feat/enhance the multi-modal support (#8818)

api/core/rag/extractor/word_extractor.py

@@ -121,7 +121,7 @@ class WordExtractor(BaseExtractor):
                 db.session.add(upload_file)
                 db.session.commit()
                 image_map[rel.target_part] = (
-                    f"![image]({dify_config.CONSOLE_API_URL}/files/{upload_file.id}/image-preview)"
+                    f"![image]({dify_config.CONSOLE_API_URL}/files/{upload_file.id}/file-preview)"
                 )
 
         return image_map

api/core/rag/retrieval/router/multi_dataset_react_route.py

@@ -9,7 +9,7 @@ from core.prompt.advanced_prompt_transform import AdvancedPromptTransform
 from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, CompletionModelPromptTemplate
 from core.rag.retrieval.output_parser.react_output import ReactAction
 from core.rag.retrieval.output_parser.structured_chat import StructuredChatOutputParser
-from core.workflow.nodes.llm.llm_node import LLMNode
+from core.workflow.nodes.llm import LLMNode
 
 PREFIX = """Respond to the human as helpfully and accurately as possible. You have access to the following tools:"""