feat: mix search weight (#4170)

* feat: mix search weight

* feat: svg render

packages/service/core/dataset/search/controller.ts

@@ -40,6 +40,7 @@ export type SearchDatasetDataProps = {
   [NodeInputKeyEnum.datasetSimilarity]?: number; // min distance
   [NodeInputKeyEnum.datasetMaxTokens]: number; // max Token limit
   [NodeInputKeyEnum.datasetSearchMode]?: `${DatasetSearchModeEnum}`;
+  [NodeInputKeyEnum.datasetSearchEmbeddingWeight]?: number;
 
   [NodeInputKeyEnum.datasetSearchUsingReRank]?: boolean;
   [NodeInputKeyEnum.datasetSearchRerankModel]?: RerankModelItemType;
@@ -161,6 +162,7 @@ export async function searchDatasetData(
     similarity = 0,
     limit: maxTokens,
     searchMode = DatasetSearchModeEnum.embedding,
+    embeddingWeight = 0.5,
     usingReRank = false,
     rerankModel,
     rerankWeight = 0.5,
@@ -731,16 +733,20 @@ export async function searchDatasetData(
   })();
 
   // embedding recall and fullText recall rrf concat
+  const baseK = 120;
+  const embK = Math.round(baseK * (1 - embeddingWeight)); // 搜索结果的 k 值
+  const fullTextK = Math.round(baseK * embeddingWeight); // rerank 结果的 k 值
+
   const rrfSearchResult = datasetSearchResultConcat([
-    { k: 60, list: embeddingRecallResults },
-    { k: 60, list: fullTextRecallResults }
+    { k: embK, list: embeddingRecallResults },
+    { k: fullTextK, list: fullTextRecallResults }
   ]);
   const rrfConcatResults = (() => {
+    if (reRankResults.length === 0) return rrfSearchResult;
     if (rerankWeight === 1) return reRankResults;
 
-    const baseK = 30;
-    const searchK = Math.round(baseK / (1 - rerankWeight)); // 搜索结果的 k 值
-    const rerankK = Math.round(baseK / rerankWeight); // rerank 结果的 k 值
+    const searchK = Math.round(baseK * rerankWeight); // 搜索结果的 k 值
+    const rerankK = Math.round(baseK * (1 - rerankWeight)); // rerank 结果的 k 值
 
     return datasetSearchResultConcat([
       { k: searchK, list: rrfSearchResult },

packages/service/core/workflow/dispatch/dataset/search.ts

@@ -22,8 +22,9 @@ type DatasetSearchProps = ModuleDispatchProps<{
   [NodeInputKeyEnum.datasetSelectList]: SelectedDatasetType;
   [NodeInputKeyEnum.datasetSimilarity]: number;
   [NodeInputKeyEnum.datasetMaxTokens]: number;
-  [NodeInputKeyEnum.datasetSearchMode]: `${DatasetSearchModeEnum}`;
   [NodeInputKeyEnum.userChatInput]?: string;
+  [NodeInputKeyEnum.datasetSearchMode]: `${DatasetSearchModeEnum}`;
+  [NodeInputKeyEnum.datasetSearchEmbeddingWeight]?: number;
 
   [NodeInputKeyEnum.datasetSearchUsingReRank]: boolean;
   [NodeInputKeyEnum.datasetSearchRerankModel]?: string;
@@ -57,11 +58,11 @@ export async function dispatchDatasetSearch(
       datasets = [],
       similarity,
       limit = 1500,
-      searchMode,
       userChatInput = '',
       authTmbId = false,
       collectionFilterMatch,
-
+      searchMode,
+      embeddingWeight,
       usingReRank,
       rerankModel,
       rerankWeight,
@@ -129,6 +130,7 @@ export async function dispatchDatasetSearch(
     limit,
     datasetIds,
     searchMode,
+    embeddingWeight,
     usingReRank: usingReRank && (await checkTeamReRankPermission(teamId)),
     rerankModel: getRerankModel(rerankModel),
     rerankWeight,
@@ -228,6 +230,9 @@ export async function dispatchDatasetSearch(
     similarity: usingSimilarityFilter ? similarity : undefined,
     limit,
     searchMode,
+    embeddingWeight: searchMode === DatasetSearchModeEnum.mixedRecall ? embeddingWeight : undefined,
+    rerankModel: usingReRank ? getRerankModel(rerankModel)?.name : undefined,
+    rerankWeight: usingReRank ? rerankWeight : undefined,
     searchUsingReRank: searchUsingReRank,
     quoteList: searchRes,
     queryExtensionResult,