can propertygraphindex be used with a retriever with a metadata filter? Also wondering about adding a document node along with the chunks nodes with edges, seems like the document itself not exising in neo4j is going to be an issue down the line

If im using propertygraphindex with neo4j and weaviage and i want to store the node embeddings in both but only caclaute then in weaviate (using t2vectransf), how do i setup the embedding pipeline. Should i add to the weaviate index then retrieve embeddings from weaviage then add them to the nodes for the propertygraphindex with ember nodes as false?

running this with weaviate and neo4j
index = PropertyGraphIndex.from_existing(
property_graph_store=graph_store,

vector_store=vector_store,
embed_kg_nodes=True,
)
as per https://docs.llamaindex.ai/en/stable/module_guides/indexing/lpg_index_guide/
and im getting
AttributeError: property 'vector_store' of 'StorageContext' object has no setter

also:
index = PropertyGraphIndex.from_existing(
property_graph_store=graph_store,
vector_store=vector_store,
embed_kg_nodes=True,
)
File c:\Users\.virtualenvs\cypher-5_nblxkf\Lib\site-packages\llama_index\core\indices\property_graph\base.py:129, in PropertyGraphIndex.init(self, nodes, llm, kg_extractors, property_graph_store, vector_store, use_async, embed_model, embed_kg_nodes, callback_manager, transformations, storage_context, show_progress, **kwargs)
...
412 except ValueError:
--> 413 raise ValueError("Not valid 'uuid' or 'uuid' can not be extracted from value") from None
414 return _uuid