youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-03 17:08:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

修复top-k硬编码回退问题

Browse Source
This commit is contained in:
Frederick2313072
2025-09-01 14:27:43 +08:00
parent f11131f8b5
commit dd7de74aa6
11 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
api/core/rag/datasource/retrieval_service.py
View File

@ -24,7 +24,7 @@ default_retrieval_model = {
"search_method": RetrievalMethod.SEMANTIC_SEARCH.value,
"reranking_enable": False,
"reranking_model": {"reranking_provider_name": "", "reranking_model_name": ""},
"top_k": 2,
"top_k": 4,
"score_threshold_enabled": False,
}

2
api/core/rag/datasource/vdb/couchbase/couchbase_vector.py
View File

@ -304,7 +304,7 @@ class CouchbaseVector(BaseVector):
return docs
def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
top_k = kwargs.get("top_k", 2)
top_k = kwargs.get("top_k", 4)
try:
CBrequest = search.SearchRequest.create(search.QueryStringQuery("text:" + query))
search_iter = self._scope.search(

6
api/core/rag/retrieval/dataset_retrieval.py
View File

@ -65,7 +65,7 @@ default_retrieval_model: dict[str, Any] = {
"search_method": RetrievalMethod.SEMANTIC_SEARCH.value,
"reranking_enable": False,
"reranking_model": {"reranking_provider_name": "", "reranking_model_name": ""},
"top_k": 2,
"top_k": 4,
"score_threshold_enabled": False,
}
@ -647,7 +647,7 @@ class DatasetRetrieval:
retrieval_method=retrieval_model["search_method"],
dataset_id=dataset.id,
query=query,
top_k=retrieval_model.get("top_k") or 2,
top_k=retrieval_model.get("top_k") or 4,
score_threshold=retrieval_model.get("score_threshold", 0.0)
if retrieval_model["score_threshold_enabled"]
else 0.0,
@ -743,7 +743,7 @@ class DatasetRetrieval:
tool = DatasetMultiRetrieverTool.from_dataset(
dataset_ids=[dataset.id for dataset in available_datasets],
tenant_id=tenant_id,
top_k=retrieve_config.top_k or 2,
top_k=retrieve_config.top_k or 4,
score_threshold=retrieve_config.score_threshold,
hit_callbacks=[hit_callback],
return_resource=return_resource,

4
api/core/tools/utils/dataset_retriever/dataset_multi_retriever_tool.py
View File

@ -181,7 +181,7 @@ class DatasetMultiRetrieverTool(DatasetRetrieverBaseTool):
retrieval_method="keyword_search",
dataset_id=dataset.id,
query=query,
top_k=retrieval_model.get("top_k") or 2,
top_k=retrieval_model.get("top_k") or 4,
)
if documents:
all_documents.extend(documents)
@ -192,7 +192,7 @@ class DatasetMultiRetrieverTool(DatasetRetrieverBaseTool):
retrieval_method=retrieval_model["search_method"],
dataset_id=dataset.id,
query=query,
top_k=retrieval_model.get("top_k") or 2,
top_k=retrieval_model.get("top_k") or 4,
score_threshold=retrieval_model.get("score_threshold", 0.0)
if retrieval_model["score_threshold_enabled"]
else 0.0,

2
api/core/tools/utils/dataset_retriever/dataset_retriever_base_tool.py
View File

@ -13,7 +13,7 @@ class DatasetRetrieverBaseTool(BaseModel, ABC):
name: str = "dataset"
description: str = "use this to retrieve a dataset. "
tenant_id: str
top_k: int = 2
top_k: int = 4
score_threshold: Optional[float] = None
hit_callbacks: list[DatasetIndexToolCallbackHandler] = []
return_resource: bool

2
api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
View File

@ -78,7 +78,7 @@ default_retrieval_model = {
"search_method": RetrievalMethod.SEMANTIC_SEARCH.value,
"reranking_enable": False,
"reranking_model": {"reranking_provider_name": "", "reranking_model_name": ""},
"top_k": 2,
"top_k": 4,
"score_threshold_enabled": False,
}