klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-06 13:22:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Handle skip indexing of unsupported image files

Browse Source 
Previously unsupported image file types would trigger an unbound local
variable error.
This commit is contained in:
Debanjum
2025-10-13 15:42:43 -04:00
parent 749bbed23d
commit a809de8970
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/khoj/processor/content/images/image_to_entries.py
View File

@@ -54,6 +54,7 @@ class ImageToEntries(TextToEntries):
entries: List[str] = [] entries: List[str] = []
entry_to_location_map: List[Tuple[str, str]] = [] entry_to_location_map: List[Tuple[str, str]] = []
for image_file in image_files: for image_file in image_files:
tmp_file = None
try: try:
bytes = image_files[image_file] bytes = image_files[image_file]
# write the image to a temporary file # write the image to a temporary file
@@ -65,6 +66,8 @@ class ImageToEntries(TextToEntries):
tmp_file = f"tmp_image_file_{timestamp_now}.jpg" tmp_file = f"tmp_image_file_{timestamp_now}.jpg"
elif image_file.endswith(".webp"): elif image_file.endswith(".webp"):
tmp_file = f"tmp_image_file_{timestamp_now}.webp" tmp_file = f"tmp_image_file_{timestamp_now}.webp"
else:
continue
with open(tmp_file, "wb") as f: with open(tmp_file, "wb") as f:
bytes = image_files[image_file] bytes = image_files[image_file]
f.write(bytes) f.write(bytes)
@@ -89,7 +92,7 @@ class ImageToEntries(TextToEntries):
logger.warning(f"Unable to process file: {image_file}. This file will not be indexed.") logger.warning(f"Unable to process file: {image_file}. This file will not be indexed.")
logger.warning(e, exc_info=True) logger.warning(e, exc_info=True)
finally: finally:
if os.path.exists(tmp_file): if tmp_file and os.path.exists(tmp_file):
os.remove(tmp_file) os.remove(tmp_file)
return file_to_text_map, ImageToEntries.convert_image_entries_to_maps(entries, dict(entry_to_location_map)) return file_to_text_map, ImageToEntries.convert_image_entries_to_maps(entries, dict(entry_to_location_map))