Fix: add download stats to kb logs. (#11112)

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

rag/app/naive.py

@@ -478,12 +478,14 @@ class Markdown(MarkdownParser):
         images = []
         # Find all image URLs in text
         for url in image_urls:
+            if not url:
+                continue
             try:
                 # check if the url is a local file or a remote URL
                 if url.startswith(('http://', 'https://')):
                     # For remote URLs, download the image
                     response = requests.get(url, stream=True, timeout=30)
-                    if response.status_code == 200 and response.headers['Content-Type'].startswith('image/'):
+                    if response.status_code == 200 and response.headers['Content-Type'] and response.headers['Content-Type'].startswith('image/'):
                         img = Image.open(BytesIO(response.content)).convert('RGB')
                         images.append(img)
                 else:

rag/svr/sync_data_source.py

@@ -258,6 +258,14 @@ func_factory = {
 
 async def dispatch_tasks():
     async with trio.open_nursery() as nursery:
+        while True:
+            try:
+                list(SyncLogsService.list_sync_tasks()[0])
+                break
+            except Exception as e:
+                logging.warning(f"DB is not ready yet: {e}")
+                await trio.sleep(3)
+
         for task in SyncLogsService.list_sync_tasks()[0]:
             if task["poll_range_start"]:
                 task["poll_range_start"] = task["poll_range_start"].astimezone(timezone.utc)