I have started getting this error in subquestionoutputparser
sub_questions = [SubQuestion.parse_obj(item) for item in json_dict]
File "pydantic/main.py", line 525, in pydantic.main.BaseModel.parse_obj
pydantic.error_wrappers.ValidationError: 1 validation error for SubQuestion
root
SubQuestion expected dict not str (type=type_error)

@kapa.ai I am getting this error while i was working on SubQuestionQueryEngine Following is the trace:
IndexError Traceback (most recent call last)

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/llama_index/response_synthesizers/base.py:119, in BaseSynthesizer.synthesize(self, query, nodes, additional_source_nodes)
113 def synthesize(
114 self,
115 query: QueryTextType,
116 nodes: List[NodeWithScore],
117 additional_source_nodes: Optional[Sequence[NodeWithScore]] = None,
118 ) -> RESPONSE_TYPE:
--> 119 event_id = self._callback_manager.on_event_start(CBEventType.SYNTHESIZE)
121 if isinstance(query, str):
122 query = QueryBundle(query_str=query)

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/llama_index/callbacks/base.py:91, in CallbackManager.on_event_start(self, event_type, payload, event_id, **kwargs)
89 """Run handlers when an event starts and return id of event."""
90 event_id = event_id or str(uuid.uuid4())
---> 91 self._trace_map[self._trace_stack[-1]].append(event_id)
92 for handler in self.handlers:
93 if event_type not in handler.event_starts_to_ignore:

IndexError: list index out of range

@kapa.ai What is the best method to create, store, and subsequently filter metadata when generating and storing embeddings?