luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Updated prompt to extract text and format it in Markdown, including additional visual details, instead of only describing the image.

Browse source
This commit is contained in:
Michał Zemełka 2024-12-22 18:02:29 +01:00
parent 125e206047
commit 3b8ecace0b
1 changed files with 15 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
src/markitdown/_markitdown.py
View file

@ -1047,7 +1047,21 @@ class ImageConverter(MediaConverter):
def _get_llm_description(self, local_path, extension, client, model, prompt=None): def _get_llm_description(self, local_path, extension, client, model, prompt=None):
if prompt is None or prompt.strip() == "": if prompt is None or prompt.strip() == "":
prompt = "Write a detailed caption for this image." prompt = '''
Analyze the image and extract all visible text in the original language.
Reproduce the extracted text in a structured Markdown format, preserving
any formatting such as headings, bullet points, and highlights. Ensure
the output accurately reflects the structure and style of the original
document.
Additionally, if the image includes any visual elements (e.g., diagrams,
logos, or specific layouts) that cannot be represented directly in Markdown,
describe them in plain text as part of the Markdown document under a section
titled "Visual Notes."
Output only the converted Markdown text without any additional commentary
or explanations.
'''
data_uri = "" data_uri = ""
with open(local_path, "rb") as image_file: with open(local_path, "rb") as image_file: