fix: Large document thumbnail display failed (#2763)

### What problem does this PR solve?

In MySQL, when the thumbnail base64 of a document is relatively large,
the display of the document's thumbnail fails.
Now, I put the document thumbnail into MiniIO storage.

### Type of change

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

---------

Co-authored-by: chongchuanbing <[email protected]>

api/apps/document_app.py

@@ -51,6 +51,7 @@ from api.utils.api_utils import get_json_result
 from rag.utils.storage_factory import STORAGE_IMPL
 from api.utils.file_utils import filename_type, thumbnail, get_project_base_directory
 from api.utils.web_utils import html2pdf, is_valid_url
+from api.contants import IMG_BASE64_PREFIX
 
 
 @manager.route('/upload', methods=['POST'])
@@ -209,6 +210,11 @@ def list_docs():
     try:
         docs, tol = DocumentService.get_by_kb_id(
             kb_id, page_number, items_per_page, orderby, desc, keywords)
+
+        for doc_item in docs:
+            if doc_item['thumbnail'] and not doc_item['thumbnail'].startswith(IMG_BASE64_PREFIX):
+                doc_item['thumbnail'] = f'/v1/document/image/{kb_id}-{doc_item['thumbnail']}'
+
         return get_json_result(data={"total": tol, "docs": docs})
     except Exception as e:
         return server_error_response(e)

api/contants.py

@@ -13,4 +13,6 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-NAME_LENGTH_LIMIT = 2 ** 10
+NAME_LENGTH_LIMIT = 2 ** 10
+
+IMG_BASE64_PREFIX = 'data:image/png;base64,'

api/db/services/file_service.py

@@ -26,7 +26,7 @@ from api.db.services.common_service import CommonService
 from api.db.services.document_service import DocumentService
 from api.db.services.file2document_service import File2DocumentService
 from api.utils import get_uuid
-from api.utils.file_utils import filename_type, thumbnail
+from api.utils.file_utils import filename_type, thumbnail_img
 from rag.utils.storage_factory import STORAGE_IMPL
 
 
@@ -354,8 +354,15 @@ class FileService(CommonService):
                     location += "_"
                 blob = file.read()
                 STORAGE_IMPL.put(kb.id, location, blob)
+
+                doc_id = get_uuid()
+
+                img = thumbnail_img(filename, blob)
+                thumbnail_location = f'thumbnail_{doc_id}.png'
+                STORAGE_IMPL.put(kb.id, thumbnail_location, img)
+
                 doc = {
-                    "id": get_uuid(),
+                    "id": doc_id,
                     "kb_id": kb.id,
                     "parser_id": self.get_parser(filetype, filename, kb.parser_id),
                     "parser_config": kb.parser_config,
@@ -364,7 +371,7 @@ class FileService(CommonService):
                     "name": filename,
                     "location": location,
                     "size": len(blob),
-                    "thumbnail": thumbnail(filename, blob)
+                    "thumbnail": thumbnail_location
                 }
                 DocumentService.insert(doc)
 

api/utils/file_utils.py

@@ -25,6 +25,7 @@ from cachetools import LRUCache, cached
 from ruamel.yaml import YAML
 
 from api.db import FileType
+from api.contants import IMG_BASE64_PREFIX
 
 PROJECT_BASE = os.getenv("RAG_PROJECT_BASE") or os.getenv("RAG_DEPLOY_BASE")
 RAG_BASE = os.getenv("RAG_BASE")
@@ -168,23 +169,20 @@ def filename_type(filename):
 
     return FileType.OTHER.value
 
-
-def thumbnail(filename, blob):
+def thumbnail_img(filename, blob):
     filename = filename.lower()
     if re.match(r".*\.pdf$", filename):
         pdf = pdfplumber.open(BytesIO(blob))
         buffered = BytesIO()
         pdf.pages[0].to_image(resolution=32).annotated.save(buffered, format="png")
-        return "data:image/png;base64," + \
-            base64.b64encode(buffered.getvalue()).decode("utf-8")
+        return buffered.getvalue()
 
     if re.match(r".*\.(jpg|jpeg|png|tif|gif|icon|ico|webp)$", filename):
         image = Image.open(BytesIO(blob))
         image.thumbnail((30, 30))
         buffered = BytesIO()
         image.save(buffered, format="png")
-        return "data:image/png;base64," + \
-            base64.b64encode(buffered.getvalue()).decode("utf-8")
+        return buffered.getvalue()
 
     if re.match(r".*\.(ppt|pptx)$", filename):
         import aspose.slides as slides
@@ -194,11 +192,15 @@ def thumbnail(filename, blob):
                 buffered = BytesIO()
                 presentation.slides[0].get_thumbnail(0.03, 0.03).save(
                     buffered, drawing.imaging.ImageFormat.png)
-                return "data:image/png;base64," + \
-                    base64.b64encode(buffered.getvalue()).decode("utf-8")
+                return buffered.getvalue()
         except Exception as e:
             pass
+    return None
 
+def thumbnail(filename, blob):
+    img = thumbnail_img(filename, blob)
+    return IMG_BASE64_PREFIX + \
+        base64.b64encode(img).decode("utf-8")
 
 def traversal_files(base):
     for root, ds, fs in os.walk(base):