klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-02 21:19:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix path issues for URL-based markdown files

Browse Source
This commit is contained in:
sabaimran
2023-07-01 00:25:11 -07:00
parent 01aa285d7b
commit d01afb3ee4
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/khoj/processor/markdown/markdown_to_jsonl.py
View File

@@ -141,7 +141,14 @@ class MarkdownToJsonl(TextToJsonl):
"Convert each Markdown entries into a dictionary"
entries = []
for parsed_entry in parsed_entries:
entry_filename = Path(entry_to_file_map[parsed_entry])
raw_filename = entry_to_file_map[parsed_entry]
# Check if raw_filename is a URL. If so, save it as is. If not, convert it to a Path.
if re.search(r"^https?://", raw_filename):
entry_filename = raw_filename
else:
entry_filename = Path(raw_filename)
heading = parsed_entry.splitlines()[0] if re.search("^#+\s", parsed_entry) else ""
# Append base filename to compiled entry for context to model
# Increment heading level for heading entries and make filename as its top level heading