utils. Bugfix QdrantVectorStoreManager to use langchain_core's Document

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/psf/black
-    rev: 24.8.0
+    rev: 25.1.0
     hooks:
       - id: black
         name: Format Python code with black

knowledge_storm/collaborative_storm/modules/grounded_question_generation.py

@@ -1,7 +1,7 @@
 """
 This module handles question generation within the Co-STORM framework, specifically designed to support the Moderator role.
 
-The Moderator generates insightful, thought-provoking questions that introduce new directions into the conversation. 
+The Moderator generates insightful, thought-provoking questions that introduce new directions into the conversation.
 By leveraging uncited or unused snippets of information retrieved during the discussion, the Moderator ensures the conversation remains dynamic and avoids repetitive or overly niche topics.
 
 For more detailed information, refer to Section 3.5 of the Co-STORM paper: https://www.arxiv.org/pdf/2408.15232.

knowledge_storm/collaborative_storm/modules/warmstart_hierarchical_chat.py

@@ -1,10 +1,10 @@
 """
 Warm starts the Co-STORM system by conducting a background information search to establish a shared conceptual space with the user.
- 
-This stage functions as a mini-STORM, where multiple LLM agents are spawned with different perspectives to engage in multi-round conversations. 
+
+This stage functions as a mini-STORM, where multiple LLM agents are spawned with different perspectives to engage in multi-round conversations.
 The knowledge base (represented as a mind map) is initialized using the information gathered during these exchanges.
 
-Additionally, the system generates a first draft of the report, which is then used to create a concise and engaging conversation. 
+Additionally, the system generates a first draft of the report, which is then used to create a concise and engaging conversation.
 The synthesized conversation is presented to the user to help them quickly catch up on the system's current knowledge about the topic.
 """
 

knowledge_storm/storm_wiki/modules/storm_dataclass.py

@@ -64,7 +64,7 @@ def __init__(self, conversations=List[Tuple[str, List[DialogueTurn]]]):
 
     @staticmethod
     def construct_url_to_info(
-        conversations: List[Tuple[str, List[DialogueTurn]]]
+        conversations: List[Tuple[str, List[DialogueTurn]]],
     ) -> Dict[str, Information]:
         url_to_info = {}
 
@@ -81,7 +81,7 @@ def construct_url_to_info(
 
     @staticmethod
     def construct_log_dict(
-        conversations: List[Tuple[str, List[DialogueTurn]]]
+        conversations: List[Tuple[str, List[DialogueTurn]]],
     ) -> List[Dict[str, Union[str, Any]]]:
         conversation_log = []
         for persona, conv in conversations:

knowledge_storm/utils.py

@@ -166,7 +166,7 @@ def create_or_update_vector_store(
         embedding_model: str = "BAAI/bge-m3",
         device: str = "mps",
     ):
-        from qdrant_client import Document
+        from langchain_core.documents.base import Document
 
         """
         Takes a CSV file and adds each row in the CSV file to the Qdrant collection.
@@ -278,7 +278,7 @@ def create_or_update_vector_store(
                 "\uff0c",  # Fullwidth comma
                 "\u3001",  # Ideographic comma
                 " ",
-                "\u200B",  # Zero-width space
+                "\u200b",  # Zero-width space
                 "",
             ],
         )
@@ -666,7 +666,7 @@ def __init__(
                 "\uff0c",  # Fullwidth comma
                 "\u3001",  # Ideographic comma
                 " ",
-                "\u200B",  # Zero-width space
+                "\u200b",  # Zero-width space
                 "",
             ],
         )