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

[Table Parsing Issue] Multiline content in single cell but detected as multiple rows instead #76

New Issue
Open
opened 2026-02-16 00:16:48 -05:00 by yindo · 4 comments
yindo commented 2026-02-16 00:16:48 -05:00
Owner
Copy Link
Copy Source

Originally created by @aswincandra on GitHub (Apr 5, 2024).

Example PDF content:
image

Result:

Header 1 Header 2 Header 3
● Item 1 Item 1 Item 1
● Item 2 Item 2 Item 2
● Item 3 Item 3
Item 4

I'm expecting that it will be still in a single row instead of separated to multiple rows because it will cause a misleading. Could you guys help to improve your table detection? Or maybe is there specific parsing instruction that I can use to handle this issue?

Several details:

  • I was using raw API call
  • Sample PDF file here

By the way, very appreciate your hard work!

Originally created by @aswincandra on GitHub (Apr 5, 2024). Example PDF content: <img width="667" alt="image" src="https://github.com/run-llama/llama_parse/assets/38917231/2374ce80-03bb-4149-b8d5-7d2c6d51c458"> Result: |Header 1|Header 2|Header 3| |---|---|---| |● Item 1|Item 1|Item 1| |● Item 2|Item 2|Item 2| |● Item 3|Item 3| | | |Item 4| | I'm expecting that it will be still in a single row instead of separated to multiple rows because it will cause a misleading. Could you guys help to improve your table detection? Or maybe is there specific parsing instruction that I can use to handle this issue? Several details: * I was using raw API call * Sample PDF file [here](https://drive.google.com/file/d/1WMJCGRfi1i6OQC8vo6tlZTZv1PE3G1XE/view?usp=sharing) By the way, very appreciate your hard work!
yindo commented 2026-02-16 00:16:48 -05:00
Author
Owner
Copy Link
Copy Source

@PowerOwner commented on GitHub (Apr 29, 2024):

Something like that?

LlamaParse Table Debug.md
im2

@PowerOwner commented on GitHub (Apr 29, 2024): Something like that? [LlamaParse Table Debug.md](https://github.com/run-llama/llama_parse/files/15149611/LlamaParse.Table.Debug.md) <img width="1122" alt="im2" src="https://github.com/run-llama/llama_parse/assets/20768277/fd8be347-6615-4f03-adeb-b3985776e836">
yindo commented 2026-02-16 00:16:48 -05:00
Author
Owner
Copy Link
Copy Source

@aswincandra commented on GitHub (Apr 29, 2024):

Something like that?

LlamaParse Table Debug.md im2

Yes. How could you achieve that? Has the Llama team updated their library? I haven't checked yet.

@aswincandra commented on GitHub (Apr 29, 2024): > Something like that? > > [LlamaParse Table Debug.md](https://github.com/run-llama/llama_parse/files/15149611/LlamaParse.Table.Debug.md) <img alt="im2" width="1122" src="https://private-user-images.githubusercontent.com/20768277/326448743-fd8be347-6615-4f03-adeb-b3985776e836.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.LsiYbMj0tfASED0sLBwbPW6lzIEfFrVsLMk0gvwU0eQ"> Yes. How could you achieve that? Has the Llama team updated their library? I haven't checked yet.
yindo commented 2026-02-16 00:16:49 -05:00
Author
Owner
Copy Link
Copy Source

@PowerOwner commented on GitHub (Apr 30, 2024):

Something like that? 像这样的事？
LlamaParse Table Debug.md im2 LlamaParse表Debug.md im2

Yes. How could you achieve that? Has the Llama team updated their library? I haven't checked yet.是的你怎么做到的？Llama团队更新了他们的图书馆吗？我还没查呢

No, See there are other PDF parsing tools can do;

@PowerOwner commented on GitHub (Apr 30, 2024): > > Something like that? 像这样的事？ > > [LlamaParse Table Debug.md](https://github.com/run-llama/llama_parse/files/15149611/LlamaParse.Table.Debug.md) <img alt="im2" width="39.640625" height="21" src="https://private-user-images.githubusercontent.com/20768277/326448743-fd8be347-6615-4f03-adeb-b3985776e836.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.LsiYbMj0tfASED0sLBwbPW6lzIEfFrVsLMk0gvwU0eQ"> LlamaParse表Debug.md <img alt="im2" width="39.640625" height="21" src="https://private-user-images.githubusercontent.com/20768277/326448743-fd8be347-6615-4f03-adeb-b3985776e836.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.LsiYbMj0tfASED0sLBwbPW6lzIEfFrVsLMk0gvwU0eQ"> > > Yes. How could you achieve that? Has the Llama team updated their library? I haven't checked yet.是的你怎么做到的？Llama团队更新了他们的图书馆吗？我还没查呢 No, See there are other PDF parsing tools can do;
yindo commented 2026-02-16 00:16:49 -05:00
Author
Owner
Copy Link
Copy Source

@aswincandra commented on GitHub (May 10, 2024):

Something like that? 像这样的事？
LlamaParse Table Debug.md im2 LlamaParse表Debug.md im2

Yes. How could you achieve that? Has the Llama team updated their library? I haven't checked yet.是的你怎么做到的？Llama团队更新了他们的图书馆吗？我还没查呢

No, See there are other PDF parsing tools can do;

What parsing tool did you use?

@aswincandra commented on GitHub (May 10, 2024): > > > Something like that? 像这样的事？ > > > [LlamaParse Table Debug.md](https://github.com/run-llama/llama_parse/files/15149611/LlamaParse.Table.Debug.md) <img alt="im2" width="39.640625" height="21" src="https://private-user-images.githubusercontent.com/20768277/326448743-fd8be347-6615-4f03-adeb-b3985776e836.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.LsiYbMj0tfASED0sLBwbPW6lzIEfFrVsLMk0gvwU0eQ"> LlamaParse表Debug.md <img alt="im2" width="39.640625" height="21" src="https://private-user-images.githubusercontent.com/20768277/326448743-fd8be347-6615-4f03-adeb-b3985776e836.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.LsiYbMj0tfASED0sLBwbPW6lzIEfFrVsLMk0gvwU0eQ"> > > > > > > Yes. How could you achieve that? Has the Llama team updated their library? I haven't checked yet.是的你怎么做到的？Llama团队更新了他们的图书馆吗？我还没查呢 > > No, See there are other PDF parsing tools can do; What parsing tool did you use?
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
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#76
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?