diff --git a/server/routers/evaluation_router.py b/server/routers/evaluation_router.py
index 913eb7b6..6036e1e3 100644
--- a/server/routers/evaluation_router.py
+++ b/server/routers/evaluation_router.py
@@ -149,7 +149,7 @@ async def run_evaluation(db_id: str, params: dict = Body(...), current_user: Use
task_id = await service.run_evaluation(
db_id=db_id,
benchmark_id=params.get("benchmark_id"),
- retrieval_config=params.get("retrieval_config", {}),
+ model_config=params.get("model_config", {}),
created_by=current_user.user_id,
)
return {"message": "success", "data": {"task_id": task_id}}
diff --git a/server/routers/knowledge_router.py b/server/routers/knowledge_router.py
index e579f204..2ccc83aa 100644
--- a/server/routers/knowledge_router.py
+++ b/server/routers/knowledge_router.py
@@ -702,13 +702,20 @@ async def update_knowledge_base_query_params(
if db_id not in knowledge_base.global_databases_meta:
knowledge_base.global_databases_meta[db_id] = {}
- # 保存查询参数到元数据
+ # 初始化 query_params 结构
if "query_params" not in knowledge_base.global_databases_meta[db_id]:
knowledge_base.global_databases_meta[db_id]["query_params"] = {}
- knowledge_base.global_databases_meta[db_id]["query_params"].update(params)
+ # 将参数保存到 options 下，与评估服务期望的结构一致
+ if "options" not in knowledge_base.global_databases_meta[db_id]["query_params"]:
+ knowledge_base.global_databases_meta[db_id]["query_params"]["options"] = {}
+
+ # 更新 options
+ knowledge_base.global_databases_meta[db_id]["query_params"]["options"].update(params)
knowledge_base._save_global_metadata()
+ logger.info(f"更新知识库 {db_id} 查询参数: {params}")
+
return {"message": "success", "data": params}
except Exception as e:
@@ -926,6 +933,22 @@ async def get_knowledge_base_query_params(db_id: str, current_user: User = Depen
],
}
+ # 获取用户保存的配置
+ saved_options = {}
+ try:
+ if db_id in knowledge_base.global_databases_meta:
+ query_params_meta = knowledge_base.global_databases_meta[db_id].get("query_params", {})
+ saved_options = query_params_meta.get("options", {})
+ except Exception as saved_error:
+ logger.warning(f"获取保存的配置失败: {saved_error}")
+
+ # 将保存的值合并到默认配置中
+ if saved_options:
+ for option in params.get("options", []):
+ key = option.get("key")
+ if key in saved_options:
+ option["default"] = saved_options[key]
+
return {"params": params, "message": "success"}
except Exception as e:
diff --git a/src/services/evaluation_service.py b/src/services/evaluation_service.py
index 0ba5eb2b..ea0c0a36 100644
--- a/src/services/evaluation_service.py
+++ b/src/services/evaluation_service.py
@@ -241,7 +241,7 @@ class EvaluationService:
raise NotImplementedError("自动生成基准功能暂时不可用，请手动上传基准文件。")
async def run_evaluation(
- self, db_id: str, benchmark_id: str, retrieval_config: dict[str, Any], created_by: str
+ self, db_id: str, benchmark_id: str, model_config: dict[str, Any] = None, created_by: str = "system"
) -> str:
"""运行RAG评估"""
try:
@@ -253,6 +253,21 @@ class EvaluationService:
with open(meta_file_path, encoding="utf-8") as f:
benchmark_meta = json.load(f)
+ # 从知识库元数据中获取检索配置
+ retrieval_config = {}
+ try:
+ kb_meta = knowledge_base.global_databases_meta.get(db_id, {})
+ query_params = kb_meta.get("query_params", {})
+ retrieval_config = query_params.get("options", {})
+ logger.info(f"从知识库 {db_id} 加载检索配置: {list(retrieval_config.keys())}")
+ except Exception as e:
+ logger.error(f"获取知识库检索配置失败: {e}")
+ # 使用空配置作为默认值
+
+ # 合并前端传递的模型配置
+ if model_config:
+ retrieval_config.update(model_config)
+
# 初始化结果文件 (Status: running)
result_dir = self._get_result_dir(db_id)
result_file_path = os.path.join(result_dir, f"{task_id}.json")
@@ -581,6 +596,8 @@ class EvaluationService:
"total_questions": data.get("total_questions"),
"completed_questions": data.get("completed_questions"),
"overall_score": data.get("overall_score"),
+ # 包含检索配置
+ "retrieval_config": data.get("retrieval_config", {}),
# 也可以带上部分 metrics 摘要
"metrics": data.get("metrics"),
}
diff --git a/web/src/apis/knowledge_api.js b/web/src/apis/knowledge_api.js
index 195fd736..2894e6d0 100644
--- a/web/src/apis/knowledge_api.js
+++ b/web/src/apis/knowledge_api.js
@@ -390,7 +390,7 @@ export const evaluationApi = {
return apiAdminPost(`/api/evaluation/databases/${dbId}/run`, params)
},
-
+
/**
* 获取评估结果
* @param {string} taskId - 任务ID
diff --git a/web/src/components/RAGEvaluationTab.vue b/web/src/components/RAGEvaluationTab.vue
index 4efd301a..6c8def84 100644
--- a/web/src/components/RAGEvaluationTab.vue
+++ b/web/src/components/RAGEvaluationTab.vue
@@ -183,6 +183,13 @@
+
+
+
+
{{ JSON.stringify(selectedResult.retrieval_config, null, 2) }}
+
整体评估报告
@@ -417,22 +424,10 @@ const startEvaluation = async () => {
startingEvaluation.value = true;
- // 获取检索配置
- let retrievalConfig = {};
- try {
- const savedConfig = localStorage.getItem(`search-config-${props.databaseId}`);
- if (savedConfig) {
- retrievalConfig = JSON.parse(savedConfig);
- }
- } catch (error) {
- console.error('获取检索配置失败:', error);
- }
-
- // 合并配置，优先使用评估页面的模型配置
+ // 只传递模型配置，检索配置由服务器从知识库读取
const params = {
benchmark_id: selectedBenchmark.value.benchmark_id,
- retrieval_config: {
- ...retrievalConfig, // 包含所有检索参数如 top_k, similarity_threshold 等
+ model_config: {
answer_llm: configForm.answer_llm, // 传递答案生成模型
judge_llm: configForm.judge_llm // 传递评判模型
}
@@ -544,9 +539,15 @@ const viewResults = async (taskId) => {
completed_at: resultData.completed_at,
total_questions: resultData.total_questions || 0,
completed_questions: resultData.completed_questions || 0,
- overall_score: resultData.overall_score
+ overall_score: resultData.overall_score,
+ retrieval_config: resultData.retrieval_config
};
+ // 如果是从历史记录获取的，确保也有 retrieval_config
+ if (selectedResult.value && !selectedResult.value.retrieval_config) {
+ selectedResult.value.retrieval_config = resultData.retrieval_config;
+ }
+
// 计算总耗时
if (resultData.started_at && resultData.completed_at) {
const startTime = new Date(resultData.started_at);
@@ -705,6 +706,7 @@ const formatDuration = (seconds) => {
}
};
+
// 组件挂载时加载数据
onMounted(() => {
loadBenchmarks();
@@ -1137,4 +1139,25 @@ onMounted(() => {
}
}
+// JSON 查看器样式
+.json-viewer-container {
+ max-height: 400px;
+ overflow: auto;
+
+ .json-viewer {
+ margin: 0;
+ padding: 0;
+ font-family: 'SF Mono', 'Monaco', 'Consolas', 'Menlo', monospace;
+ font-size: 13px;
+ line-height: 1.5;
+ color: var(--gray-800);
+ white-space: pre-wrap;
+ word-wrap: break-word;
+ background: var(--gray-50);
+ border: 1px solid var(--gray-200);
+ border-radius: 6px;
+ padding: 12px;
+ }
+}
+
\ No newline at end of file
diff --git a/web/src/components/SearchConfigTab.vue b/web/src/components/SearchConfigTab.vue
index 23356a52..40ee6d33 100644
--- a/web/src/components/SearchConfigTab.vue
+++ b/web/src/components/SearchConfigTab.vue
@@ -197,21 +197,19 @@ const saveConfig = async () => {
// 确保 include_distances 始终为 true
meta['include_distances'] = true;
- // 保存到 localStorage（兼容性）
- localStorage.setItem(`search-config-${props.databaseId}`, JSON.stringify(meta));
-
- // 保存到知识库元数据
+ // 先保存到知识库元数据
try {
- const { knowledgeApi } = await import('@/apis/knowledge_api');
- const response = await knowledgeApi.updateKnowledgeBaseQueryParams(props.databaseId, meta);
+ const response = await queryApi.updateKnowledgeBaseQueryParams(props.databaseId, meta);
if (response.message === 'success') {
- message.success('配置已保存到知识库');
+ // 服务器保存成功后，再保存到 localStorage（兼容性）
+ localStorage.setItem(`search-config-${props.databaseId}`, JSON.stringify(meta));
+ message.success('配置已保存');
} else {
- message.warning('配置已保存到本地，但同步到知识库失败');
+ throw new Error(response.message || '保存失败');
}
} catch (error) {
console.error('保存配置到知识库失败:', error);
- message.warning('配置已保存到本地，但同步到知识库失败');
+ message.error('保存配置失败：' + error.message);
}
// 更新 store 中的配置