AILlamaParse reportedly keeps Fed forecast data aligned despite a blank cell
LlamaIndex says all nine numbers in a displayed GDP median excerpt matched the original Fed PDF, while LlamaParse’s HTML output kept the data aligned.
TLDR
LlamaIndex says the Fed’s September 2026 projections table has a 2029 column with an empty cell in the June comparison row—a layout it describes as a common failure point for document parsers. It says it parsed page 2 with LlamaParse and checked the displayed GDP median excerpt against the original PDF: all nine numbers matched, and the returned HTML kept the data aligned.
