refactor: apply pep-484 (#3542)

* apply pep-484

* another implicit optional

* apply pep-484 on rest_api and ui too

Author: ZanSara

haystack/document_stores/base.py

@@ -376,7 +376,7 @@ def add_eval_data(
         label_index: str = "label",
         batch_size: Optional[int] = None,
         preprocessor: Optional[PreProcessor] = None,
-        max_docs: Union[int, bool] = None,
+        max_docs: Optional[Union[int, bool]] = None,
         open_domain: bool = False,
         headers: Optional[Dict[str, str]] = None,
     ):
@@ -568,7 +568,7 @@ def get_documents_by_id(
         pass
 
     @abstractmethod
-    def update_document_meta(self, id: str, meta: Dict[str, Any], index: str = None):
+    def update_document_meta(self, id: str, meta: Dict[str, Any], index: Optional[str] = None):
         pass
 
     def _drop_duplicate_documents(self, documents: List[Document], index: Optional[str] = None) -> List[Document]:
@@ -633,7 +633,7 @@ def _handle_duplicate_documents(
         return documents
 
     def _get_duplicate_labels(
-        self, labels: list, index: str = None, headers: Optional[Dict[str, str]] = None
+        self, labels: list, index: Optional[str] = None, headers: Optional[Dict[str, str]] = None
     ) -> List[Label]:
         """
         Return all duplicate labels

haystack/document_stores/deepsetcloud.py

@@ -37,7 +37,7 @@ def wrapper(self, *args, **kwargs):
 class DeepsetCloudDocumentStore(KeywordDocumentStore):
     def __init__(
         self,
-        api_key: str = None,
+        api_key: Optional[str] = None,
         workspace: str = "default",
         index: Optional[str] = None,
         duplicate_documents: str = "overwrite",
@@ -603,7 +603,7 @@ def write_documents(
         pass
 
     @disable_and_log
-    def update_document_meta(self, id: str, meta: Dict[str, Any], index: str = None):
+    def update_document_meta(self, id: str, meta: Dict[str, Any], index: Optional[str] = None):
         """
         Update the metadata dictionary of a document by specifying its string id.
 

haystack/document_stores/faiss.py

@@ -42,7 +42,7 @@ class FAISSDocumentStore(SQLDocumentStore):
     def __init__(
         self,
         sql_url: str = "sqlite:///faiss_document_store.db",
-        vector_dim: int = None,
+        vector_dim: Optional[int] = None,
         embedding_dim: int = 768,
         faiss_index_factory_str: str = "Flat",
         faiss_index: Optional[faiss.swigfaiss.Index] = None,
@@ -52,9 +52,9 @@ def __init__(
         embedding_field: str = "embedding",
         progress_bar: bool = True,
         duplicate_documents: str = "overwrite",
-        faiss_index_path: Union[str, Path] = None,
-        faiss_config_path: Union[str, Path] = None,
-        isolation_level: str = None,
+        faiss_index_path: Optional[Union[str, Path]] = None,
+        faiss_config_path: Optional[Union[str, Path]] = None,
+        isolation_level: Optional[str] = None,
         n_links: int = 64,
         ef_search: int = 20,
         ef_construction: int = 80,

haystack/document_stores/memory.py

@@ -485,7 +485,7 @@ def get_document_count(
         )
         return len(documents)
 
-    def update_document_meta(self, id: str, meta: Dict[str, Any], index: str = None):
+    def update_document_meta(self, id: str, meta: Dict[str, Any], index: Optional[str] = None):
         """
         Update the metadata dictionary of a document by specifying its string id.
 
@@ -639,7 +639,7 @@ def get_all_documents_generator(
 
     def get_all_labels(
         self,
-        index: str = None,
+        index: Optional[str] = None,
         filters: Optional[Dict[str, Any]] = None,  # TODO: Adapt type once we allow extended filters in InMemoryDocStore
         headers: Optional[Dict[str, str]] = None,
     ) -> List[Label]:

haystack/document_stores/milvus1.py

@@ -46,7 +46,7 @@ def __init__(
         milvus_url: str = "tcp://localhost:19530",
         connection_pool: str = "SingletonThread",
         index: str = "document",
-        vector_dim: int = None,
+        vector_dim: Optional[int] = None,
         embedding_dim: int = 768,
         index_file_size: int = 1024,
         similarity: str = "dot_product",
@@ -57,7 +57,7 @@ def __init__(
         embedding_field: str = "embedding",
         progress_bar: bool = True,
         duplicate_documents: str = "overwrite",
-        isolation_level: str = None,
+        isolation_level: Optional[str] = None,
     ):
         """
         **WARNING:** Milvus1DocumentStore is deprecated and will be removed in a future version. Please switch to Milvus2

haystack/document_stores/milvus2.py

@@ -61,7 +61,7 @@ def __init__(
         port: str = "19530",
         connection_pool: str = "SingletonThread",
         index: str = "document",
-        vector_dim: int = None,
+        vector_dim: Optional[int] = None,
         embedding_dim: int = 768,
         index_file_size: int = 1024,
         similarity: str = "dot_product",
@@ -74,7 +74,7 @@ def __init__(
         custom_fields: Optional[List[Any]] = None,
         progress_bar: bool = True,
         duplicate_documents: str = "overwrite",
-        isolation_level: str = None,
+        isolation_level: Optional[str] = None,
         consistency_level: int = 0,
         recreate_index: bool = False,
     ):

haystack/document_stores/pinecone.py

@@ -762,7 +762,7 @@ def get_documents_by_id(
         batch_size: int = 32,
         headers: Optional[Dict[str, str]] = None,
         return_embedding: Optional[bool] = None,
-        namespace: str = None,
+        namespace: Optional[str] = None,
     ) -> List[Document]:
         """
         Retrieves all documents in the index using their IDs.
@@ -826,7 +826,7 @@ def get_document_by_id(
         index: Optional[str] = None,
         headers: Optional[Dict[str, str]] = None,
         return_embedding: Optional[bool] = None,
-        namespace: str = None,
+        namespace: Optional[str] = None,
     ) -> Document:
         """
         Returns a single Document retrieved using an ID.
@@ -869,7 +869,7 @@ def get_embedding_count(
             count = 0
         return count
 
-    def update_document_meta(self, id: str, meta: Dict[str, str], namespace: str = None, index: str = None):  # type: ignore
+    def update_document_meta(self, id: str, meta: Dict[str, str], namespace: Optional[str] = None, index: Optional[str] = None):  # type: ignore
         """
         Update the metadata dictionary of a document by specifying its string ID.
 

haystack/document_stores/search_engine.py

@@ -487,7 +487,7 @@ def write_labels(
             self._bulk(labels_to_index, request_timeout=300, refresh=self.refresh_type, headers=headers)
 
     def update_document_meta(
-        self, id: str, meta: Dict[str, str], index: str = None, headers: Optional[Dict[str, str]] = None
+        self, id: str, meta: Dict[str, str], index: Optional[str] = None, headers: Optional[Dict[str, str]] = None
     ):
         """
         Update the metadata dictionary of a document by specifying its string id

haystack/document_stores/sql.py

@@ -129,7 +129,7 @@ def __init__(
         label_index: str = "label",
         duplicate_documents: str = "overwrite",
         check_same_thread: bool = False,
-        isolation_level: str = None,
+        isolation_level: Optional[str] = None,
     ):
         """
         An SQL backed DocumentStore. Currently supports SQLite, PostgreSQL and MySQL backends.
@@ -524,7 +524,7 @@ def reset_vector_ids(self, index: Optional[str] = None):
         self.session.query(DocumentORM).filter_by(index=index).update({DocumentORM.vector_id: null()})
         self.session.commit()
 
-    def update_document_meta(self, id: str, meta: Dict[str, str], index: str = None):
+    def update_document_meta(self, id: str, meta: Dict[str, str], index: Optional[str] = None):
         """
         Update the metadata dictionary of a document by specifying its string id
         """

haystack/document_stores/utils.py

@@ -17,7 +17,10 @@
 
 
 def eval_data_from_json(
-    filename: str, max_docs: Union[int, bool] = None, preprocessor: PreProcessor = None, open_domain: bool = False
+    filename: str,
+    max_docs: Optional[Union[int, bool]] = None,
+    preprocessor: Optional[PreProcessor] = None,
+    open_domain: bool = False,
 ) -> Tuple[List[Document], List[Label]]:
     """
     Read Documents + Labels from a SQuAD-style file.
@@ -58,8 +61,8 @@ def eval_data_from_json(
 def eval_data_from_jsonl(
     filename: str,
     batch_size: Optional[int] = None,
-    max_docs: Union[int, bool] = None,
-    preprocessor: PreProcessor = None,
+    max_docs: Optional[Union[int, bool]] = None,
+    preprocessor: Optional[PreProcessor] = None,
     open_domain: bool = False,
 ) -> Generator[Tuple[List[Document], List[Label]], None, None]:
     """
@@ -123,7 +126,7 @@ def squad_json_to_jsonl(squad_file: str, output_file: str):
 
 
 def _extract_docs_and_labels_from_dict(
-    document_dict: Dict, preprocessor: PreProcessor = None, open_domain: bool = False
+    document_dict: Dict, preprocessor: Optional[PreProcessor] = None, open_domain: bool = False
 ):
     """
     Set open_domain to True if you are trying to load open_domain labels (i.e. labels without doc id or start idx)