Feat/support multimodal embedding (#29115)

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

api/core/rag/rerank/weight_rerank.py

@@ -7,6 +7,8 @@ from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
 from core.rag.datasource.keyword.jieba.jieba_keyword_table_handler import JiebaKeywordTableHandler
 from core.rag.embedding.cached_embedding import CacheEmbedding
+from core.rag.index_processor.constant.doc_type import DocType
+from core.rag.index_processor.constant.query_type import QueryType
 from core.rag.models.document import Document
 from core.rag.rerank.entity.weight import VectorSetting, Weights
 from core.rag.rerank.rerank_base import BaseRerankRunner
@@ -24,6 +26,7 @@ class WeightRerankRunner(BaseRerankRunner):
         score_threshold: float | None = None,
         top_n: int | None = None,
         user: str | None = None,
+        query_type: QueryType = QueryType.TEXT_QUERY,
     ) -> list[Document]:
         """
         Run rerank model
@@ -43,8 +46,10 @@ class WeightRerankRunner(BaseRerankRunner):
                 and document.metadata is not None
                 and document.metadata["doc_id"] not in doc_ids
             ):
-                doc_ids.add(document.metadata["doc_id"])
-                unique_documents.append(document)
+                # weight rerank only support text documents
+                if not document.metadata.get("doc_type") or document.metadata.get("doc_type") == DocType.TEXT:
+                    doc_ids.add(document.metadata["doc_id"])
+                    unique_documents.append(document)
             else:
                 if document not in unique_documents:
                     unique_documents.append(document)