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

Unable to parse application forms having square boxes to fill in letters #227

New Issue
Open
opened 2026-02-16 00:17:11 -05:00 by yindo · 2 comments
yindo commented 2026-02-16 00:17:11 -05:00
Owner
Copy Link
Copy Source

Originally created by @ashutosh-3pillarglobal on GitHub (Aug 9, 2024).

Hi Team,

I am exploring different options to parse different application forms (in .png and .pdf format) using Python and LLMs. I am trying to do this using LlamaParse but looks like it is unable to read the letters written in square boxes of the application form.

Attached is the sample image I am trying to parse. From this image I am trying to extract the Date of Birth i.e. 11-08-71. But it is just not reading these letters.

IDFC_form_3

Following is the prompt instruction:
"You are an OCR processor and your task is to extract the content in the provided image.
The image is an application form.
There are multiple columns but you have to extract — Folio Number and Date of Birth.
You will find values for these columns adjacent to there names and the values will be in set of square boxes where each square box contain one letter of the whole value.
You will have to read inside those square boxes to get the values.
In case you are not able to extract values for any of the above fields mention it as Unable to Extract and mention the reason why you are not able to extract this."

Following is the markdown output I am getting:
"# OCR Processed Data

Extracted Data:

Folio Number
Date of Birth

Unable to Extract
Unable to Extract - The values are not provided in a readable format (set of square boxes)."

Please let me know:

  1. Is there a workaround to achieve this?
  2. Is it a know issue?
  3. Is there any work in progress to handle this?
Originally created by @ashutosh-3pillarglobal on GitHub (Aug 9, 2024). Hi Team, I am exploring different options to parse different application forms (in .png and .pdf format) using Python and LLMs. I am trying to do this using LlamaParse but looks like it is unable to read the letters written in square boxes of the application form. Attached is the sample image I am trying to parse. From this image I am trying to extract the Date of Birth i.e. 11-08-71. But it is just not reading these letters. <img width="560" alt="IDFC_form_3" src="https://github.com/user-attachments/assets/c069f294-62f0-468f-922f-0023eb3055e4"> Following is the prompt instruction: "You are an OCR processor and your task is to extract the content in the provided image. The image is an application form. There are multiple columns but you have to extract — Folio Number and Date of Birth. You will find values for these columns adjacent to there names and the values will be in set of square boxes where each square box contain one letter of the whole value. You will have to read inside those square boxes to get the values. In case you are not able to extract values for any of the above fields mention it as Unable to Extract and mention the reason why you are not able to extract this." Following is the markdown output I am getting: "# OCR Processed Data # Extracted Data: Folio Number Date of Birth Unable to Extract Unable to Extract - The values are not provided in a readable format (set of square boxes)." Please let me know: 1. Is there a workaround to achieve this? 2. Is it a know issue? 3. Is there any work in progress to handle this?
yindo commented 2026-02-16 00:17:12 -05:00
Author
Owner
Copy Link
Copy Source

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

Hi,
Please provide your JobID and if possible, your PDF so we can have a look at the issue.

@BinaryBrain commented on GitHub (Aug 12, 2024): Hi, Please provide your JobID and if possible, your PDF so we can have a look at the issue.
yindo commented 2026-02-16 00:17:12 -05:00
Author
Owner
Copy Link
Copy Source

@ashutosh-3pillarglobal commented on GitHub (Aug 13, 2024):

Hi @BinaryBrain,
Job ID - 14b96860-8709-4fc8-a493-063c60a93901
Attached is the image I am trying to parse.

IDFC_form_3
@ashutosh-3pillarglobal commented on GitHub (Aug 13, 2024): Hi @BinaryBrain, Job ID - 14b96860-8709-4fc8-a493-063c60a93901 Attached is the image I am trying to parse. <img width="560" alt="IDFC_form_3" src="https://github.com/user-attachments/assets/f4b3aba8-db85-42e9-aefe-0a10c4036e58">
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#227
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?