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

Parsing with "auto_mode=true" scanned PDFs returns "NO_CONTENT_HERE" on every page #398

New Issue
Closed
opened 2026-02-16 00:17:43 -05:00 by yindo · 7 comments
yindo commented 2026-02-16 00:17:43 -05:00
Owner
Copy Link
Copy Source

Originally created by @moMinosia on GitHub (Jan 2, 2025).

Originally assigned to: @BinaryBrain on GitHub.

Describe the bug
Parsing scanned PDFs returns "NO_CONTENT_HERE" on every page
My api request:

("auto_mode", "true");
("auto_mode_trigger_on_table_in_page", "true");
("auto_mode_trigger_on_image_in_page", "true");
("take_screenshot", "false");
("annotate_links", "true");
("disable_image_extraction", "true");

Files

Job ID

cbdeee57-3557-430f-aeb1-0d5a4e4580b4

Client:

  • API

Additional context
Add any additional context about the problem here.
What options did you use? Premium mode, multimodal, fast mode, parsing instructions, etc.
Screenshots, code snippets, etc.

Originally created by @moMinosia on GitHub (Jan 2, 2025). Originally assigned to: @BinaryBrain on GitHub. **Describe the bug** Parsing scanned PDFs returns "NO_CONTENT_HERE" on every page My api request: ``` ("auto_mode", "true"); ("auto_mode_trigger_on_table_in_page", "true"); ("auto_mode_trigger_on_image_in_page", "true"); ("take_screenshot", "false"); ("annotate_links", "true"); ("disable_image_extraction", "true"); ``` **Files** **Job ID** - cbdeee57-3557-430f-aeb1-0d5a4e4580b4 **Client:** - API **Additional context** Add any additional context about the problem here. What options did you use? Premium mode, multimodal, fast mode, parsing instructions, etc. Screenshots, code snippets, etc.
yindo added the bug label 2026-02-16 00:17:43 -05:00
yindo closed this issue 2026-02-16 00:17:43 -05:00
yindo commented 2026-02-16 00:17:44 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Jan 3, 2025):

We noticed this bug as well. Can you try to remove ("disable_image_extraction", "true"); and try again?

@BinaryBrain commented on GitHub (Jan 3, 2025): We noticed this bug as well. Can you try to remove `("disable_image_extraction", "true");` and try again?
yindo commented 2026-02-16 00:17:44 -05:00
Author
Owner
Copy Link
Copy Source

@moMinosia commented on GitHub (Jan 3, 2025):

I tried again same results 0bdc1807-3c66-4cf0-8040-db8dd47b1860, it was cached so I added ("invalidate_cache", "true"), same results with the NO_CONTENT_HERE, here's the job id afa8d7ad-9f56-4d3a-87ee-3f32ba24c4d8

@moMinosia commented on GitHub (Jan 3, 2025): I tried again same results `0bdc1807-3c66-4cf0-8040-db8dd47b1860`, it was cached so I added `("invalidate_cache", "true")`, same results with the NO_CONTENT_HERE, here's the job id `afa8d7ad-9f56-4d3a-87ee-3f32ba24c4d8`
yindo commented 2026-02-16 00:17:44 -05:00
Author
Owner
Copy Link
Copy Source

@moMinosia commented on GitHub (Jan 3, 2025):

Apologise, seems I didn't remove ("disable_image_extraction", "true") when I tested, it works after it's removed, here's the job id 5e146e7b-965d-403c-a04b-db928e382b6c. does "image_extraction" cost credits?

@moMinosia commented on GitHub (Jan 3, 2025): Apologise, seems I didn't remove `("disable_image_extraction", "true")` when I tested, it works after it's removed, here's the job id `5e146e7b-965d-403c-a04b-db928e382b6c`. does "image_extraction" cost credits?
yindo commented 2026-02-16 00:17:44 -05:00
Author
Owner
Copy Link
Copy Source

@moMinosia commented on GitHub (Jan 3, 2025):

also, the markdown output was good but the text output was gibberish

@moMinosia commented on GitHub (Jan 3, 2025): also, the markdown output was good but the text output was gibberish
yindo commented 2026-02-16 00:17:44 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Jan 3, 2025):

image_extraction doesn't cost any extra credits, but can be slightly slower.

@BinaryBrain commented on GitHub (Jan 3, 2025): image_extraction doesn't cost any extra credits, but can be slightly slower.
yindo commented 2026-02-16 00:17:44 -05:00
Author
Owner
Copy Link
Copy Source

@moMinosia commented on GitHub (Jan 5, 2025):

alright, for now I have auto mode true on all format, but when it's pdf I set ("disable_image_extraction", "true").
but I would like to disable it for all format and avoid slow times

@moMinosia commented on GitHub (Jan 5, 2025): alright, for now I have auto mode true on all format, but when it's pdf I set ("disable_image_extraction", "true"). but I would like to disable it for all format and avoid slow times
yindo commented 2026-02-16 00:17:44 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Jan 6, 2025):

You cannot have these two parameters at the same time anyway:

("auto_mode_trigger_on_image_in_page", "true");
("disable_image_extraction", "true");

Because how do you want to trigger the premium mode on images if you don't extract them?

@BinaryBrain commented on GitHub (Jan 6, 2025): You cannot have these two parameters at the same time anyway: ``` ("auto_mode_trigger_on_image_in_page", "true"); ("disable_image_extraction", "true"); ``` Because how do you want to trigger the premium mode on images if you don't extract them?
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#398
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?