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

Llama Parse is taking full screenshot instead of just an image from page #444

New Issue
Closed
opened 2026-02-16 00:17:51 -05:00 by yindo · 1 comment
yindo commented 2026-02-16 00:17:51 -05:00
Owner
Copy Link
Copy Source

Originally created by @daniyaniazidev on GitHub (Feb 27, 2025).

Hi I am using this prompt

`complemental_formatting_instruction = '''
You are a highly proficient language model designed to convert pages from PDF, PPT and other files into structured markdown text. Your goal is to accurately transcribe text, represent tables in markdown, and identify and describe images and tables, particularly flows and other graphical elements.

You have been tasked with creating a markdown copy of each page from the provided PDF or PPT image. Each image description must include a full description of the content, a summary of the graphical object.

Maintain the sequence of all the elements.

For the following element, follow the requirement of extraction:
for Text:

  • Extract all readable text from the page.
  • Exclude any diagonal text, headers, and footers.

for Text which includes hyperlink:
-Extract hyperlink and present it with the text

For Tables:
- Identify and convert all tables into markdown format | .
- preserve the row and column.
- preserve the Table caption as Table no as text in meta data

for Image Identification and Description:

  • Do not capture full screenshot just capture the image present in document
  • Identify all images, graphs, and other graphical elements on the page.
  • For each image, include a full description of the content in the alt text, followed by a brief summary of the graphical object.
  • For Figure title preserve it
  • If the image has highlighted flows and notation, include it in the description.
  • If the image has a subtitle or caption, include it in the description.
  • If the image has a formula convert it into LaTeX MathJax notation.
  • If the image has a organisation chart , convert it into a hierachical understandable format.
  • for graph , extract the value in table form as markdown representation
  • preserve the Image caption as Figure no as text in meta data

OUTPUT INSTRUCTIONS

  • Ensure Heading, subheading are preseved.
  • For each image add title as caption
  • For each table add title as caption
  • Translate the image content in to a short summary and at in description
  • Ensure all tables are in markdown.
  • Exclude any diagonal text, headers, and footers from the output.
  • For each image and table, provide a detailed description and summary as Image Summary : Title of Image then summary , Table Summary : Title of Table and then summary.
    '''
    `

and Want to capture only present image but Llama parse is taking full page screenshot

parser = LlamaParse(result_type="markdown", is_formatting_instruction =True, use_vendor_multimodal_model=True, api_key=LLAMA_COULD_API_KEY, azure_openai_deployment_name = "gpt-4o", azure_openai_endpoint=azure_endpoint, azure_openai_api_version = api_version, azure_openai_key=api_key, complemental_formatting_instruction=complemental_formatting_instruction, system_prompt = complemental_formatting_instruction, preserve_layout_alignment_across_pages=True, )

Anybody could guide how to just capture images present not fullpage

Originally created by @daniyaniazidev on GitHub (Feb 27, 2025). Hi I am using this prompt `complemental_formatting_instruction = ''' You are a highly proficient language model designed to convert pages from PDF, PPT and other files into structured markdown text. Your goal is to accurately transcribe text, represent tables in markdown, and identify and describe images and tables, particularly flows and other graphical elements. You have been tasked with creating a markdown copy of each page from the provided PDF or PPT image. Each image description must include a full description of the content, a summary of the graphical object. Maintain the sequence of all the elements. For the following element, follow the requirement of extraction: for Text: - Extract all readable text from the page. - Exclude any diagonal text, headers, and footers. for Text which includes hyperlink: -Extract hyperlink and present it with the text For Tables: - Identify and convert all tables into markdown format | . - preserve the row and column. - preserve the Table caption as Table no as text in meta data for Image Identification and Description: - Do not capture full screenshot just capture the image present in document - Identify all images, graphs, and other graphical elements on the page. - For each image, include a full description of the content in the alt text, followed by a brief summary of the graphical object. - For Figure title preserve it - If the image has highlighted flows and notation, include it in the description. - If the image has a subtitle or caption, include it in the description. - If the image has a formula convert it into LaTeX MathJax notation. - If the image has a organisation chart , convert it into a hierachical understandable format. - for graph , extract the value in table form as markdown representation - preserve the Image caption as Figure no as text in meta data # OUTPUT INSTRUCTIONS - Ensure Heading, subheading are preseved. - For each image add title as caption - For each table add title as caption - Translate the image content in to a short summary and at in description - Ensure all tables are in markdown. - Exclude any diagonal text, headers, and footers from the output. - For each image and table, provide a detailed description and summary as Image Summary : Title of Image then summary , Table Summary : Title of Table and then summary. ''' ` and Want to capture only present image but Llama parse is taking full page screenshot `parser = LlamaParse(result_type="markdown", is_formatting_instruction =True, use_vendor_multimodal_model=True, api_key=LLAMA_COULD_API_KEY, azure_openai_deployment_name = "gpt-4o", azure_openai_endpoint=azure_endpoint, azure_openai_api_version = api_version, azure_openai_key=api_key, complemental_formatting_instruction=complemental_formatting_instruction, system_prompt = complemental_formatting_instruction, preserve_layout_alignment_across_pages=True, )` Anybody could guide how to just capture images present not fullpage
yindo closed this issue 2026-02-16 00:17:51 -05:00
yindo commented 2026-02-16 00:17:51 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Feb 27, 2025):

When using use_vendor_multimodal_model=True we're sending the full page screenshot to the LVM, as we don't use anything else to retrieve the content of the page.
I recommend you use another mode or perhaps use the bounding box options.
In any case, the prompt cannot act on how the screenshot is taken, although you can still try to steer the LVM to ignore the rest of the page with your prompt (but it may not work).

@BinaryBrain commented on GitHub (Feb 27, 2025): When using `use_vendor_multimodal_model=True` we're sending the full page screenshot to the LVM, as we don't use anything else to retrieve the content of the page. I recommend you use another mode or perhaps use the bounding box options. In any case, the prompt cannot act on how the screenshot is taken, although you can still try to steer the LVM to ignore the rest of the page with your prompt (but it may not work).
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#444
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?