forked from AI_team/Philosophy-RAG-demo
Add logging info when skipping file or website
This commit is contained in:
parent
a6e9c95a6d
commit
450a00e6fe
@ -29,6 +29,7 @@ def add_urls(vector_store: Chroma, urls: list[str], chunk_size: int) -> None:
|
||||
all_splits = []
|
||||
for url in urls:
|
||||
if len(vector_store.get(where={"source": url}, limit=1)["ids"]) > 0:
|
||||
logging.info(f"Skipping URL {url}, as it is already in the database.")
|
||||
continue
|
||||
|
||||
response = requests.get(url)
|
||||
@ -70,6 +71,8 @@ def add_pdf_files(
|
||||
for pdf_file in pdf_files:
|
||||
if len(vector_store.get(where={"source": str(pdf_file)}, limit=1)["ids"]) == 0:
|
||||
new_pdfs.append(pdf_file)
|
||||
else:
|
||||
logging.info(f"Skipping PDF {pdf_file}, as it is already in the database.")
|
||||
|
||||
if len(new_pdfs) == 0:
|
||||
return
|
||||
|
||||
Loading…
Reference in New Issue
Block a user