Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

community: fallback on core async atransform_documents method for MarkdownifyTransformer #27866

Merged
merged 14 commits into from
Dec 13, 2024
Merged

community: fallback on core async atransform_documents method for MarkdownifyTransformer #27866

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
74570cc
Implement atransform_documents for MarkdownifyTransformer
rparkr Oct 30, 2024
d809491
Merge branch 'langchain-ai:master' into rparkr/async-markdownify-tran…
rparkr Nov 1, 2024
5c04122
Simplify asynchronous task creation
rparkr Nov 1, 2024
61309de
Merge branch 'langchain-ai:master' into rparkr/async-markdownify-tran…
rparkr Nov 3, 2024
e8abfb4
Format for readability
rparkr Nov 3, 2024
e8d5a94
Merge branch 'master' into rparkr/async-markdownify-transform
rparkr Dec 4, 2024
7f14677
Merge branch 'langchain-ai:master' into rparkr/async-markdownify-tran…
rparkr Dec 4, 2024
e37fc18
Add async unit tests for markdownify
rparkr Dec 4, 2024
be788ff
Update unit tests for CI failures
rparkr Dec 4, 2024
ffac42a
Update unit tests to fix CI failures
rparkr Dec 4, 2024
8fe6ca0
Fix CI unit test failures
rparkr Dec 4, 2024
17f6563
Merge branch 'master' into rparkr/async-markdownify-transform
rparkr Dec 4, 2024
6c19280
Merge branch 'master' into rparkr/async-markdownify-transform
efriis Dec 13, 2024
6cfbd0c
x
efriis Dec 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 0 additions & 7 deletions libs/community/langchain_community/document_transformers/markdownify.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,10 +74,3 @@ def transform_documents(
)

return converted_documents

async def atransform_documents(
self,
documents: Sequence[Document],
**kwargs: Any,
) -> Sequence[Document]:
raise NotImplementedError
142 changes: 140 additions & 2 deletions libs/community/tests/unit_tests/document_transformers/test_markdownify.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,8 @@ def test_extract_html() -> None:
documents = [Document(page_content=basic_html)]
docs_transformed = markdownify.transform_documents(documents)
assert docs_transformed[0].page_content == (
"Simple Test Page # Test Header\n\n "
"Simple Test Page "
"# Test Header\n\n "
"First paragraph.\n\n "
"Second paragraph.\n\n "
"[Example Link](https://example.com)"
Expand Down Expand Up @@ -105,7 +106,8 @@ def test_convert_tags() -> None:
assert docs_transformed[0].page_content == (
"Header "
"**1st paragraph.** "
"2nd paragraph. Here is [link](http://example.com) "
"2nd paragraph. "
"Here is [link](http://example.com) "
"Ignore at end"
)

Expand Down Expand Up @@ -137,3 +139,139 @@ def test_strip_convert_conflict_error() -> None:
)
documents = [Document(page_content=paragraphs_html)]
markdownify.transform_documents(documents)


# Async variants: exact duplicates of the above functions, using atransform_documents()
@pytest.mark.requires("markdownify")
async def test_empty_html_async() -> None:
markdownify = MarkdownifyTransformer()
empty_html = "<html></html>"
documents = [Document(page_content=empty_html)]
docs_transformed = await markdownify.atransform_documents(documents)
assert docs_transformed[0].page_content == ""


@pytest.mark.requires("markdownify")
async def test_extract_paragraphs_async() -> None:
markdownify = MarkdownifyTransformer()
paragraphs_html = (
"<html><h1>Header</h1><p>First paragraph.</p>"
"<p>Second paragraph.</p><h1>Ignore at end</h1></html>"
)
documents = [Document(page_content=paragraphs_html)]
docs_transformed = await markdownify.atransform_documents(documents)
assert docs_transformed[0].page_content == (
"# Header\n\n" "First paragraph.\n\n" "Second paragraph.\n\n" "# Ignore at end"
)


@pytest.mark.requires("markdownify")
async def test_extract_html_async() -> None:
markdownify = MarkdownifyTransformer(skip="title")
basic_html = (
"<!DOCTYPE html>"
'<html lang="en">'
"<head>"
' <meta charset="UTF-8">'
" <title>Simple Test Page</title>"
"</head>"
"<body>"
" <h1>Test Header</h1>"
" <p>First paragraph.</p>"
" <p>Second paragraph.</p>"
' <a href="https://example.com">Example Link</a>'
"</body>"
"</html>"
)
documents = [Document(page_content=basic_html)]
docs_transformed = await markdownify.atransform_documents(documents)
assert docs_transformed[0].page_content == (
"Simple Test Page "
"# Test Header\n\n "
"First paragraph.\n\n "
"Second paragraph.\n\n "
"[Example Link](https://example.com)"
)


@pytest.mark.requires("markdownify")
async def test_strip_tags_async() -> None:
markdownify = MarkdownifyTransformer(strip="strong")
paragraphs_html = (
"<html>"
"<h1>Header</h1>"
" <p><strong>1st paragraph.</strong></p>"
' <p>2nd paragraph. Here is <a href="http://example.com">link</a></p>'
' <img src="image.jpg" alt="Sample Image">'
"<h1>Ignore at end</h1></html>"
)
documents = [Document(page_content=paragraphs_html)]
docs_transformed = await markdownify.atransform_documents(documents)
assert docs_transformed[0].page_content == (
"# Header\n\n "
"1st paragraph.\n\n "
"2nd paragraph. Here is [link](http://example.com)\n\n "
"![Sample Image](image.jpg)"
"# Ignore at end"
)

markdownify = MarkdownifyTransformer(strip=["strong", "a", "img"])
documents = [Document(page_content=paragraphs_html)]
docs_transformed = await markdownify.atransform_documents(documents)
assert docs_transformed[0].page_content == (
"# Header\n\n "
"1st paragraph.\n\n "
"2nd paragraph. Here is link\n\n "
"# Ignore at end"
)


@pytest.mark.requires("markdownify")
async def test_convert_tags_async() -> None:
markdownify = MarkdownifyTransformer(convert=["strong", "a"])
paragraphs_html = (
"<html>"
"<h1>Header</h1>"
" <p><strong>1st paragraph.</strong></p>"
' <p>2nd paragraph. Here is <a href="http://example.com">link</a></p>'
' <img src="image.jpg" alt="Sample Image">'
"<h1>Ignore at end</h1></html>"
)
documents = [Document(page_content=paragraphs_html)]
docs_transformed = await markdownify.atransform_documents(documents)
assert docs_transformed[0].page_content == (
"Header "
"**1st paragraph.** "
"2nd paragraph. "
"Here is [link](http://example.com) "
"Ignore at end"
)

markdownify = MarkdownifyTransformer(convert="p")
documents = [Document(page_content=paragraphs_html)]
docs_transformed = await markdownify.atransform_documents(documents)
assert docs_transformed[0].page_content == (
"Header "
"1st paragraph.\n\n "
"2nd paragraph. Here is link\n\n "
"Ignore at end"
)


@pytest.mark.requires("markdownify")
async def test_strip_convert_conflict_error_async() -> None:
with pytest.raises(
ValueError,
match="You may specify either tags to strip or tags to convert, but not both.",
):
markdownify = MarkdownifyTransformer(strip="h1", convert=["strong", "a"])
paragraphs_html = (
"<html>"
"<h1>Header</h1>"
" <p><strong>1st paragraph.</strong></p>"
' <p>2nd paragraph. Here is <a href="http://example.com">link</a></p>'
' <img src="image.jpg" alt="Sample Image">'
"<h1>Ignore at end</h1></html>"
)
documents = [Document(page_content=paragraphs_html)]
await markdownify.atransform_documents(documents)
Loading