PGVectorStore. In PineCone we used different indexes for different documents to limit the replies to a particular document/scope. I was wondering what the equivalent would in PGVectoreStore. Do you recommend setting up a new table for each "context"/"namespace"?KeywordExtractor and specified keywords=5 as a param. But yet in my postgres DB i find up to 50 keywords per document chunk. Is this normal?DocumentSummaryIndex.from_documents and using load_index_from_storagegpt-3.5-turbo-1106 produces significantly worse results as the old gpt-3.5-turbo-16k-0613 PyMuPDFReader = download_loader("PDFReader")
loader = PyMuPDFReader()
documents = loader.load_data(file=Path("./test-doc2.pdf"))
# Create and store Summray index
storage_context = StorageContext.from_defaults()
index = DocumentSummaryIndex.from_documents(
documents,
service_context=service_context,
storage_context=storage_context,
show_progress=True,
)
query_engine = index.as_query_engine()
result = query_engine.query("Write an extensive summary of this context for me?")
print(result)service_context does NOT update unless I restart the entire application, has anyone run into this issue before? set_global_service_context(service_context)
vector_store = PineconeVectorStore(
pinecone_index=PINECONE_INDEX, namespace=namespace
)
storage_context = StorageContext.from_defaults(
docstore=DOCUMENT_STORE,
index_store=INDEX_STORE,
vector_store=vector_store,
)
print(service_context)
return VectorStoreIndex.from_vector_store(
vector_store=vector_store,
storage_context=storage_context,
service_context=service_context,
)tree-sitter-languages and Tree Sitter doesnt have a build for Mac: https://github.com/grantjenks/py-tree-sitter-languages/issues/20