Hello everyone !!! i would like some help/opinion. what "parsing instructions" would you use with llama-parse to extract only text and tables from a textbook like the one in the image ?

i am trying and trying again with multiple instructions, but it is obvious that i can't exploit this great functionality properly. I mainly use "accurate" and "premium-mode." Any suggestions are welcome ! thank you very much.

hello @Logan M ! sorry to bother you. is it possible that the reranker is skipped using the chat_engine on a query_engine and memory_buffer with context mode ? I am using cohere as the reranker, as specified in the example notebook.I checked the use of the api key in the Coehere dashboard and it doesn't seem to receive calls.


 # Define the QueryFusionRetriever
retriever = QueryFusionRetriever(
[vector_retriever, bm25_retriever],
similarity_top_k=20,
num_queries=4,
mode="reciprocal_rerank",
use_async=True,
verbose=True,
)

# Define the query engine with the reranker as a postprocessor
query_engine = RetrieverQueryEngine.from_args(
callback_manager=callback_manager,
retriever=retriever,
response_mode="compact",
verbose=True,
node_postprocessors=[reranker]
)

memory = ChatMemoryBuffer.from_defaults(chat_history=messages or [])

## Define the Chat engine on Quey engine with memory buffer and context mode as query
chat_engine = index.as_chat_engine(
query_engine=query_engine,
chat_mode="context",
memory=memory,
verbose=True
)

hello everyone ! for llama-index, is it possible to implement the capabilities of KnowledgeGraph (Grafoù Properties) in a workflow that already uses QueryFusionRetriever, by merging bm25 + vector retriving ?

hi! does anyone know how to correctly import SmartPDFLoader ? i tried

'from llama_index.readers.smart_pdf_loader import SmartPDFLoader'

but it doesn't seem to work.