feat(知识图谱): 添加批处理大小配置并优化上传功能

- 在知识图谱上传功能中添加批处理大小配置选项 - 将同步操作改为异步以提高性能 - 优化前端上传配置界面布局 - 更新文档中的路线图信息
2026-01-01 23:39:17 +08:00 · 2026-01-01 23:39:17 +08:00 · 9c1747667c
commit 9c1747667c
parent c8b8c92644
6 changed files with 113 additions and 36 deletions
--- a/docs/latest/changelog/roadmap.md
+++ b/docs/latest/changelog/roadmap.md
@ -2,7 +2,6 @@

 路线图可能会经常变更，如果有强烈的建议，可以在 [issue](https://github.com/xerrors/Yuxi-Know/issues) 中提。

-v0.5

 ### 看板

@ -15,9 +14,10 @@ v0.5
 - skills 如何实现还需要继续调研
 - 优化 paddle 的命名，paddlex 有歧义，修改为 PP-StructureV3
 - 增加 paddle-vl 以及 deepseek-ocr 的支持（deepseek-ocr 已支持）
- RAG 检索的时候，支持限定文件类型
 - 将现有的 Milvus 的命名调整为通用 RAG
 - 将工具与知识库解耦，在 context 中就完成解耦，虽然最终都是在 Agent 中的 get_tools 中获取
+- 系统层面添加 apikey，在智能体、知识库调用中支持 apikey 以支持外部调用
+- 支持更多类型的文档源的导入功能

 ### Bugs
 - 部分异常状态下，智能体的模型名称出现重叠[#279](https://github.com/xerrors/Yuxi-Know/issues/279)
@ -27,6 +27,20 @@ v0.5
 - 目前的知识库的图片存在公开访问风险
 - 工具传递给模型的时候，使用英文，但部分模型不支持中文函数名（如gpt-4o-mini）
 - 首页加载的问题
+- 当前的 upload 图谱查询为同步操作，可能会导致页面卡顿
+
+## v0.5
+
+### 新增
+
+- 优化 OCR 体验并新增对 Deepseek OCR 的支持
+- 优化 RAG 检索，支持根据文件 pattern 来检索（Agentic Mode）
+- 重构智能体对于“工具变更/模型变更”的处理逻辑，无需导入更复杂的中间件
+- 重构知识库的 Agentic 配置逻辑，与 Tools 解耦
+
+### 修复
+
+- 修复知识图谱上传的向量配置错误，并新增模型选择以及 batch size 选择

 ## v0.4

--- a/server/routers/graph_router.py
+++ b/server/routers/graph_router.py
@ -251,7 +251,7 @@ async def index_neo4j_entities(data: dict = Body(default={}), current_user: User
            raise HTTPException(status_code=400, detail="图数据库未启动")

        kgdb_name = data.get("kgdb_name", "neo4j")
-        count = graph_base.add_embedding_to_nodes(kgdb_name=kgdb_name)
+        count = await graph_base.add_embedding_to_nodes(kgdb_name=kgdb_name)

        return {
            "success": True,
@ -269,6 +269,7 @@ async def add_neo4j_entities(
    file_path: str = Body(...),
    kgdb_name: str | None = Body(None),
    embed_model_name: str | None = Body(None),
+    batch_size: int | None = Body(None),
    current_user: User = Depends(get_admin_user),
 ):
    """通过JSONL文件添加图谱实体到Neo4j"""
@ -284,7 +285,7 @@ async def add_neo4j_entities(
        if not file_path.endswith(".jsonl"):
            return {"success": False, "message": "文件格式错误，请上传jsonl文件", "status": "failed"}

-        await graph_base.jsonl_file_add_entity(file_path, kgdb_name, embed_model_name)
+        await graph_base.jsonl_file_add_entity(file_path, kgdb_name, embed_model_name, batch_size)
        return {"success": True, "message": "实体添加成功", "status": "success"}
    except Exception as e:
        logger.error(f"添加实体失败: {e}, {traceback.format_exc()}")
--- a/src/knowledge/services/upload_graph_service.py
+++ b/src/knowledge/services/upload_graph_service.py
@ -25,8 +25,8 @@ class UploadGraphService:
        self.connection = db_manager or Neo4jConnectionManager()
        self.files = []
        self.kgdb_name = "neo4j"
-        self.embed_model_name = os.getenv("GRAPH_EMBED_MODEL_NAME") or "siliconflow/BAAI/bge-m3"
-        self.embed_model = select_embedding_model(self.embed_model_name)
+        self.embed_model_name = None  # self.load_graph_info() 时加载
+        self.embed_model = None  # self.load_graph_info() 时加载
        self.work_dir = os.path.join(config.save_dir, "knowledge_graph", self.kgdb_name)
        os.makedirs(self.work_dir, exist_ok=True)
        self.is_initialized_from_file = False
@ -51,7 +51,6 @@ class UploadGraphService:
        if not self.connection.is_running():
            self.connection._connect()
            logger.info(f"Connected to Neo4j: {self.get_graph_info(self.kgdb_name)}")
-            # 连接成功后保存图数据库信息

    def close(self):
        """关闭数据库连接"""
@ -84,7 +83,7 @@ class UploadGraphService:
        if self.status == "closed":
            self.start()

-    async def jsonl_file_add_entity(self, file_path, kgdb_name="neo4j", embed_model_name=None):
+    async def jsonl_file_add_entity(self, file_path, kgdb_name="neo4j", embed_model_name=None, batch_size=None):
        """从JSONL文件添加实体三元组到Neo4j"""
        assert self.driver is not None, "Database is not connected"
        self.connection.status = "processing"
@ -134,7 +133,7 @@ class UploadGraphService:

            triples = list(read_triples(actual_file_path))

-            await self.txt_add_vector_entity(triples, kgdb_name, embed_model_name)
+            await self.txt_add_vector_entity(triples, kgdb_name, embed_model_name, batch_size)

        except Exception as e:
            logger.error(f"处理文件失败: {e}")
@ -153,7 +152,7 @@ class UploadGraphService:
        self.save_graph_info()
        return kgdb_name

-    async def txt_add_vector_entity(self, triples, kgdb_name="neo4j", embed_model_name=None):
+    async def txt_add_vector_entity(self, triples, kgdb_name="neo4j", embed_model_name=None, batch_size=None):
        """添加实体三元组"""
        assert self.driver is not None, "Database is not connected"
        self.use_database(kgdb_name)
@ -274,9 +273,7 @@ class UploadGraphService:

        # 允许 self.embed_model_name 与 config.embed_model 不同（用户自定义选择的情况）
        # 但必须在支持的模型列表中
-        assert self.embed_model_name in config.embed_model_names, (
-            f"Unsupported embed model: {self.embed_model_name}"
-        )
+        assert self.embed_model_name in config.embed_model_names, f"Unsupported embed model: {self.embed_model_name}"

        with self.driver.session() as session:
            logger.info(f"Adding entity to {kgdb_name}")
@ -316,7 +313,7 @@ class UploadGraphService:
                )

                # 批量获取嵌入向量
-                batch_embeddings = await self.aget_embedding(batch_entities)
+                batch_embeddings = await self.aget_embedding(batch_entities, batch_size=batch_size)

                # 将实体名称和嵌入向量配对
                entity_embedding_pairs = list(zip(batch_entities, batch_embeddings))
@ -327,12 +324,13 @@ class UploadGraphService:
            # 数据添加完成后保存图信息
            self.save_graph_info()

-    def add_embedding_to_nodes(self, node_names=None, kgdb_name="neo4j"):
+    async def add_embedding_to_nodes(self, node_names=None, kgdb_name="neo4j", batch_size=None):
        """为节点添加嵌入向量

        Args:
            node_names (list, optional): 要添加嵌入向量的节点名称列表，None表示所有没有嵌入向量的节点
            kgdb_name (str, optional): 图数据库名称，默认为'neo4j'
+            batch_size (int, optional): 嵌入批次大小

        Returns:
            int: 成功添加嵌入向量的节点数量
@ -348,7 +346,7 @@ class UploadGraphService:
        with self.driver.session() as session:
            for node_name in node_names:
                try:
-                    embedding = self.get_embedding(node_name)
+                    embedding = await self.aget_embedding(node_name, batch_size=batch_size)
                    session.execute_write(self.set_embedding, node_name, embedding)
                    count += 1
                except Exception as e:
@ -500,23 +498,24 @@ class UploadGraphService:
            logger.error(f"加载图数据库信息失败：{e}")
            return False

-    async def aget_embedding(self, text):
+    async def aget_embedding(self, text, batch_size=40):
        if isinstance(text, list):
-            outputs = await self.embed_model.abatch_encode(text, batch_size=40)
+            outputs = await self.embed_model.abatch_encode(text, batch_size=batch_size)
            return outputs
        else:
            outputs = await self.embed_model.aencode(text)
            return outputs

-    def get_embedding(self, text):
+    def get_embedding(self, text, batch_size=40):
        if isinstance(text, list):
-            outputs = self.embed_model.batch_encode(text, batch_size=40)
+            outputs = self.embed_model.batch_encode(text, batch_size=batch_size)
            return outputs
        else:
            outputs = self.embed_model.encode([text])[0]
            return outputs

    def set_embedding(self, tx, entity_name, embedding):
+        """为单个实体设置嵌入向量"""
        tx.run(
            """
        MATCH (e:Entity {name: $name})
@ -564,9 +563,8 @@ class UploadGraphService:
                entity_to_score[name] = max(entity_to_score.get(name, 0.0), 0.3)

        # 排序并截断
-        qualified_entities = [name for name, _ in sorted(entity_to_score.items(), key=lambda x: x[1], reverse=True)][
-            :max_entities
-        ]
+        sorted_entity_to_score = sorted(entity_to_score.items(), key=lambda x: x[1], reverse=True)
+        qualified_entities = [name for name, _ in sorted_entity_to_score][:max_entities]

        logger.debug(f"Graph Query Entities: {keyword}, {qualified_entities=}")

--- a/web/src/apis/graph_api.js
+++ b/web/src/apis/graph_api.js
@ -123,13 +123,15 @@ export const neo4jApi = {
   * @param {string} file_path - JSONL文件路径
   * @param {string} kgdb_name - Neo4j数据库名称（默认为'neo4j'）
   * @param {string} embed_model_name - 嵌入模型名称 (可选)
+   * @param {number} batch_size - 批处理大小 (可选)
   * @returns {Promise} - 添加结果
   */
-  addEntities: async (file_path, kgdb_name = 'neo4j', embed_model_name = null) => {
+  addEntities: async (file_path, kgdb_name = 'neo4j', embed_model_name = null, batch_size = null) => {
    return await apiPost('/api/graph/neo4j/add-entities', {
      file_path: file_path,
      kgdb_name: kgdb_name,
-      embed_model_name: embed_model_name
+      embed_model_name: embed_model_name,
+      batch_size: batch_size
    }, {}, true)
  },

--- a/web/src/layouts/AppLayout.vue
+++ b/web/src/layouts/AppLayout.vue
@ -327,8 +327,8 @@ div.header, #app-router-view {
    display: flex;
    align-items: center;
    justify-content: center;
-    width: 40px;
-    height: 40px;
+    width: 36px;
+    height: 36px;
    padding: 4px;
    border: 1px solid transparent;
    border-radius: 12px;
--- a/web/src/views/GraphView.vue
+++ b/web/src/views/GraphView.vue
@ -115,16 +115,34 @@
        <div class="note">
          <p>上传的文件内容参考 test/data/A_Dream_of_Red_Mansions_tiny.jsonl 中的格式：</p>
        </div>
-        <div style="margin-bottom: 16px;">
-          <span>嵌入模型:</span>
-          <EmbeddingModelSelector
-            v-model:value="state.embedModelName"
-            :disabled="!embedModelConfigurable"
-            style="width: 100%;"
-          />
-           <div v-if="!embedModelConfigurable" style="font-size: 12px; margin-top: 4px;">
+        <div class="upload-config">
+          <div class="config-row">
+            <label class="config-label">嵌入模型</label>
+            <div class="config-field">
+              <EmbeddingModelSelector
+                v-model:value="state.embedModelName"
+                :disabled="!embedModelConfigurable"
+                :style="{ width: '100%' }"
+              />
+            </div>
+          </div>
+          <div v-if="!embedModelConfigurable" class="config-hint-row">
            * 图数据库已有数据或已设定模型，不可更改
          </div>
+          <div class="config-row">
+            <label class="config-label">批处理大小</label>
+            <div class="config-field">
+              <a-input-number
+                v-model:value="state.batchSize"
+                :min="1"
+                :max="1000"
+                style="width: 100%"
+              />
+            </div>
+          </div>
+          <div class="config-hint-row">
+            默认值: 40，范围: 1-1000
+          </div>
        </div>
        <a-upload-dragger
          class="upload-dragger"
@ -215,6 +233,7 @@ const state = reactive({
  dbOptions: [],
  lightragStats: null,
  embedModelName: '',
+  batchSize: 40,
 })

 const isNeo4j = computed(() => {
@ -343,7 +362,7 @@ const addDocumentByFile = () => {
    return
  }

-  neo4jApi.addEntities(filePath, 'neo4j', state.embedModelName)
+  neo4jApi.addEntities(filePath, 'neo4j', state.embedModelName, state.batchSize)
    .then((data) => {
      if (data.status === 'success') {
        message.success(data.message);
@ -640,6 +659,49 @@ const goToDatabasePage = () => {
  .upload-dragger {
    margin: 0px;
  }
+
+  .upload-config {
+    margin: 24px 0;
+    padding: 16px;
+    background-color: var(--gray-0);
+    border-radius: 4px;
+
+    .config-row {
+      display: flex;
+      align-items: center;
+      margin-bottom: 16px;
+
+      &:last-of-type {
+        margin-bottom: 0;
+      }
+
+      .config-label {
+        width: 100px;
+        flex-shrink: 0;
+        font-size: 14px;
+        color: var(--color-text);
+        text-align: right;
+        margin-right: 16px;
+      }
+
+      .config-field {
+        flex: 1;
+        min-width: 0;
+      }
+    }
+
+    .config-hint-row {
+      margin-bottom: 16px;
+      padding-left: 116px;
+      font-size: 12px;
+      color: var(--color-text-secondary);
+      line-height: 1.5;
+
+      &:last-child {
+        margin-bottom: 0;
+      }
+    }
+  }
 }

 .container-outter {