Skip to content

fix: Expose MarkdownHeaderLevelInferrer in preprocessors module and fix example #384

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

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

fix: Expose MarkdownHeaderLevelInferrer in preprocessors module and fix example #384

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ddbde13
expose MarkdownHeaderLevelInferrer in init file
julian-risch Oct 21, 2025
e34c829
fix example
julian-risch Oct 21, 2025
daa2ee2
simplify import path
julian-risch Oct 21, 2025
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
2 changes: 2 additions & 0 deletions haystack_experimental/components/preprocessors/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,10 +9,12 @@

_import_structure = {
"embedding_based_document_splitter": ["EmbeddingBasedDocumentSplitter"],
"md_header_level_inferrer": ["MarkdownHeaderLevelInferrer"],
}

if TYPE_CHECKING:
from .embedding_based_document_splitter import EmbeddingBasedDocumentSplitter
from .md_header_level_inferrer import MarkdownHeaderLevelInferrer

else:
sys.modules[__name__] = LazyImporter(name=__name__, module_file=__file__, import_structure=_import_structure)
4 changes: 2 additions & 2 deletions haystack_experimental/components/preprocessors/md_header_level_inferrer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ class MarkdownHeaderLevelInferrer:
from haystack_experimental.components.preprocessors import MarkdownHeaderLevelInferrer

# Create a document with uniform header levels
text = "## Title\nSome content\n## Section\nMore content\n## Subsection\nFinal content"
text = "## Title\n## Subheader\nSection\n## Subheader\nMore Content"
doc = Document(content=text)

# Initialize the inferrer and process the document
Expand All @@ -33,7 +33,7 @@ class MarkdownHeaderLevelInferrer:

# The headers are now normalized with proper hierarchy
print(result["documents"][0].content)
> # Title\nSome content\n## Section\nMore content\n### Subsection\nFinal content
> # Title\n## Subheader\nSection\n## Subheader\nMore Content
```
"""

Expand Down
6 changes: 3 additions & 3 deletions test/components/preprocessors/test_markdown_header_level_inferrer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
# SPDX-License-Identifier: Apache-2.0

from haystack import Document
from haystack_experimental.components.preprocessors.md_header_level_inferrer import MarkdownHeaderLevelInferrer
from haystack_experimental.components.preprocessors import MarkdownHeaderLevelInferrer


def test_single_header_level_inference():
Expand Down Expand Up @@ -124,7 +124,7 @@ def test_multiple_documents():
inferrer = MarkdownHeaderLevelInferrer()
docs = [Document(content=text1), Document(content=text2)]
result = inferrer.run(docs)

assert len(result["documents"]) == 2
assert result["documents"][0].content == "# Title 1\nContent 1"
assert result["documents"][1].content == "# Title 2\nContent 2"
Expand Down Expand Up @@ -154,7 +154,7 @@ def test_very_long_content():
inferrer = MarkdownHeaderLevelInferrer()
doc = Document(content=text)
result = inferrer.run([doc])

# verify first header becomes level 1, others follow the pattern
content = result["documents"][0].content
assert content.startswith("# Header 0")
Expand Down
Loading