Fix: docx get image exception. (#7636)

### What problem does this PR solve?

Close #7631

### Type of change

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

rag/app/naive.py

         except InvalidImageStreamError:
             logging.info("The recognized image stream appears to be corrupted. Skipping image.")
             return None
+        except UnicodeDecodeError:
+            logging.info("The recognized image stream appears to be corrupted. Skipping image.")
+            return None
         try:
             image = Image.open(BytesIO(image_blob)).convert('RGB')
             return image

rag/prompts.py

             "similarity": chunk.get("similarity"),
             "vector_similarity": chunk.get("vector_similarity"),
             "term_similarity": chunk.get("term_similarity"),
+            "doc_type": chunk.get("doc_type_kwd"),
         }
         for chunk in reference.get("chunks", [])
     ]