run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-26 16:56:36 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

When parsing a PDF with markdown, some parts of text are getting lost. #462

New Issue
Open
opened 2026-02-16 00:17:55 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:55 -05:00
Owner
Copy Link
Copy Source

Originally created by @gulabyang on GitHub (Apr 23, 2025).

Describe the bug
I'm parsing a PDF and requesting a markdown, but in it some portions of text are missing (i.e. "A. 3% of a long sentence here", might be completely missed). When checking requesting text, everything is in place.

Files
API endpoint:

6.     Deductibles
       Each claim for loss or damage as insured against arising out of any one (1)
       Occurrence shall be adjusted separately and from the amount of each such
       adjusted loss shall be deducted the sum of $500,000 except;
       Earthquake:
           With respect to locations in Puerto Rico and the Pacific Northwest, the
           deductible shall be:
           A.  3% of the value of each separate building or structure involved in the loss
               and/or the contents of each separate building or structure involved in the
               loss at the time of loss;
           B.  3% of the net profits and continuing expenses attributable to the
               operations at each separate building or structure which has sustained
               loss or damage for the 12 month period immediately following the
               covered loss or damage, considering the most probable experience of the
               business over that period had no loss or damage occurred..
       Named Storm, including resulting Flood:
           ...... Rest of the content

next.js library getText()

6. Deductibles
Each claim for loss or damage as insured against arising out of any one (1) Occurrence shall be adjusted separately and from the amount of each such adjusted loss shall be deducted the sum of $500,000 except;

Earthquake:

With respect to locations in Puerto Rico and the Pacific Northwest, the deductible shall be:
Named Storm, including resulting Flood:
...... Rest of the content

Blocks A & B with 3% are just missing.

Job ID
97958a6b-2187-4d50-8bc5-57cf89f2e229

Client:
Please remove untested options:

  • Typescript Library

Additional context
Default parsing.

Originally created by @gulabyang on GitHub (Apr 23, 2025). **Describe the bug** I'm parsing a PDF and requesting a markdown, but in it some portions of text are missing (i.e. "A. 3% of a long sentence here", might be completely missed). When checking requesting text, everything is in place. **Files** API endpoint: ``` 6. Deductibles Each claim for loss or damage as insured against arising out of any one (1) Occurrence shall be adjusted separately and from the amount of each such adjusted loss shall be deducted the sum of $500,000 except; Earthquake: With respect to locations in Puerto Rico and the Pacific Northwest, the deductible shall be: A. 3% of the value of each separate building or structure involved in the loss and/or the contents of each separate building or structure involved in the loss at the time of loss; B. 3% of the net profits and continuing expenses attributable to the operations at each separate building or structure which has sustained loss or damage for the 12 month period immediately following the covered loss or damage, considering the most probable experience of the business over that period had no loss or damage occurred.. Named Storm, including resulting Flood: ...... Rest of the content ``` next.js library getText() ``` 6. Deductibles Each claim for loss or damage as insured against arising out of any one (1) Occurrence shall be adjusted separately and from the amount of each such adjusted loss shall be deducted the sum of $500,000 except; Earthquake: With respect to locations in Puerto Rico and the Pacific Northwest, the deductible shall be: Named Storm, including resulting Flood: ...... Rest of the content ``` Blocks A & B with 3% are just missing. **Job ID** 97958a6b-2187-4d50-8bc5-57cf89f2e229 **Client:** Please remove untested options: - Typescript Library **Additional context** Default parsing.
yindo added the bug label 2026-02-16 00:17:55 -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#462
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?