Skip to content

Commit

Permalink
remove space from MarkdownNodeParser Header metadata (run-llama#11982)
Browse files Browse the repository at this point in the history
  • Loading branch information
haarisedhi102 authored Mar 17, 2024
1 parent d651dbb commit 5c53f41
Show file tree
Hide file tree
Showing 2 changed files with 10 additions and 10 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -99,11 +99,11 @@ def _update_metadata(
updated_headers = {}

for i in range(1, new_header_level):
key = f"Header {i}"
key = f"Header_{i}"
if key in headers_metadata:
updated_headers[key] = headers_metadata[key]

updated_headers[f"Header {new_header_level}"] = new_header
updated_headers[f"Header_{new_header_level}"] = new_header
return updated_headers

def _build_node_from_split(
Expand Down
16 changes: 8 additions & 8 deletions llama-index-core/tests/node_parser/test_markdown.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,8 @@ def test_header_splits() -> None:
]
)
assert len(splits) == 2
assert splits[0].metadata == {"Header 1": "Main Header"}
assert splits[1].metadata == {"Header 1": "Header 2"}
assert splits[0].metadata == {"Header_1": "Main Header"}
assert splits[1].metadata == {"Header_1": "Header 2"}
assert splits[0].text == "Main Header\n\nHeader 1 content"
assert splits[1].text == "Header 2\nHeader 2 content"

Expand Down Expand Up @@ -80,11 +80,11 @@ def test_header_metadata() -> None:
]
)
assert len(splits) == 4
assert splits[0].metadata == {"Header 1": "Main Header"}
assert splits[1].metadata == {"Header 1": "Main Header", "Header 2": "Sub-header"}
assert splits[0].metadata == {"Header_1": "Main Header"}
assert splits[1].metadata == {"Header_1": "Main Header", "Header_2": "Sub-header"}
assert splits[2].metadata == {
"Header 1": "Main Header",
"Header 2": "Sub-header",
"Header 3": "Sub-sub header",
"Header_1": "Main Header",
"Header_2": "Sub-header",
"Header_3": "Sub-sub header",
}
assert splits[3].metadata == {"Header 1": "New title"}
assert splits[3].metadata == {"Header_1": "New title"}

0 comments on commit 5c53f41

Please sign in to comment.