[Question]: The parsed document fragment tags are only of type Text

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (Language Policy).
• Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
• Please do not modify this template :) and fill in all the required fields.

Describe your problem

After deploying in Ubuntu, DeepDoc is used to parse document content. The labels of parsed images and table fragments change from Image and Table to Text. The operation log is as follows： “”“ ragflow-cpu-1 | 2026-05-21 08:51:07,356 INFO 47 load_model /ragflow/rag/res/deepdoc/det.onnx reuses cached model ragflow-cpu-1 | 2026-05-21 08:51:07,363 INFO 47 load_model /ragflow/rag/res/deepdoc/rec.onnx reuses cached model ragflow-cpu-1 | 2026-05-21 08:51:08,139 INFO 47 load_model /ragflow/rag/res/deepdoc/layout.onnx uses CPU ragflow-cpu-1 | 2026-05-21 08:51:08,221 INFO 47 load_model /ragflow/rag/res/deepdoc/tsr.onnx uses CPU ragflow-cpu-1 | 2026-05-21 08:51:08,223 INFO 47 updown_cnt_mdl initialized on CPU ....... ragflow-cpu-1 | 2026-05-21 08:51:14,777 INFO 47 handle_task done for task {"id": "2575a76254af11f1b933edf481ce3f0b", "doc_id": "24114df454af11f1b933edf481ce3f0b", "from_page": 0, "to_page": 1, "retry_count": 0, "kb_id": "177f05d654af11f1b933edf481ce3f0b", "parser_id": "naive", "parser_config": {"table_context_size": 0, "image_context_size": 0, "layout_recognize": "DeepDOC", "chunk_token_num": 512, "delimiter": "\n", "auto_keywords": 0, "auto_questions": 0, "html4excel": false, "topn_tags": 3, "raptor": {"use_raptor": true, "prompt": "Please summarize the following paragraphs. Be careful with the numbers, do not make things up. Paragraphs as following:\n {cluster_content}\nThe above is the content you need to summarize.", "max_token": 256, "threshold": 0.1, "max_cluster": 64, "random_seed": 0}, "graphrag": {"use_graphrag": true, "entity_types": ["organization", "person", "geo", "event", "category"], "method": "light"}, "parent_child": {"use_parent_child": false, "children_delimiter": "\n"}, "children_delimiter": "", "llm_id": "qwen3.5-plus@Tongyi-Qianwen"}, "name": "\u65b0\u7586\u548c\u5e03\u514b\u8d5b\u5c14\u53bf\u4e4c\u4ec0\u52a0\u560e\u8863\u63d0\u5730\u533a\u91d1\u94dc\u591a\u91d1\u5c5e\u77ff\u4fe1\u606f.pdf", "type": "pdf", "location": "\u65b0\u7586\u548c\u5e03\u514b\u8d5b\u5c14\u53bf\u4e4c\u4ec0\u52a0\u560e\u8863\u63d0\u5730\u533a\u91d1\u94dc\u591a\u91d1\u5c5e\u77ff\u4fe1\u606f.pdf", "size": 1163328, "tenant_id": "fea31f2054ae11f1b933edf481ce3f0b", "language": "English", "embd_id": "Qwen/Qwen3-Embedding-8B@SILICONFLOW", "pagerank": 0, "kb_parser_config": {"table_context_size": 0, "image_context_size": 0, "layout_recognize": "DeepDOC", "chunk_token_num": 512, "delimiter": "\n", “”“ How can I solve this problem, please