LlamaParse JSON Output for an XLSX File contains null elements in the table #545

Open
opened 2026-02-16 00:18:12 -05:00 by yindo · 0 comments
Owner

Originally created by @doyeka on GitHub (Oct 1, 2025).

Describe the bug
The JSON output for parsing XLSX files includes null for empty cells. It was previously empty strings if I remember correctly.

  1. Is this expected behavior?
  2. Is there documentation that references the expected JSON output for XLSX files?

Files
q4 direct to funnel ad copies.xlsx

Job ID
2f14150a-f013-4aa1-a5b0-b12af85ec8ae

Client:
Please remove untested options:

  • Python Library

Additional context
My call to LlamaParse is as follows:

    parser = LlamaParse(
        language=llama_language,
        api_key=settings.LLAMAPARSE_API_KEY,  # LlamaParse will try to detect long table and adapt the output
        parse_mode="parse_page_with_layout_agent",
        adaptive_long_table=True,
        outlined_table_extraction=True,  # Whether to try to extract outlined tables
        high_res_ocr=True,  # Whether to use high resolution OCR (slower but more precise)
        output_tables_as_HTML=True,
        replace_failed_page_mode="raw_text",
    )
   json_result = await parser.aget_json(file_path)
Originally created by @doyeka on GitHub (Oct 1, 2025). **Describe the bug** The JSON output for parsing XLSX files includes `null` for empty cells. It was previously empty strings if I remember correctly. 1) Is this expected behavior? 2) Is there documentation that references the expected JSON output for XLSX files? **Files** [q4 direct to funnel ad copies.xlsx](https://github.com/user-attachments/files/22648800/q4.direct.to.funnel.ad.copies.xlsx) **Job ID** 2f14150a-f013-4aa1-a5b0-b12af85ec8ae **Client:** Please remove untested options: - Python Library **Additional context** My call to LlamaParse is as follows: ``` parser = LlamaParse( language=llama_language, api_key=settings.LLAMAPARSE_API_KEY, # LlamaParse will try to detect long table and adapt the output parse_mode="parse_page_with_layout_agent", adaptive_long_table=True, outlined_table_extraction=True, # Whether to try to extract outlined tables high_res_ocr=True, # Whether to use high resolution OCR (slower but more precise) output_tables_as_HTML=True, replace_failed_page_mode="raw_text", ) json_result = await parser.aget_json(file_path) ```
yindo added the bug label 2026-02-16 00:18:12 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#545