feat:完成dify知识库文档基础CRUD模块

2025-11-30 21:28:49 +08:00
parent d85010bada
commit 754ec2c7b5
21 changed files with 1142 additions and 706 deletions
@@ -0,0 +1,74 @@
+import { type LoaderFunctionArgs } from '@remix-run/node';
+import { API_BASE_URL } from '~/config/api-config';
+
+/**
+ * GET /api/dataset/datasets/:datasetId/documents/:batch/indexing-status
+ * 获取文档嵌入状态（处理进度）
+ *
+ * Dify API: GET /datasets/{dataset_id}/documents/{batch}/indexing-status
+ *
+ * 返回示例:
+ * {
+ *   "data": [{
+ *     "id": "",
+ *     "indexing_status": "indexing",
+ *     "processing_started_at": 1681623462.0,
+ *     "parsing_completed_at": 1681623462.0,
+ *     "cleaning_completed_at": 1681623462.0,
+ *     "splitting_completed_at": 1681623462.0,
+ *     "completed_at": null,
+ *     "paused_at": null,
+ *     "error": null,
+ *     "stopped_at": null,
+ *     "completed_segments": 24,
+ *     "total_segments": 100
+ *   }]
+ * }
+ */
+export async function loader({ request, params }: LoaderFunctionArgs) {
+    try {
+        const { getUserSession } = await import("~/api/login/auth.server");
+        const { frontendJWT } = await getUserSession(request);
+
+        if (!frontendJWT) {
+            return new Response(
+                JSON.stringify({ error: 'JWT认证失败，请重新登录' }),
+                { status: 401, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const { datasetId, batch } = params;
+        if (!datasetId || !batch) {
+            return new Response(
+                JSON.stringify({ error: '缺少必要参数 (datasetId, batch)' }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        console.log('[API] Indexing Status:', { datasetId, batch });
+
+        // 转发请求到 FastAPI -> Dify API
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents/${batch}/indexing-status`;
+        const response = await fetch(apiUrl, {
+            method: 'GET',
+            headers: {
+                'Content-Type': 'application/json',
+                'Authorization': `Bearer ${frontendJWT}`,
+            },
+        });
+
+        const data = await response.json();
+
+        return new Response(JSON.stringify(data), {
+            status: response.status,
+            headers: { 'Content-Type': 'application/json' },
+        });
+
+    } catch (error: any) {
+        console.error('[API] Indexing Status - Error:', error.message);
+        return new Response(
+            JSON.stringify({ error: error.message || 'Failed to get indexing status' }),
+            { status: 500, headers: { 'Content-Type': 'application/json' } }
+        );
+    }
+}
@@ -0,0 +1,143 @@
+import { type LoaderFunctionArgs, type ActionFunctionArgs } from '@remix-run/node';
+import { API_BASE_URL } from '~/config/api-config';
+
+/**
+ * GET /api/dataset/datasets/:datasetId/documents/:documentId/segments/:segmentId - 获取分段详情
+ * Dify API: GET /datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}
+ */
+export async function loader({ request, params }: LoaderFunctionArgs) {
+    try {
+        const { getUserSession } = await import("~/api/login/auth.server");
+        const { frontendJWT } = await getUserSession(request);
+
+        if (!frontendJWT) {
+            return new Response(
+                JSON.stringify({ error: 'JWT认证失败，请重新登录' }),
+                { status: 401, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const { datasetId, documentId, segmentId } = params;
+        if (!datasetId || !documentId || !segmentId) {
+            return new Response(
+                JSON.stringify({ error: '缺少必要参数' }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        console.log('[API] Segment Detail:', { datasetId, documentId, segmentId });
+
+        // 转发请求到 FastAPI -> Dify API
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents/${documentId}/segments/${segmentId}`;
+        const response = await fetch(apiUrl, {
+            method: 'GET',
+            headers: {
+                'Content-Type': 'application/json',
+                'Authorization': `Bearer ${frontendJWT}`,
+            },
+        });
+
+        const data = await response.json();
+
+        return new Response(JSON.stringify(data), {
+            status: response.status,
+            headers: { 'Content-Type': 'application/json' },
+        });
+
+    } catch (error: any) {
+        console.error('[API] Segment Detail - Error:', error.message);
+        return new Response(
+            JSON.stringify({ error: error.message || 'Failed to get segment' }),
+            { status: 500, headers: { 'Content-Type': 'application/json' } }
+        );
+    }
+}
+
+/**
+ * DELETE /api/dataset/datasets/:datasetId/documents/:documentId/segments/:segmentId - 删除分段
+ * POST - 更新分段 (Dify用POST更新分段，可传enabled参数切换状态)
+ * Dify API: DELETE/POST /datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}
+ */
+export async function action({ request, params }: ActionFunctionArgs) {
+    try {
+        const { getUserSession } = await import("~/api/login/auth.server");
+        const { frontendJWT } = await getUserSession(request);
+
+        if (!frontendJWT) {
+            return new Response(
+                JSON.stringify({ error: 'JWT认证失败，请重新登录' }),
+                { status: 401, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const { datasetId, documentId, segmentId } = params;
+        if (!datasetId || !documentId || !segmentId) {
+            return new Response(
+                JSON.stringify({ error: '缺少必要参数' }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const method = request.method;
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents/${documentId}/segments/${segmentId}`;
+
+        if (method === 'DELETE') {
+            console.log('[API] Delete Segment:', { datasetId, documentId, segmentId });
+
+            const response = await fetch(apiUrl, {
+                method: 'DELETE',
+                headers: {
+                    'Content-Type': 'application/json',
+                    'Authorization': `Bearer ${frontendJWT}`,
+                },
+            });
+
+            // Dify删除分段返回 204 No Content
+            if (response.status === 204) {
+                return new Response(
+                    JSON.stringify({ result: 'success' }),
+                    { status: 200, headers: { 'Content-Type': 'application/json' } }
+                );
+            }
+
+            const data = await response.json();
+            return new Response(JSON.stringify(data), {
+                status: response.status,
+                headers: { 'Content-Type': 'application/json' },
+            });
+        }
+
+        if (method === 'POST') {
+            // POST 用于更新分段（包括启用/禁用）
+            const body = await request.json();
+            console.log('[API] Update Segment:', { datasetId, documentId, segmentId, body });
+
+            const response = await fetch(apiUrl, {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json',
+                    'Authorization': `Bearer ${frontendJWT}`,
+                },
+                body: JSON.stringify(body),
+            });
+
+            const data = await response.json();
+            return new Response(JSON.stringify(data), {
+                status: response.status,
+                headers: { 'Content-Type': 'application/json' },
+            });
+        }
+
+        return new Response(
+            JSON.stringify({ error: 'Method not allowed' }),
+            { status: 405, headers: { 'Content-Type': 'application/json' } }
+        );
+
+    } catch (error: any) {
+        console.error('[API] Segment Action - Error:', error.message);
+        return new Response(
+            JSON.stringify({ error: error.message || 'Failed to process segment request' }),
+            { status: 500, headers: { 'Content-Type': 'application/json' } }
+        );
+    }
+}
@@ -0,0 +1,66 @@
+import { type LoaderFunctionArgs } from '@remix-run/node';
+import { API_BASE_URL } from '~/config/api-config';
+
+/**
+ * GET /api/dataset/datasets/:datasetId/documents/:documentId/segments - 获取分段列表
+ * Dify API: GET /datasets/{dataset_id}/documents/{document_id}/segments
+ */
+export async function loader({ request, params }: LoaderFunctionArgs) {
+    try {
+        const { getUserSession } = await import("~/api/login/auth.server");
+        const { frontendJWT } = await getUserSession(request);
+
+        if (!frontendJWT) {
+            return new Response(
+                JSON.stringify({ error: 'JWT认证失败，请重新登录' }),
+                { status: 401, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const { datasetId, documentId } = params;
+        if (!datasetId || !documentId) {
+            return new Response(
+                JSON.stringify({ error: '缺少必要参数' }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        // 获取查询参数
+        const url = new URL(request.url);
+        const page = url.searchParams.get('page') || '1';
+        const limit = url.searchParams.get('limit') || '20';
+        const keyword = url.searchParams.get('keyword') || '';
+        const status = url.searchParams.get('status') || '';
+
+        console.log('[API] Segments List:', { datasetId, documentId, page, limit, keyword, status });
+
+        // 构建查询参数
+        const queryParams = new URLSearchParams({ page, limit });
+        if (keyword) queryParams.append('keyword', keyword);
+        if (status) queryParams.append('status', status);
+
+        // 转发请求到 FastAPI -> Dify API
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents/${documentId}/segments?${queryParams}`;
+        const response = await fetch(apiUrl, {
+            method: 'GET',
+            headers: {
+                'Content-Type': 'application/json',
+                'Authorization': `Bearer ${frontendJWT}`,
+            },
+        });
+
+        const data = await response.json();
+
+        return new Response(JSON.stringify(data), {
+            status: response.status,
+            headers: { 'Content-Type': 'application/json' },
+        });
+
+    } catch (error: any) {
+        console.error('[API] Segments List - Error:', error.message);
+        return new Response(
+            JSON.stringify({ error: error.message || 'Failed to get segments' }),
+            { status: 500, headers: { 'Content-Type': 'application/json' } }
+        );
+    }
+}
@@ -26,7 +26,7 @@ export async function loader({ request, params }: LoaderFunctionArgs) {

        console.log('[API] Document Detail:', { datasetId, documentId });

-        const apiUrl = `${API_BASE_URL}/dify-dataset/datasets/${datasetId}/documents/${documentId}`;
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents/${documentId}`;
        const response = await fetch(apiUrl, {
            method: 'GET',
            headers: {
@@ -79,7 +79,7 @@ export async function action({ request, params }: ActionFunctionArgs) {
        if (method === 'DELETE') {
            console.log('[API] Delete Document:', { datasetId, documentId });

-            const apiUrl = `${API_BASE_URL}/dify-dataset/datasets/${datasetId}/documents/${documentId}`;
+            const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents/${documentId}`;
            const response = await fetch(apiUrl, {
                method: 'DELETE',
                headers: {
@@ -1,10 +1,26 @@
-import { type ActionFunctionArgs } from '@remix-run/node';
+import { type LoaderFunctionArgs } from '@remix-run/node';
 import { API_BASE_URL } from '~/config/api-config';

 /**
- * PATCH /api/dataset/datasets/:datasetId/documents/:documentId/status - 切换文档状态
+ * GET /api/dataset/datasets/:datasetId/documents/:documentId/upload-file
+ * 获取文档上传文件信息
+ *
+ * Dify API: GET /datasets/{dataset_id}/documents/{document_id}/upload-file
+ *
+ * 返回示例:
+ * {
+ *   "id": "file_id",
+ *   "name": "file_name",
+ *   "size": 1024,
+ *   "extension": "txt",
+ *   "url": "preview_url",
+ *   "download_url": "download_url",
+ *   "mime_type": "text/plain",
+ *   "created_by": "user_id",
+ *   "created_at": 1728734540
+ * }
 */
-export async function action({ request, params }: ActionFunctionArgs) {
+export async function loader({ request, params }: LoaderFunctionArgs) {
    try {
        const { getUserSession } = await import("~/api/login/auth.server");
        const { frontendJWT } = await getUserSession(request);
@@ -19,24 +35,21 @@ export async function action({ request, params }: ActionFunctionArgs) {
        const { datasetId, documentId } = params;
        if (!datasetId || !documentId) {
            return new Response(
-                JSON.stringify({ error: '缺少必要参数' }),
+                JSON.stringify({ error: '缺少必要参数 (datasetId, documentId)' }),
                { status: 400, headers: { 'Content-Type': 'application/json' } }
            );
        }

-        const body = await request.json();
-        const { enabled } = body;
+        console.log('[API] Upload File Info:', { datasetId, documentId });

-        console.log('[API] Toggle Document Status:', { datasetId, documentId, enabled });
-
-        const apiUrl = `${API_BASE_URL}/dify-dataset/datasets/${datasetId}/documents/${documentId}/status`;
+        // 转发请求到 FastAPI -> Dify API
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents/${documentId}/upload-file`;
        const response = await fetch(apiUrl, {
-            method: 'PATCH',
+            method: 'GET',
            headers: {
                'Content-Type': 'application/json',
                'Authorization': `Bearer ${frontendJWT}`,
            },
-            body: JSON.stringify({ enabled }),
        });

        const data = await response.json();
@@ -47,9 +60,9 @@ export async function action({ request, params }: ActionFunctionArgs) {
        });

    } catch (error: any) {
-        console.error('[API] Toggle Document Status - Error:', error.message);
+        console.error('[API] Upload File Info - Error:', error.message);
        return new Response(
-            JSON.stringify({ error: error.message || 'Failed to toggle status' }),
+            JSON.stringify({ error: error.message || 'Failed to get upload file info' }),
            { status: 500, headers: { 'Content-Type': 'application/json' } }
        );
    }
@@ -0,0 +1,75 @@
+import { type ActionFunctionArgs } from '@remix-run/node';
+import { API_BASE_URL } from '~/config/api-config';
+
+/**
+ * PATCH /api/dataset/datasets/:datasetId/documents/status/:action - 批量更新文档状态
+ * Dify API: PATCH /datasets/{dataset_id}/documents/status/{action}
+ * action: enable / disable / archive / un_archive
+ */
+export async function action({ request, params }: ActionFunctionArgs) {
+    try {
+        const { getUserSession } = await import("~/api/login/auth.server");
+        const { frontendJWT } = await getUserSession(request);
+
+        if (!frontendJWT) {
+            return new Response(
+                JSON.stringify({ error: 'JWT认证失败，请重新登录' }),
+                { status: 401, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const { datasetId, action: statusAction } = params;
+        if (!datasetId || !statusAction) {
+            return new Response(
+                JSON.stringify({ error: '缺少必要参数' }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        // 验证action参数
+        const validActions = ['enable', 'disable', 'archive', 'un_archive'];
+        if (!validActions.includes(statusAction)) {
+            return new Response(
+                JSON.stringify({ error: `无效的action参数，有效值: ${validActions.join(', ')}` }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const body = await request.json();
+        const { document_ids } = body;
+
+        if (!document_ids || !Array.isArray(document_ids) || document_ids.length === 0) {
+            return new Response(
+                JSON.stringify({ error: '缺少 document_ids 参数' }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        console.log('[API] Update Documents Status:', { datasetId, action: statusAction, document_ids });
+
+        // 转发请求到 FastAPI -> Dify API
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents/status/${statusAction}`;
+        const response = await fetch(apiUrl, {
+            method: 'PATCH',
+            headers: {
+                'Content-Type': 'application/json',
+                'Authorization': `Bearer ${frontendJWT}`,
+            },
+            body: JSON.stringify({ document_ids }),
+        });
+
+        const data = await response.json();
+
+        return new Response(JSON.stringify(data), {
+            status: response.status,
+            headers: { 'Content-Type': 'application/json' },
+        });
+
+    } catch (error: any) {
+        console.error('[API] Update Documents Status - Error:', error.message);
+        return new Response(
+            JSON.stringify({ error: error.message || 'Failed to update documents status' }),
+            { status: 500, headers: { 'Content-Type': 'application/json' } }
+        );
+    }
+}
@@ -38,7 +38,7 @@ export async function loader({ request, params }: LoaderFunctionArgs) {
        if (keyword) queryParams.append('keyword', keyword);

        // 转发请求到 FastAPI
-        const apiUrl = `${API_BASE_URL}/dify-dataset/datasets/${datasetId}/documents?${queryParams}`;
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/documents?${queryParams}`;
        const response = await fetch(apiUrl, {
            method: 'GET',
            headers: {
@@ -92,8 +92,8 @@ export async function action({ request, params }: ActionFunctionArgs) {

        console.log('[API] Upload Document:', { datasetId });

-        // 转发请求到 FastAPI
-        const apiUrl = `${API_BASE_URL}/dify-dataset/datasets/${datasetId}/documents/create-by-file`;
+        // 转发请求到 FastAPI (注意：Dify API是 /document/create-by-file，document是单数)
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}/document/create-by-file`;
        const response = await fetch(apiUrl, {
            method: 'POST',
            headers: {
@@ -0,0 +1,135 @@
+import { type LoaderFunctionArgs, type ActionFunctionArgs } from '@remix-run/node';
+import { API_BASE_URL } from '~/config/api-config';
+
+/**
+ * GET /api/dataset/datasets/:datasetId - 获取知识库详情
+ * Dify API: GET /datasets/{dataset_id}
+ */
+export async function loader({ request, params }: LoaderFunctionArgs) {
+    try {
+        const { getUserSession } = await import("~/api/login/auth.server");
+        const { frontendJWT } = await getUserSession(request);
+
+        if (!frontendJWT) {
+            return new Response(
+                JSON.stringify({ error: 'JWT认证失败，请重新登录' }),
+                { status: 401, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const { datasetId } = params;
+        if (!datasetId) {
+            return new Response(
+                JSON.stringify({ error: '缺少 datasetId 参数' }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        console.log('[API] Dataset Detail:', { datasetId });
+
+        // 转发请求到 FastAPI -> Dify API
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}`;
+        const response = await fetch(apiUrl, {
+            method: 'GET',
+            headers: {
+                'Content-Type': 'application/json',
+                'Authorization': `Bearer ${frontendJWT}`,
+            },
+        });
+
+        const data = await response.json();
+
+        return new Response(JSON.stringify(data), {
+            status: response.status,
+            headers: { 'Content-Type': 'application/json' },
+        });
+
+    } catch (error: any) {
+        console.error('[API] Dataset Detail - Error:', error.message);
+        return new Response(
+            JSON.stringify({ error: error.message || 'Failed to get dataset' }),
+            { status: 500, headers: { 'Content-Type': 'application/json' } }
+        );
+    }
+}
+
+/**
+ * PATCH /api/dataset/datasets/:datasetId - 修改知识库详情
+ *
+ * Dify API: PATCH /datasets/{dataset_id}
+ *
+ * 请求体示例:
+ * {
+ *   "name": "知识库名称",
+ *   "description": "描述",
+ *   "indexing_technique": "high_quality",
+ *   "permission": "only_me",
+ *   "embedding_model_provider": "zhipuai",
+ *   "embedding_model": "embedding-3",
+ *   "retrieval_model": {
+ *     "search_method": "semantic_search",
+ *     "reranking_enable": false,
+ *     "top_k": 2,
+ *     "score_threshold_enabled": false
+ *   }
+ * }
+ *
+ * 注意：删除知识库功能不对外开放
+ */
+export async function action({ request, params }: ActionFunctionArgs) {
+    try {
+        const { getUserSession } = await import("~/api/login/auth.server");
+        const { frontendJWT } = await getUserSession(request);
+
+        if (!frontendJWT) {
+            return new Response(
+                JSON.stringify({ error: 'JWT认证失败，请重新登录' }),
+                { status: 401, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const { datasetId } = params;
+        if (!datasetId) {
+            return new Response(
+                JSON.stringify({ error: '缺少 datasetId 参数' }),
+                { status: 400, headers: { 'Content-Type': 'application/json' } }
+            );
+        }
+
+        const method = request.method;
+
+        if (method === 'PATCH') {
+            // 修改知识库详情
+            const body = await request.json();
+            console.log('[API] Update Dataset:', { datasetId, body });
+
+            const apiUrl = `${API_BASE_URL}/dify_dataset/datasets/${datasetId}`;
+            const response = await fetch(apiUrl, {
+                method: 'PATCH',
+                headers: {
+                    'Content-Type': 'application/json',
+                    'Authorization': `Bearer ${frontendJWT}`,
+                },
+                body: JSON.stringify(body),
+            });
+
+            const data = await response.json();
+            return new Response(JSON.stringify(data), {
+                status: response.status,
+                headers: { 'Content-Type': 'application/json' },
+            });
+        }
+
+        return new Response(
+            JSON.stringify({ error: 'Method not allowed' }),
+            { status: 405, headers: { 'Content-Type': 'application/json' } }
+        );
+
+    } catch (error: any) {
+        console.error('[API] Dataset Action - Error:', error.message);
+        return new Response(
+            JSON.stringify({ error: error.message || 'Failed to process dataset request' }),
+            { status: 500, headers: { 'Content-Type': 'application/json' } }
+        );
+    }
+}
@@ -30,7 +30,7 @@ export async function loader({ request }: LoaderFunctionArgs) {
        console.log('[API] Dataset List - 获取知识库列表:', { page, limit });

        // 转发请求到 FastAPI
-        const apiUrl = `${API_BASE_URL}/dify-dataset/datasets?page=${page}&limit=${limit}`;
+        const apiUrl = `${API_BASE_URL}/dify_dataset/datasets?page=${page}&limit=${limit}`;
        const response = await fetch(apiUrl, {
            method: 'GET',
            headers: {