The community member is experiencing an issue with the index.refresh_ref_docs(documents) function using the VectorStoreIndex in the Llama-index library version 0.7.15. The error they are encountering is a KeyError: '6dd96c06-9775-47c6-ab65-a30f235a3a7f', which occurs sporadically. The community member is using the Llama-index library and its related components, such as LLMPredictor, ServiceContext, Document, and StorageContext, but they are not using an external vector database integration.
index.refresh_ref_docs(documents) using the VectorStoreIndex thows this error sporadically "KeyError: '6dd96c06-9775-47c6-ab65-a30f235a3a7f'" . stack trace below. This is with Llama-index 0.7.15
File "/crawler.py", line 37, in add_page_to_index retval = index.refresh_ref_docs(documents) File "/env/lib/python3.10/site-packages/llama_index/indices/base.py", line 313, in refresh_ref_docs self.update_ref_doc( File "/env/lib/python3.10/site-packages/llama_index/indices/base.py", line 277, in update_ref_doc self.delete_ref_doc( File "/env/lib/python3.10/site-packages/llama_index/indices/vector_store/base.py", line 288, in delete_ref_doc self._index_struct.delete(node_id) File "/env/lib/python3.10/site-packages/llama_index/data_structs/data_structs.py", line 198, in delete del self.nodes_dict[doc_id] KeyError: '6dd96c06-9775-47c6-ab65-a30f235a3a7f'
Are you asking me if i am using an external database. I believe the answer is no. I am using what is wrapped in llama-index. these are my vector store related imports from llama_index import LLMPredictor, ServiceContext, VectorStoreIndex, Document,StorageContext, load_index_from_storage
