[CI Refactoring] Refactor Document fixtures in tests

docs/_src/api/api/crawler.md

@@ -88,7 +88,7 @@ List of paths where the crawled webpages got stored
 #### Crawler.run
 
 ```python
-def run(output_dir: Union[str, Path, None] = None, urls: Optional[List[str]] = None, crawler_depth: Optional[int] = None, filter_urls: Optional[List] = None, overwrite_existing_files: Optional[bool] = None, return_documents: Optional[bool] = False, id_hash_keys: Optional[List[str]] = None, extract_hidden_text: Optional[bool] = True) -> Tuple[Dict, str]
+def run(output_dir: Union[str, Path, None] = None, urls: Optional[List[str]] = None, crawler_depth: Optional[int] = None, filter_urls: Optional[List] = None, overwrite_existing_files: Optional[bool] = None, return_documents: Optional[bool] = False, id_hash_keys: Optional[List[str]] = None, extract_hidden_text: Optional[bool] = True) -> Tuple[Dict[str, Union[List[Document], List[Path]]], str]
 ```
 
 Method to be executed when the Crawler is used as a Node within a Haystack pipeline.

docs/_src/api/api/primitives.md

@@ -79,7 +79,7 @@ dict with content of the Document
 
 ```python
 @classmethod
-def from_dict(cls, dict, field_map={}, id_hash_keys=None)
+def from_dict(cls, dict: Dict[str, Any], field_map: Dict[str, Any] = {}, id_hash_keys: Optional[List[str]] = None) -> Document
 ```
 
 Create Document from dict. An optional field_map can be supplied to adjust for custom names of the keys in the

haystack/document_stores/pinecone.py

@@ -256,7 +256,7 @@ def write_documents(
                         if self.similarity == "cosine":
                             self.normalize_embedding(embeddings_to_index)
                         # Convert embeddings to list objects
-                        embeddings = [embed.tolist() for embed in embeddings]
+                        embeddings = [embed.tolist() if embed is not None else None for embed in embeddings]
                         data_to_write_to_pinecone = zip(ids, embeddings, metadata)
                         # Metadata fields and embeddings are stored in Pinecone
                         self.pinecone_indexes[index].upsert(vectors=data_to_write_to_pinecone)

haystack/document_stores/sql.py

@@ -376,10 +376,7 @@ def write_documents(
         if len(documents) == 0:
             return
         # Make sure we comply to Document class format
-        if isinstance(documents[0], dict):
-            document_objects = [Document.from_dict(d) if isinstance(d, dict) else d for d in documents]
-        else:
-            document_objects = documents
+        document_objects = [Document.from_dict(d) if isinstance(d, dict) else d for d in documents]
 
         document_objects = self._handle_duplicate_documents(
             documents=document_objects, index=index, duplicate_documents=duplicate_documents

haystack/nodes/connector/crawler.py

@@ -232,7 +232,7 @@ def run(  # type: ignore
         return_documents: Optional[bool] = False,
         id_hash_keys: Optional[List[str]] = None,
         extract_hidden_text: Optional[bool] = True,
-    ) -> Tuple[Dict, str]:
+    ) -> Tuple[Dict[str, Union[List[Document], List[Path]]], str]:
         """
         Method to be executed when the Crawler is used as a Node within a Haystack pipeline.
 
@@ -263,6 +263,7 @@ def run(  # type: ignore
             overwrite_existing_files=overwrite_existing_files,
             extract_hidden_text=extract_hidden_text,
         )
+        results: Dict[str, Union[List[Document], List[Path]]] = {}
         if return_documents:
             crawled_data = []
             for _file in file_paths:

haystack/schema.py

@@ -161,7 +161,9 @@ def to_dict(self, field_map={}) -> Dict:
         return _doc
 
     @classmethod
-    def from_dict(cls, dict, field_map={}, id_hash_keys=None):
+    def from_dict(
+        cls, dict: Dict[str, Any], field_map: Dict[str, Any] = {}, id_hash_keys: Optional[List[str]] = None
+    ) -> Document:
         """
         Create Document from dict. An optional field_map can be supplied to adjust for custom names of the keys in the
         input dict. This way you can work with standardized Document objects in Haystack, but adjust the format that