc_type: The exception type, if any exception occurred in the context block.

mysql-connector-python/lib/mysql/ai/ml/__init__.py

@@ -26,6 +26,13 @@
 # along with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA
 
+"""ML package for MySQL Connector/Python.
+
+Performs optional dependency checks and exposes ML utilities:
+- ML_TASK, MyModel
+- MyClassifier, MyRegressor, MyGenericTransformer
+- MyAnomalyDetector
+"""
 from mysql.ai.utils import check_dependencies as _check_dependencies
 
 _check_dependencies(["ML"])

mysql-connector-python/lib/mysql/ai/ml/base.py

@@ -26,15 +26,19 @@
 # along with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin St, Fifth Floor, Boston, MA 02110-1301  USA
 
+"""Base classes for MySQL HeatWave ML estimators for Connector/Python.
+
+Implements a scikit-learn-compatible base estimator wrapping server-side ML.
+"""
 from typing import Optional, Union
 
 import pandas as pd
 
-from mysql.ai.ml.model import ML_TASK, MyModel
-from mysql.ai.utils import copy_dict
 from sklearn.base import BaseEstimator
 
 from mysql.connector.abstracts import MySQLConnectionAbstract
+from mysql.ai.ml.model import ML_TASK, MyModel
+from mysql.ai.utils import copy_dict
 
 
 class MyBaseMLModel(BaseEstimator):
@@ -80,7 +84,11 @@ def __init__(
         self._model = MyModel(db_connection, task=task, model_name=model_name)
         self.fit_extra_options = copy_dict(fit_extra_options)
 
-    def fit(self, X: pd.DataFrame, y: Optional[pd.DataFrame] = None) -> "MyBaseMLModel":
+    def fit(
+        self,
+        X: pd.DataFrame,  # pylint: disable=invalid-name
+        y: Optional[pd.DataFrame] = None,
+    ) -> "MyBaseMLModel":
         """
         Fit the underlying ML model using pandas DataFrames.
         Delegates to MyMLModelPandasHelper.fit.
@@ -120,7 +128,8 @@ def _delete_model(self) -> bool:
 
     def get_model_info(self) -> Optional[dict]:
         """
-        Checks if the model name is available. Model info will only be present in the catalog if the model has previously been fitted.
+        Checks if the model name is available. Model info will only be present in the
+        catalog if the model has previously been fitted.
 
         Returns:
             True if the model name is not part of the model catalog