Hey guys, I have tried to find an answer to this but to no avail.
For some reason the S3 loader (eg: https://docs.llamaindex.ai/en/stable/examples/data_connectors/simple_directory_reader_remote_fs/)

Fails to load/parse pdf files from my S3 bucket, but suceeds on .txt files.
Did someone encounter a similar issue? Any help would be much appreciated!

I want to load the sentence + metadata index from a persisted directory (where I have saved the relevant docstore, indexstore and vectorstore json files). Does anyone have a code snippet how we might do so? Because when I call :

storage_context_s = StorageContext.from_defaults(
docstore=SimpleDocumentStore.from_persist_dir(persist_dir=r"persist_dir"),
vector_store=SimpleVectorStore.from_persist_dir(persist_dir=r"persist_dir"),
index_store=SimpleIndexStore.from_persist_dir(persist_dir=r"persist_dir"),
)

load_indices_from_storage

load_index_from_storage

sentence_index = load_indices_from_storage(storage_context_s)

query_engine = sentence_index.as_query_engine(
similarity_top_k=2,
# the target key defaults to window to match the node_parser's default
node_postprocessors=[
MetadataReplacementPostProcessor(target_metadata_key="window")
],
)
window_response = query_engine.query(
"Who is xxx?"
)
print(window_response)

I later get:

AttributeError: 'list' object has no attribute 'as_query_engine'

Help would be much obliged

Hi, I am building a RAG app on top of llamaindex, and would want to store data from knowledge graph and summary index (the json files that are created when you persist the storage_context) remotely to a cloud Db (something like MongoDB). I cant find any good example of how to do so (since I created the knowledge graph by running code on parallel on AWS), and would now just want to save the indexes/jsons on a remote DB. If some of you habe faced similar issues, help would be much appreciated!!

Hi good people! When are we getting the RAPTOR paper implementation in llamaindex (https://twitter.com/IntuitMachine/status/1753057138438492530)? Seems to fit perfectly for this framework

Hi All,
What the current consensus on whats the best way to ingest finance data (complex pdfs with tables and excel files) in llamaindex? Currently I find the best result with the UnstructuredReader. Does anyone have a different experience?
Thanks