new result object

[logan-markewich]

Add a new method and result object

Example Usage:

parser = LlamaParse(
    take_screenshot=True,
    auto_mode=True,
    fast_mode=False,
)
result = await parser.aparse(file_path)

assert isinstance(result, JobResult)
assert result.job_id is not None
assert result.file_name == file_path
assert len(result.pages) > 0

assert result.pages[0].text is not None
assert len(result.pages[0].text) > 0

assert result.pages[0].md is not None
assert len(result.pages[0].md) > 0

assert result.pages[0].md != result.pages[0].text

assert len(result.pages[0].images) > 0
assert result.pages[0].images[0].name is not None

with tempfile.TemporaryDirectory() as temp_dir:
    file_names = await result.asave_all_images(temp_dir)
    assert len(file_names) > 0
    for file_name in file_names:
        assert os.path.exists(file_name)
        assert os.path.getsize(file_name) > 0

assert result.job_metadata is not None

text_documents = result.get_text_documents(
    split_by_page=True,
)
assert len(text_documents) > 0
assert text_documents[0].text is not None
assert len(text_documents[0].text) > 0

markdown_documents = result.get_markdown_documents(
    split_by_page=True,
)
assert len(markdown_documents) > 0
assert markdown_documents[0].text is not None
assert len(markdown_documents[0].text) > 0

image_documents = result.get_image_documents()
assert len(image_documents) > 0
assert image_documents[0].image_url is not None
assert len(image_documents[0].resolve_image().getvalue()) > 0

TODO

• Update (some) examples to use this syntax
• Add this syntax to the readme

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB