Hi

# code 1:

from llama_index import GPTVectorStoreIndex, ServiceContext

# storage_context = mongodb_storage_context()
embed_model = huggingface_embed_model()

# Set up the service context, i.e., the embedding model (and completion if used)
service_context = ServiceContext.from_defaults(embed_model=embed_model)

index_GPTVectorStoreIndex = GPTVectorStoreIndex(nodes=nodes,
                                service_context=service_context,
                                show_progress=True
                                )


# Code 2:

from llama_index import GPTSimpleKeywordTableIndex, ServiceContext

# storage_context = mongodb_storage_context()
embed_model = huggingface_embed_model()

# Set up the service context, i.e., the embedding model (and completion if used)
service_context = ServiceContext.from_defaults(embed_model=embed_model)

index_GPTSimpleKeywordTableIndex = GPTSimpleKeywordTableIndex(nodes=nodes,
                                service_context=service_context,
                                show_progress=True
                                )


# Verification: my metadata has url field

filter_nodes = [x for x in nodes if " " + query_term.lower() in x.text.lower()]
filter_nodes_urls = list(set([x.metadata["url"] for x in filter_nodes]))

retriever_nodes_GPTVectorStoreIndex_urls = []
for each_node in retriever_nodes_GPTVectorStoreIndex:
  for _node in nodes:
    if _node.id_ == each_node.id_:
      retriever_nodes_GPTVectorStoreIndex_urls.append(_node.metadata["url"])
      break

retriever_nodes_GPTVectorStoreIndex_urls = list(set(retriever_nodes_GPTVectorStoreIndex_urls))


retriever_nodes_GPTVectorStoreIndex_urls == filter_nodes_urls
False