Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #5754] [BUG] (NOT SURE): uploading an XLSX file via API, the document list shows the internal sheet name (e.g., 'sheet-START') instead of the original filename (e.g., 'Book1.xlsx') #5276

New Issue
Closed
opened 2026-06-05 14:53:04 -04:00 by yindo · 2 comments
yindo commented 2026-06-05 14:53:04 -04:00
Owner
Copy Link
Copy Source

Originally created by @ohromeo on GitHub (Jun 4, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5754

Originally assigned to: @timothycarambat on GitHub.

How are you running AnythingLLM?

Docker (local)

What happened?

created a new fancy /insights command to review spreadsheets..
uploaded test SS book1.xlsx in allm frontend (docker), appears as:

Image

Move to workspace:

Image

Save and Embed

Image

in my front-end via API, documents displayed as:

Image

uploading from my front-end:

Image

running "/insights"
I cannot review the file because you did not provide a filename or upload a file in your message. Please upload a spreadsheet file (.xlsx, .xls, .csv, .ods, or .numbers) so I can analyze it.

BUT:
running: /insights book1.xlsx -- returns correctly:

"Data Analysis Report: Personal Monthly Budget

  1. Data Overview
    This dataset contains a personal monthly budget spreadsheet with projected and actual costs across multiple expense categories (Utilities, Transportation, Insurance, Taxes, Loans, Entertainment, and Savings).

  2. Key Highlights (The "Headlines")..."

When uploading an XLSX file via the GUI displays 2 spreadsheets , via API the document list shows the internal sheet name (e.g., 'sheet-START') instead of the original filename (e.g., 'Book1.xlsx').

  1. Is this a bug or intentional behavior?

  2. Since the /document/upload API accepts a metadata field containing the original_filename , why is this value not being used as the primary display name in the workspace documents list for XLSX files?

  3. Is there a specific API endpoint or parameter to force the system to use the, uploaded filename instead of the parsed sheet name?"

  4. not sure why it uploaded 2 files, it recognized "sheet-PERSONAL-MONTHLY-BUDGET" as a SS

all other document types work/display correctly, except for spreadsheets.

Thanks!

Are there known steps to reproduce?

see above

LLM Provider & Model (if applicable)

N/A

Embedder Provider & Model (if applicable)

N/A

Originally created by @ohromeo on GitHub (Jun 4, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5754 Originally assigned to: @timothycarambat on GitHub. ### How are you running AnythingLLM? Docker (local) ### What happened? created a new fancy /insights command to review spreadsheets.. uploaded test SS book1.xlsx in allm frontend (docker), appears as: <img width="527" height="136" alt="Image" src="https://github.com/user-attachments/assets/99d0965d-e7f2-4957-bd45-fc2759cc60ed" /> Move to workspace: <img width="577" height="190" alt="Image" src="https://github.com/user-attachments/assets/3c61bb7b-6153-4fea-a1c5-0696343f8cd1" /> Save and Embed <img width="711" height="126" alt="Image" src="https://github.com/user-attachments/assets/21358b11-8270-405e-9b8b-3aeaabdbdfb5" /> in my front-end via API, documents displayed as: <img width="396" height="297" alt="Image" src="https://github.com/user-attachments/assets/edf27eae-90d1-449f-873e-96e5a5ac4279" /> uploading from my front-end: <img width="387" height="130" alt="Image" src="https://github.com/user-attachments/assets/a6803b5d-ac91-4086-8666-b21f493b05a8" /> running "/insights" I cannot review the file because you did not provide a filename or upload a file in your message. Please upload a spreadsheet file (.xlsx, .xls, .csv, .ods, or .numbers) so I can analyze it. BUT: running: /insights book1.xlsx -- returns correctly: "Data Analysis Report: Personal Monthly Budget 1. Data Overview This dataset contains a personal monthly budget spreadsheet with projected and actual costs across multiple expense categories (Utilities, Transportation, Insurance, Taxes, Loans, Entertainment, and Savings). 2. Key Highlights (The "Headlines")..." When uploading an XLSX file via the GUI displays 2 spreadsheets , via API the document list shows the internal sheet name (e.g., 'sheet-START') instead of the original filename (e.g., 'Book1.xlsx'). 1. Is this a bug or intentional behavior? 2. Since the /document/upload API accepts a metadata field containing the original_filename , why is this value not being used as the primary display name in the workspace documents list for XLSX files? 3. Is there a specific API endpoint or parameter to force the system to use the, uploaded filename instead of the parsed sheet name?" 4. not sure why it uploaded 2 files, it recognized "sheet-PERSONAL-MONTHLY-BUDGET" as a SS all other document types work/display correctly, except for spreadsheets. Thanks! ### Are there known steps to reproduce? see above ### LLM Provider & Model (if applicable) N/A ### Embedder Provider & Model (if applicable) N/A
yindo added the possible buginvestigating labels 2026-06-05 14:53:04 -04:00
yindo closed this issue 2026-06-05 14:53:04 -04:00
yindo commented 2026-06-05 14:53:05 -04:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 5, 2026):

Sheet START is weird, assuming you have a single-sheet XLSX file that should not be there. That being said we always split sheets for embedding and processing since - https://github.com/Mintplex-Labs/anything-llm/blob/master/collector/processSingleFile/convert/asXlsx.js is what is handling that.

Do you have an example request of what your frontend is send so that we can try to repro this. Also I want to confirm the actual data here. This is a single sheet XSLX?

<!-- gh-comment-id:4632638709 --> @timothycarambat commented on GitHub (Jun 5, 2026): Sheet START is weird, assuming you have a single-sheet XLSX file that should not be there. That being said we always split sheets for embedding and processing since - https://github.com/Mintplex-Labs/anything-llm/blob/master/collector/processSingleFile/convert/asXlsx.js is what is handling that. Do you have an example request of what your frontend is send so that we can try to repro this. Also I want to confirm the actual data here. This is a single sheet XSLX?
yindo commented 2026-06-07 16:36:38 -04:00
Author
Owner
Copy Link
Copy Source

@ohromeo commented on GitHub (Jun 5, 2026):

ahhh ok.. i see you are pulling out the sheets into separate entities.....
yes, there 2 sheets.

so since they are not "spreadsheets" - i suspect i have to alter my slash command to not check for SS types?
`
You are an expert Data Analyst AI. Review the uploaded spreadsheet file "{filename}". Your task is to act exactly like Microsoft Excel's "Analyze Data" (formerly Insights) feature and the Copilot for Excel assistant.

First, check the uploaded file type. If the file is NOT a spreadsheet (.xlsx, .xls, .csv), immediately stop and respond with EXACTLY:

" Sorry, this doesn't appear to be a spreadsheet. Only Microsoft.xls and .xls(x) formats are currently supported."

Do not attempt any analysis. Do not apologize or explain further.
...
`

Image

Book 1.xlsx

<!-- gh-comment-id:4636388624 --> @ohromeo commented on GitHub (Jun 5, 2026): ahhh ok.. i see you are pulling out the sheets into separate entities..... yes, there 2 sheets. so since they are not "spreadsheets" - i suspect i have to alter my slash command to not check for SS types? ` You are an expert Data Analyst AI. Review the uploaded spreadsheet file "{filename}". Your task is to act exactly like Microsoft Excel's "Analyze Data" (formerly Insights) feature and the Copilot for Excel assistant. **First, check the uploaded file type. If the file is NOT a spreadsheet (.xlsx, .xls, .csv), immediately stop and respond with EXACTLY:** " Sorry, this doesn't appear to be a spreadsheet. Only Microsoft.xls and .xls(x) formats are currently supported." Do not attempt any analysis. Do not apologize or explain further. ... ` <img width="387" height="71" alt="Image" src="https://github.com/user-attachments/assets/2163a441-13b9-4a98-8ec1-1d64e59f4571" /> [Book 1.xlsx](https://github.com/user-attachments/files/28656527/Book.1.xlsx)
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label investigating possible bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#5276
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?