multi-retrival use dataset's top-k (langgenius#8416)

LLmoskk · Sep 16, 2024 · 33f6cba · 33f6cba
1 parent 30e0cb7
commit 33f6cba
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 3 deletions.
diff --git a/api/core/rag/retrieval/dataset_retrieval.py b/api/core/rag/retrieval/dataset_retrieval.py
@@ -426,7 +426,7 @@ def _retriever(self, flask_app: Flask, dataset_id: str, query: str, top_k: int,
                         retrieval_method=retrieval_model["search_method"],
                         dataset_id=dataset.id,
                         query=query,
-                        top_k=top_k,
+                        top_k=retrieval_model.get("top_k") or 2,
                         score_threshold=retrieval_model.get("score_threshold", 0.0)
                         if retrieval_model["score_threshold_enabled"]
                         else 0.0,

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
@@ -165,7 +165,10 @@ def _retriever(
             if dataset.indexing_technique == "economy":
                 # use keyword table query
                 documents = RetrievalService.retrieve(
-                    retrieval_method="keyword_search", dataset_id=dataset.id, query=query, top_k=self.top_k
+                    retrieval_method="keyword_search",
+                    dataset_id=dataset.id,
+                    query=query,
+                    top_k=retrieval_model.get("top_k") or 2,
                 )
                 if documents:
                     all_documents.extend(documents)
@@ -176,7 +179,7 @@ def _retriever(
                         retrieval_method=retrieval_model["search_method"],
                         dataset_id=dataset.id,
                         query=query,
-                        top_k=self.top_k,
+                        top_k=retrieval_model.get("top_k") or 2,
                         score_threshold=retrieval_model.get("score_threshold", 0.0)
                         if retrieval_model["score_threshold_enabled"]
                         else 0.0,