Skip to content

Commit 08fdeac

Browse files
committed
2 parents 8467cb0 + 6aeea1d commit 08fdeac

File tree

2 files changed

+11
-2
lines changed

2 files changed

+11
-2
lines changed

sources/gc-qa-rag-etl/etlapp/das/das_generic.py

Lines changed: 8 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -118,8 +118,14 @@ def das_generic_main(
118118
ensure_folder_exists(output_dir)
119119

120120
logger.info(f"MarkItDown instance is getting")
121-
markitdown_inst = get_markitdown_inst()
122-
logger.info(f"MarkItDown instance created")
121+
markitdown_inst = None
122+
try:
123+
markitdown_inst = get_markitdown_inst()
124+
logger.info(f"MarkItDown instance created")
125+
except:
126+
markitdown_inst = None
127+
logger.info(f"MarkItDown instance created failed")
128+
return
123129

124130
files = collect_files(input_dir)
125131
logger.info(f"Found {len(files)} files in {input_dir}")

sources/gc-qa-rag-etl/etlapp/ved/initialize_forum_qa.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -210,6 +210,9 @@ def start_initialize_forum_qa(context: EtlRagContext) -> None:
210210
content = read_text_from_file(file_path)
211211
forum = extract_object(content)
212212

213+
if not thread_dict[file_index]["content"]:
214+
continue
215+
213216
metadata = {
214217
"product": product,
215218
"url": thread_dict[file_index]["content"]["url"],

0 commit comments

Comments
 (0)