How can I convert an image into Markdown?

[Alndaly]

I tried passing the image directly as input to Zerox, but it returned an error.

ERROR:root:Error converting PDF to images: Unable to get page count.
Syntax Warning: May not be a PDF file (continuing anyway)
Syntax Error: Couldn't find trailer dictionary
Syntax Error: Couldn't find trailer dictionary
Syntax Error: Couldn't read xref table

Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/Users/kinda/Developer/清韵公司项目/open-source/Revornix/celery-worker/engine/zerox.py", line 55, in <module>
    result = asyncio.run(
             ^^^^^^^^^^^^
  File "/Users/kinda/anaconda3/envs/link/lib/python3.11/asyncio/runners.py", line 190, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/Users/kinda/anaconda3/envs/link/lib/python3.11/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kinda/anaconda3/envs/link/lib/python3.11/asyncio/base_events.py", line 654, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "/Users/kinda/Developer/清韵公司项目/open-source/Revornix/celery-worker/engine/zerox.py", line 28, in analyse_website
    result = await zerox(
             ^^^^^^^^^^^^
  File "/Users/kinda/anaconda3/envs/link/lib/python3.11/site-packages/pyzerox/core/zerox.py", line 149, in zerox
    results = await process_pages_in_batches(
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kinda/anaconda3/envs/link/lib/python3.11/site-packages/pyzerox/processor/pdf.py", line 94, in process_pages_in_batches
    tasks = [
            ^
TypeError: 'NoneType' object is not iterable

Here is my code below:

...
async with async_playwright() as p:
    browser = await p.chromium.launch(headless=True)
    page = await browser.new_page()
    await page.goto(url, wait_until="networkidle")
    html_content = await page.content()
    await page.screenshot(path=temp_shot_img_path, full_page=True)
    await browser.close()
result = await zerox(
    file_path=temp_shot_img_path,
    model="gpt-4o-mini",
    cleanup=True,
)
...

[w1tv]

You can leave , you're not supported.

[gjssy]

you can add some code in ./py_zerox/pyzerox/core/zerox.py ,for example:
import imghdr
is_image = imghdr.what(local_path) is not None
if is_image:
images = [local_path]
else:
images = await convert_pdf_to_images(
image_density=image_density,
image_height=image_height,
local_path=local_path,
temp_dir=temp_directory
)

if not images:
raise ValueError(f"can't process file {file_path}, has not images data.")