run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 01:15:06 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Issue with LlamaParse : bBox hight is not correct #247

New Issue
Open
opened 2026-02-16 00:17:16 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:16 -05:00
Owner
Copy Link
Copy Source

Originally created by @abhishek9998 on GitHub (Aug 28, 2024).

Originally assigned to: @hexapode on GitHub.

Note: we're aware of some missing content in the output and layout issues on tables. Please refrain from opening new issues on this topic unless if you think it's different from what has already been reported.

Describe the bug
The bBox height returned by LlamaParse is incorrect. When processing a document, the bounding box dimensions provided for text elements are not accurate, leading to issues with layout and formatting detection. Here in attachment you can see it is only showing first line not whole paragraph.

Files
Unfortunately, I am unable to provide the PDF file causing the issue at this time.

Job ID
b6c798ed-0c0b-43aa-beca-8e972bf74c20

Screenshots

    "id": null,
    "metadata": {
        "bBox": "{'x': 126, 'y': 545.9, 'w': 380.9630999999997, 'h': 12}",
        "data_type": "raw",
        "end_index": 537,
        "source": "share-point",
        "start_index": 0
    },
    "page_content": "Employees CANNOT possess or use any weapons at any time, on any of the ‘Name of the Company’ owned, leased, or controlled property. This includes any place where the company’s business is conducted, like customer locations, trade shows, client locations, company event venues, restaurants, and so forth. The ban stays even for the places where the employee represents the company. Concealed weapons are prohibited on any company property regardless of whether they own a concealed weapons permit or are legally allowed to carry a weapon.",
    "type": "Document"
}

image
image

Client
NA

Options
Default one with accurate

Additional context
The issue with the bBox height seems to affect the rendering and analysis of document layout. Accurate bounding box measurements are crucial for correct text positioning and formatting interpretation. This bug is causing problems with subsequent processing and utilization of extracted text.

Originally created by @abhishek9998 on GitHub (Aug 28, 2024). Originally assigned to: @hexapode on GitHub. _Note: we're aware of some missing content in the output and layout issues on tables. Please refrain from opening new issues on this topic unless if you think it's different from what has already been reported._ **Describe the bug** The `bBox` height returned by LlamaParse is incorrect. When processing a document, the bounding box dimensions provided for text elements are not accurate, leading to issues with layout and formatting detection. Here in attachment you can see it is only showing first line not whole paragraph. **Files** Unfortunately, I am unable to provide the PDF file causing the issue at this time. **Job ID** b6c798ed-0c0b-43aa-beca-8e972bf74c20 **Screenshots** ```{ "id": null, "metadata": { "bBox": "{'x': 126, 'y': 545.9, 'w': 380.9630999999997, 'h': 12}", "data_type": "raw", "end_index": 537, "source": "share-point", "start_index": 0 }, "page_content": "Employees CANNOT possess or use any weapons at any time, on any of the ‘Name of the Company’ owned, leased, or controlled property. This includes any place where the company’s business is conducted, like customer locations, trade shows, client locations, company event venues, restaurants, and so forth. The ban stays even for the places where the employee represents the company. Concealed weapons are prohibited on any company property regardless of whether they own a concealed weapons permit or are legally allowed to carry a weapon.", "type": "Document" } ``` ![image](https://github.com/user-attachments/assets/89362306-4b83-4f8f-9043-e0697d77afea) ![image](https://github.com/user-attachments/assets/63d214f8-a925-4527-8199-a3dfee5332a1) **Client** NA **Options** Default one with accurate **Additional context** The issue with the `bBox` height seems to affect the rendering and analysis of document layout. Accurate bounding box measurements are crucial for correct text positioning and formatting interpretation. This bug is causing problems with subsequent processing and utilization of extracted text.
yindo added the bug label 2026-02-16 00:17:16 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label 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: run-llama/llama_cloud_services#247
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?