fix wrong using of RetrievalMethod Enum (#6345)

langgenius · Jul 16, 2024 · 0de224b · 0de224b
1 parent ed9e692
commit 0de224b
Show file tree

Hide file tree

Showing 10 changed files with 24 additions and 24 deletions.
diff --git a/api/controllers/console/datasets/datasets.py b/api/controllers/console/datasets/datasets.py
@@ -545,15 +545,15 @@ def get(self):
             case VectorType.MILVUS | VectorType.RELYT | VectorType.PGVECTOR | VectorType.TIDB_VECTOR | VectorType.CHROMA | VectorType.TENCENT | VectorType.ORACLE:
                 return {
                     'retrieval_method': [
-                        RetrievalMethod.SEMANTIC_SEARCH
+                        RetrievalMethod.SEMANTIC_SEARCH.value
                     ]
                 }
             case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE:
                 return {
                     'retrieval_method': [
-                        RetrievalMethod.SEMANTIC_SEARCH,
-                        RetrievalMethod.FULL_TEXT_SEARCH,
-                        RetrievalMethod.HYBRID_SEARCH,
+                        RetrievalMethod.SEMANTIC_SEARCH.value,
+                        RetrievalMethod.FULL_TEXT_SEARCH.value,
+                        RetrievalMethod.HYBRID_SEARCH.value,
                     ]
                 }
             case _:
@@ -569,15 +569,15 @@ def get(self, vector_type):
             case VectorType.MILVUS | VectorType.RELYT | VectorType.PGVECTOR | VectorType.TIDB_VECTOR | VectorType.CHROMA | VectorType.TENCENT | VectorType.ORACLE:
                 return {
                     'retrieval_method': [
-                        RetrievalMethod.SEMANTIC_SEARCH
+                        RetrievalMethod.SEMANTIC_SEARCH.value
                     ]
                 }
             case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE:
                 return {
                     'retrieval_method': [
-                        RetrievalMethod.SEMANTIC_SEARCH,
-                        RetrievalMethod.FULL_TEXT_SEARCH,
-                        RetrievalMethod.HYBRID_SEARCH,
+                        RetrievalMethod.SEMANTIC_SEARCH.value,
+                        RetrievalMethod.FULL_TEXT_SEARCH.value,
+                        RetrievalMethod.HYBRID_SEARCH.value,
                     ]
                 }
             case _:

diff --git a/api/core/rag/datasource/retrieval_service.py b/api/core/rag/datasource/retrieval_service.py
@@ -11,7 +11,7 @@
 from models.dataset import Dataset
 
 default_retrieval_model = {
-    'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+    'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
     'reranking_enable': False,
     'reranking_model': {
         'reranking_provider_name': '',
@@ -86,7 +86,7 @@ def retrieve(cls, retrival_method: str, dataset_id: str, query: str,
             exception_message = ';\n'.join(exceptions)
             raise Exception(exception_message)
 
-        if retrival_method == RetrievalMethod.HYBRID_SEARCH:
+        if retrival_method == RetrievalMethod.HYBRID_SEARCH.value:
             data_post_processor = DataPostProcessor(str(dataset.tenant_id), reranking_model, False)
             all_documents = data_post_processor.invoke(
                 query=query,
@@ -142,7 +142,7 @@ def embedding_search(cls, flask_app: Flask, dataset_id: str, query: str,
                 )
 
                 if documents:
-                    if reranking_model and retrival_method == RetrievalMethod.SEMANTIC_SEARCH:
+                    if reranking_model and retrival_method == RetrievalMethod.SEMANTIC_SEARCH.value:
                         data_post_processor = DataPostProcessor(str(dataset.tenant_id), reranking_model, False)
                         all_documents.extend(data_post_processor.invoke(
                             query=query,
@@ -174,7 +174,7 @@ def full_text_index_search(cls, flask_app: Flask, dataset_id: str, query: str,
                     top_k=top_k
                 )
                 if documents:
-                    if reranking_model and retrival_method == RetrievalMethod.FULL_TEXT_SEARCH:
+                    if reranking_model and retrival_method == RetrievalMethod.FULL_TEXT_SEARCH.value:
                         data_post_processor = DataPostProcessor(str(dataset.tenant_id), reranking_model, False)
                         all_documents.extend(data_post_processor.invoke(
                             query=query,

diff --git a/api/core/rag/retrieval/dataset_retrieval.py b/api/core/rag/retrieval/dataset_retrieval.py
@@ -28,7 +28,7 @@
 from models.dataset import Document as DatasetDocument
 
 default_retrieval_model = {
-    'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+    'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
     'reranking_enable': False,
     'reranking_model': {
         'reranking_provider_name': '',
@@ -464,7 +464,7 @@ def to_dataset_retriever_tool(self, tenant_id: str,
         if retrieve_config.retrieve_strategy == DatasetRetrieveConfigEntity.RetrieveStrategy.SINGLE:
             # get retrieval model config
             default_retrieval_model = {
-                'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+                'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
                 'reranking_enable': False,
                 'reranking_model': {
                     'reranking_provider_name': '',

diff --git a/api/core/rag/retrieval/retrival_methods.py b/api/core/rag/retrieval/retrival_methods.py
@@ -1,15 +1,15 @@
 from enum import Enum
 
 
-class RetrievalMethod(str, Enum):
+class RetrievalMethod(Enum):
     SEMANTIC_SEARCH = 'semantic_search'
     FULL_TEXT_SEARCH = 'full_text_search'
     HYBRID_SEARCH = 'hybrid_search'
 
     @staticmethod
     def is_support_semantic_search(retrieval_method: str) -> bool:
-        return retrieval_method in {RetrievalMethod.SEMANTIC_SEARCH, RetrievalMethod.HYBRID_SEARCH}
+        return retrieval_method in {RetrievalMethod.SEMANTIC_SEARCH.value, RetrievalMethod.HYBRID_SEARCH.value}
 
     @staticmethod
     def is_support_fulltext_search(retrieval_method: str) -> bool:
-        return retrieval_method in {RetrievalMethod.FULL_TEXT_SEARCH, RetrievalMethod.HYBRID_SEARCH}
+        return retrieval_method in {RetrievalMethod.FULL_TEXT_SEARCH.value, RetrievalMethod.HYBRID_SEARCH.value}
diff --git a/api/core/tools/tool/dataset_retriever/dataset_multi_retriever_tool.py b/api/core/tools/tool/dataset_retriever/dataset_multi_retriever_tool.py
@@ -14,7 +14,7 @@
 from models.dataset import Dataset, Document, DocumentSegment
 
 default_retrieval_model = {
-    'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+    'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
     'reranking_enable': False,
     'reranking_model': {
         'reranking_provider_name': '',

diff --git a/api/core/tools/tool/dataset_retriever/dataset_retriever_tool.py b/api/core/tools/tool/dataset_retriever/dataset_retriever_tool.py
@@ -8,7 +8,7 @@
 from models.dataset import Dataset, Document, DocumentSegment
 
 default_retrieval_model = {
-    'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+    'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
     'reranking_enable': False,
     'reranking_model': {
         'reranking_provider_name': '',

diff --git a/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py b/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
@@ -22,7 +22,7 @@
 from models.workflow import WorkflowNodeExecutionStatus
 
 default_retrieval_model = {
-    'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+    'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
     'reranking_enable': False,
     'reranking_model': {
         'reranking_provider_name': '',

diff --git a/api/models/dataset.py b/api/models/dataset.py
@@ -117,7 +117,7 @@ def doc_form(self):
     @property
     def retrieval_model_dict(self):
         default_retrieval_model = {
-            'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+            'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
             'reranking_enable': False,
             'reranking_model': {
                 'reranking_provider_name': '',

diff --git a/api/services/dataset_service.py b/api/services/dataset_service.py
@@ -688,7 +688,7 @@ def save_document_with_dataset_id(
                 dataset.collection_binding_id = dataset_collection_binding.id
                 if not dataset.retrieval_model:
                     default_retrieval_model = {
-                        'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+                        'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
                         'reranking_enable': False,
                         'reranking_model': {
                             'reranking_provider_name': '',
@@ -1059,7 +1059,7 @@ def save_document_without_dataset_id(tenant_id: str, document_data: dict, accoun
                 retrieval_model = document_data['retrieval_model']
             else:
                 default_retrieval_model = {
-                    'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+                    'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
                     'reranking_enable': False,
                     'reranking_model': {
                         'reranking_provider_name': '',

diff --git a/api/services/hit_testing_service.py b/api/services/hit_testing_service.py
@@ -9,7 +9,7 @@
 from models.dataset import Dataset, DatasetQuery, DocumentSegment
 
 default_retrieval_model = {
-    'search_method': RetrievalMethod.SEMANTIC_SEARCH,
+    'search_method': RetrievalMethod.SEMANTIC_SEARCH.value,
     'reranking_enable': False,
     'reranking_model': {
         'reranking_provider_name': '',