support single metadata dict in markdown2document

haystack/components/converters/markdown.py

@@ -7,7 +7,7 @@
 from haystack import Document, component
 from haystack.dataclasses import ByteStream
 from haystack.lazy_imports import LazyImport
-from haystack.components.converters.utils import get_bytestream_from_source
+from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
 
 with LazyImport("Run 'pip install markdown-it-py mdit_plain'") as markdown_conversion_imports:
  from markdown_it import MarkdownIt
@@ -27,7 +27,7 @@ class MarkdownToDocument:
  from haystack.components.converters.markdown import MarkdownToDocument
 
  converter = MarkdownToDocument()
- results = converter.run(sources=["sample.md"])
+ results = converter.run(sources=["sample.md"], meta={"date_added": datetime.now().isoformat()})
  documents = results["documents"]
  print(documents[0].content)
  # 'This is a text from the markdown file.'
@@ -50,23 +50,22 @@ def run(self, sources: List[Union[str, Path, ByteStream]], meta: Optional[List[D
  Reads text from a markdown file and executes optional preprocessing steps.
 
  :param sources: A list of markdown data sources (file paths or binary objects)
- :param meta: Optional list of metadata to attach to the Documents.
- The length of the list must match the number of paths. Defaults to `None`.
+ :param meta: Optional metadata to attach to the Documents.
+ This value can be either a list of dictionaries or a single dictionary.
+ If it's a single dictionary, its content is added to the metadata of all produced Documents.
+ If it's a list, the length of the list must match the number of sources, because the two lists will be zipped.
+ Defaults to `None`.
  :return: A dictionary containing a list of Document objects under the 'documents' key.
  """
  parser = MarkdownIt(renderer_cls=RendererPlain)
  if self.table_to_single_line:
  parser.enable("table")
 
  documents = []
-
- if meta is None:
- meta = [{}] * len(sources)
- elif len(sources) != len(meta):
- raise ValueError("The length of the metadata list must match the number of sources.")
+ meta_list = normalize_metadata(meta=meta, sources_count=len(sources))
 
  for source, metadata in tqdm(
- zip(sources, meta),
+ zip(sources, meta_list),
  total=len(sources),
  desc="Converting markdown files to Documents",
  disable=not self.progress_bar,

releasenotes/notes/main-082bae7b20bd605d.yaml

@@ -0,0 +1,33 @@
+---
+prelude: >
+ Replace this text with content to appear at the top of the section for this
+ release. This is equivalent to the "Highlights" section we used before.
+ The prelude might repeat some details that are also present in other notes
+ from the same release, that's ok. Not every release note requires a prelude,
+ use it only to describe major features or notable changes.
+upgrade:
+ - |
+ List upgrade notes here, or remove this section.
+ Upgrade notes should be rare: only list known/potential breaking changes,
+ or major changes that require user action before the upgrade.
+ Notes here must include steps that users can follow to 1. know if they're
+ affected and 2. handle the change gracefully on their end.
+features:
+ - |
+ List new features here, or remove this section.
+enhancements:
+ - |
+ List new behavior that is too small to be
+ considered a new feature, or remove this section.
+issues:
+ - |
+ List known issues here, or remove this section. For example, if some change is experimental or known to not work in some cases, it should be mentioned here.
+deprecations:
+ - |
+ List deprecations notes here, or remove this section. Deprecations should not be used for something that is removed in the release, use upgrade section instead. Deprecation should allow time for users to make necessary changes for the removal to happen in a future release.
+security:
+ - |
+ Add security notes here, or remove this section.
+fixes:
+ - |
+ Add normal bug fixes here, or remove this section.

test/components/converters/test_markdown_to_document.py

@@ -31,17 +31,19 @@ def test_run(self, test_files_path):
  assert "What to build with Haystack" in doc.content
  assert "# git clone https://github.com/deepset-ai/haystack.git" in doc.content
 
- def test_run_with_meta(self):
+ def test_run_with_meta(self, test_files_path):
  bytestream = ByteStream(data=b"test", meta={"author": "test_author", "language": "en"})
 
  converter = MarkdownToDocument()
 
  with patch("haystack.components.converters.markdown.MarkdownIt"):
- output = converter.run(sources=[bytestream], meta=[{"language": "it"}])
- document = output["documents"][0]
+ output = converter.run(
+ sources=[bytestream, test_files_path / "markdown" / "sample.md"], meta=[{"language": "it"}]
+ )
 
  # check that the metadata from the bytestream is merged with that from the meta parameter
- assert document.meta == {"author": "test_author", "language": "it"}
+ assert output["documents"][0].meta == {"author": "test_author", "language": "it"}
+ assert output["documents"][1].meta == {"language": "it"}
 
  @pytest.mark.integration
  def test_run_wrong_file_type(self, test_files_path, caplog):