Fix: reject empty/space-only content in update_chunk API (#14082)

Closes #6541

### What problem does this PR solve?

Add content validation to `update_chunk` (SDK and non-SDK) to reject
empty or whitespace-only content before it reaches the embedding model.

**Before:** Calling `update_chunk` with space-only content (like `" "`,
`""`, `"\n"`) bypassed validation and was sent directly to the embedding
model, which returned an error. This was the same bug previously fixed
for `add_chunk` in #6390, but `update_chunk` was missed.

**After:** Empty/whitespace-only content is caught by validation and
returns an error: `` `content` is required ``

### Type of change

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

api/apps/chunk_app.py

@@ -43,7 +43,7 @@ from rag.app.qa import beAdoc, rmPrefix
 from rag.app.tag import label_question
 from rag.nlp import rag_tokenizer, search
 from rag.prompts.generator import cross_languages, keyword_extraction
-from common.string_utils import remove_redundant_spaces
+from common.string_utils import is_content_empty, remove_redundant_spaces
 from common.constants import RetCode, LLMType, ParserType, PAGERANK_FLD
 from common import settings
 from api.apps import login_required, current_user
@@ -140,6 +140,8 @@ async def set():
         raise TypeError("expected string or bytes-like object")
     if isinstance(content_with_weight, bytes):
         content_with_weight = content_with_weight.decode("utf-8", errors="ignore")
+    if is_content_empty(content_with_weight):
+        return get_data_error_result(message="`content_with_weight` is required")
     d = {
         "id": req["chunk_id"],
         "content_with_weight": content_with_weight}

api/apps/sdk/doc.py

@@ -38,7 +38,7 @@ from common import settings
 from common.constants import FileSource, LLMType, ParserType, RetCode, TaskStatus
 from common.metadata_utils import convert_conditions, meta_filter
 from common.misc_utils import thread_pool_exec
-from common.string_utils import remove_redundant_spaces
+from common.string_utils import is_content_empty, remove_redundant_spaces
 from common.tag_feature_utils import validate_tag_features
 from rag.app.qa import beAdoc, rmPrefix
 from rag.app.tag import label_question
@@ -933,7 +933,7 @@ async def add_chunk(tenant_id, dataset_id, document_id):
         return get_error_data_result(message=f"You don't own the document {document_id}.")
     doc = doc[0]
     req = await get_request_json()
-    if not str(req.get("content", "")).strip():
+    if is_content_empty(req.get("content")):
         return get_error_data_result(message="`content` is required")
     if "important_keywords" in req:
         if not isinstance(req["important_keywords"], list):
@@ -1176,8 +1176,10 @@ async def update_chunk(tenant_id, dataset_id, document_id, chunk_id):
         return get_error_data_result(message=f"You don't own the document {document_id}.")
     doc = doc[0]
     req = await get_request_json()
-    if "content" in req and req["content"] is not None:
-        content = req["content"]
+    content = req.get("content")
+    if content is not None:
+        if is_content_empty(content):
+            return get_error_data_result(message="`content` is required")
     else:
         content = chunk.get("content_with_weight", "")
     d = {"id": chunk_id, "content_with_weight": content}