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 #325

New Issue
Closed
opened 2026-02-16 00:17:29 -05:00 by yindo · 5 comments
yindo commented 2026-02-16 00:17:29 -05:00
Owner
Copy Link
Copy Source

Originally created by @vicacid on GitHub (Nov 12, 2024).

Originally assigned to: @BinaryBrain on GitHub.

Describe the bug
If I work with low-quality files (bad scans/photos and etc.), the result turns out to be incorrect—the model simply hallucinates, making up content. The main problem is not that I'm getting an incorrect result, but rather that I have no way of knowing this. There's no confidence rate or similar parameter that I could rely on, nor do I receive any error in response.

Using OCR tools for such files (like docTR), I get correct results.

Job ID
70288cfd-b87f-4b39-8df3-901a8920e761
42362160-7a18-434f-8e51-405eb711ec7b - without parsing instructions
1d45ede8-18d2-4c36-bd79-06ac5f110c34 - without parsing instructions

Client:

  • API

Additional context
I understand that this is a tricky question from a business process perspective—how the parser should behave. It might make sense to use tools to identify such file types before sending them to LLamaParse, but maybe there are some internal tools that I haven't been able to find.

Originally created by @vicacid on GitHub (Nov 12, 2024). Originally assigned to: @BinaryBrain on GitHub. **Describe the bug** If I work with low-quality files (bad scans/photos and etc.), the result turns out to be incorrect—the model simply hallucinates, making up content. The main problem is not that I'm getting an incorrect result, but rather that I have no way of knowing this. There's no confidence rate or similar parameter that I could rely on, nor do I receive any error in response. Using OCR tools for such files (like docTR), I get correct results. **Job ID** 70288cfd-b87f-4b39-8df3-901a8920e761 42362160-7a18-434f-8e51-405eb711ec7b - without parsing instructions 1d45ede8-18d2-4c36-bd79-06ac5f110c34 - without parsing instructions **Client:** - API **Additional context** I understand that this is a tricky question from a business process perspective—how the parser should behave. It might make sense to use tools to identify such file types before sending them to LLamaParse, but maybe there are some internal tools that I haven't been able to find.
yindo added the ocr label 2026-02-16 00:17:29 -05:00
yindo closed this issue 2026-02-16 00:17:29 -05:00
yindo commented 2026-02-16 00:17:29 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Nov 12, 2024):

Hi @vicacid,
You can get confidence levels of the OCR in the Json output (.images[0].ocr[0].confidence).

I just checked this job: 1d45ede8-18d2-4c36-bd79-06ac5f110c34 and I don't see how we could correctly OCR the photo of a page in 480x640. I haven't tried it with docTR, but I doubt it can output credible results.

@BinaryBrain commented on GitHub (Nov 12, 2024): Hi @vicacid, You can get confidence levels of the OCR in the Json output (`.images[0].ocr[0].confidence`). I just checked this job: `1d45ede8-18d2-4c36-bd79-06ac5f110c34` and I don't see how we could correctly OCR the photo of a page in 480x640. I haven't tried it with docTR, but I doubt it can output credible results.
yindo commented 2026-02-16 00:17:30 -05:00
Author
Owner
Copy Link
Copy Source

@vicacid commented on GitHub (Nov 12, 2024):

@BinaryBrain thank you for the answer.

I believe confidence param will work!

I also thought that 1d45ede8-18d2-4c36-bd79-06ac5f110c34 is not readable - but they did it (of course there is minor mismatches - but you can check the result)

@vicacid commented on GitHub (Nov 12, 2024): @BinaryBrain thank you for the answer. I believe `confidence` param will work! I also thought that `1d45ede8-18d2-4c36-bd79-06ac5f110c34` is not readable - but they did it (of course there is minor mismatches - but you can check the result)
yindo commented 2026-02-16 00:17:30 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Nov 12, 2024):

I'd love to see the output of docTR if you have it.

@BinaryBrain commented on GitHub (Nov 12, 2024): I'd love to see the output of docTR if you have it.
yindo commented 2026-02-16 00:17:30 -05:00
Author
Owner
Copy Link
Copy Source

@vicacid commented on GitHub (Nov 12, 2024):

I'd love to see the output of docTR if you have it.

@BinaryBrain
I'm not sure it's a good idea to share it here. Do you have any support email or other messenger channels for the communication? I've tried email from llamacloud which is under "Email us" but that one is dead.

@vicacid commented on GitHub (Nov 12, 2024): > I'd love to see the output of docTR if you have it. @BinaryBrain I'm not sure it's a good idea to share it here. Do you have any support email or other messenger channels for the communication? I've tried email from llamacloud which is under "Email us" but that one is dead.
yindo commented 2026-02-16 00:17:30 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Nov 12, 2024):

You can email me at sacha@runllama.ai

@BinaryBrain commented on GitHub (Nov 12, 2024): You can email me at sacha@runllama.ai
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 ocr
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#325
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?