feat: import DOCX/PDF/scanned templates via DeepSeek recognition

Backend pipeline:
- POST /api/templates/import (multipart, max 25 MB)
- extract.ts: DOCX→mammoth, PDF→pdf-parse, fallback to OCR via tesseract+poppler-utils
  (pdftoppm renders pages to PNG, tesseract reads with rus+eng)
- deepseek.ts: chat completions client with strict JSON response_format
- recognize.ts: structured prompt that produces simplified DocBody (string text),
  postprocessor wraps text in TipTap-compatible JSON, validates with zod schema
- prompt enforces placeholder substitution: {{customer.*}}, {{executor.*}},
  {{contract.number}}, {{contract.date}}, {{today}}
- error codes: NO_OCR / NO_DEEPSEEK_KEY / UNSUPPORTED_MIME / INVALID_DOC_BODY

Dockerfile: apk add tesseract-ocr (+rus +eng data), poppler-utils, imagemagick

Frontend:
- Templates page: ⤴ Загрузить документ → file picker (.docx,.pdf,.png,.jpg)
- doc type selector (contract/invoice/act/upd)
- import-banner with spinner shows uploading→analyzing stages
- on success navigates to /templates/:id (TemplateEdit) for review

Reuses DEEPSEEK_API_KEY pattern from Hall-planer.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

apps/api/.env.example

@@ -35,6 +35,12 @@ DEFAULT_ORGANIZATION_ID=00000000-0000-0000-0000-000000000001
 # Бесплатно до 10000 запросов/сутки.
 DADATA_API_KEY=
 
+# DeepSeek — разбор загруженных шаблонов (DOCX/PDF/скан) в DocBody-структуру.
+# Получить ключ: https://platform.deepseek.com/api_keys
+DEEPSEEK_API_KEY=
+# DEEPSEEK_BASE_URL=https://api.deepseek.com
+# DEEPSEEK_MODEL=deepseek-chat
+
 # --- Dev-only ---
 # Если 1 — пропускает проверку JWT и подсовывает фейкового admin'а.
 # В production отказывается стартовать с этой переменной.

apps/api/package.json

@@ -20,15 +20,20 @@
     "@fastify/cookie": "^9.4.0",
     "@fastify/cors": "^9.0.1",
     "@fastify/helmet": "^11.1.1",
+    "@fastify/multipart": "^10.0.0",
     "@prisma/client": "^5.22.0",
     "fastify": "^4.28.1",
     "fastify-plugin": "^4.5.1",
     "jose": "^5.9.6",
+    "mammoth": "^1.12.0",
+    "node-tesseract-ocr": "^2.2.1",
+    "pdf-parse": "^2.4.5",
     "puppeteer-core": "^24.42.0",
     "zod": "^3.23.8"
   },
   "devDependencies": {
     "@types/node": "^20.16.0",
+    "@types/pdf-parse": "^1.1.5",
     "embedded-postgres": "^18.3.0-beta.17",
     "pino-pretty": "^11.3.0",
     "prisma": "^5.22.0",

apps/api/src/env.ts

@@ -25,6 +25,11 @@ const EnvSchema = z.object({
   // Получить: https://dadata.ru/api/find-party/  (нужен «API-ключ для приложения», не secret)
   DADATA_API_KEY: z.string().optional(),
 
+  // DeepSeek (https://api.deepseek.com) — для разбора документов в DocBody.
+  DEEPSEEK_API_KEY: z.string().optional(),
+  DEEPSEEK_BASE_URL: z.string().url().default('https://api.deepseek.com'),
+  DEEPSEEK_MODEL: z.string().default('deepseek-chat'),
+
   DEFAULT_ORGANIZATION_ID: z.string().uuid().default('00000000-0000-0000-0000-000000000001'),
 
   // Только для локальной разработки. В проде — НИКОГДА. Hard-check ниже.

apps/api/src/modules/templates/deepseek.ts

@@ -0,0 +1,48 @@
+import { env } from '../../env.js';
+
+type ChatMessage = { role: 'system' | 'user' | 'assistant'; content: string };
+
+type DeepSeekResponse = {
+  choices: { message: { content: string } }[];
+};
+
+export async function deepseekJsonChat<T>(messages: ChatMessage[], opts: { temperature?: number; maxTokens?: number } = {}): Promise<T> {
+  if (!env.DEEPSEEK_API_KEY) {
+    throw Object.assign(new Error('DeepSeek API ключ не настроен (DEEPSEEK_API_KEY).'), {
+      code: 'NO_DEEPSEEK_KEY',
+    });
+  }
+  const res = await fetch(`${env.DEEPSEEK_BASE_URL}/chat/completions`, {
+    method: 'POST',
+    headers: {
+      Authorization: `Bearer ${env.DEEPSEEK_API_KEY}`,
+      'Content-Type': 'application/json',
+    },
+    body: JSON.stringify({
+      model: env.DEEPSEEK_MODEL,
+      messages,
+      response_format: { type: 'json_object' },
+      temperature: opts.temperature ?? 0.2,
+      max_tokens: opts.maxTokens ?? 8000,
+    }),
+    signal: AbortSignal.timeout(120_000),
+  });
+  if (!res.ok) {
+    const body = await res.text().catch(() => '');
+    throw Object.assign(new Error(`DeepSeek ${res.status}: ${body.slice(0, 300)}`), {
+      code: 'DEEPSEEK_HTTP_ERROR',
+      status: res.status,
+    });
+  }
+  const data = (await res.json()) as DeepSeekResponse;
+  const content = data.choices?.[0]?.message?.content;
+  if (!content) throw new Error('DeepSeek: пустой ответ');
+  try {
+    return JSON.parse(content) as T;
+  } catch {
+    throw Object.assign(new Error('DeepSeek вернул не валидный JSON'), {
+      code: 'DEEPSEEK_BAD_JSON',
+      raw: content,
+    });
+  }
+}

apps/api/src/modules/templates/extract.ts

@@ -0,0 +1,114 @@
+import { execFile } from 'node:child_process';
+import { mkdtemp, readFile, readdir, rm, writeFile } from 'node:fs/promises';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { promisify } from 'node:util';
+import mammoth from 'mammoth';
+import * as pdfParseNs from 'pdf-parse';
+
+// pdf-parse в ESM экспортирует default или сам namespace — нормализуем.
+const pdfParse: (buf: Buffer) => Promise<{ text: string; numpages: number }> =
+  // @ts-expect-error namespace shape varies between cjs/esm
+  (pdfParseNs.default ?? pdfParseNs) as never;
+
+const execFileP = promisify(execFile);
+
+export type ExtractedSource = 'docx' | 'pdf-text' | 'pdf-ocr' | 'image-ocr';
+export type Extracted = { text: string; source: ExtractedSource; pageCount?: number };
+
+const OCR_LANGS = 'rus+eng';
+
+/**
+ * Извлекает читаемый текст из произвольного загруженного документа.
+ * - DOCX → mammoth (без OCR);
+ * - PDF с текстовым слоем → pdf-parse;
+ * - PDF-скан → pdftoppm в PNG → tesseract;
+ * - PNG/JPG → tesseract напрямую.
+ *
+ * Если в системе нет tesseract/poppler — для не-DOCX вернётся ошибка с code=NO_OCR.
+ */
+export async function extractText(buf: Buffer, mime: string, filename: string): Promise<Extracted> {
+  const lower = (mime + ' ' + filename).toLowerCase();
+  if (lower.includes('wordprocessingml') || lower.endsWith('.docx')) {
+    const r = await mammoth.extractRawText({ buffer: buf });
+    return { text: cleanup(r.value), source: 'docx' };
+  }
+  if (mime.includes('pdf') || lower.endsWith('.pdf')) {
+    return extractFromPdf(buf);
+  }
+  if (mime.startsWith('image/') || /\.(png|jpe?g|tiff?|bmp)$/i.test(filename)) {
+    const text = await ocrImageBuffer(buf, '.png');
+    return { text: cleanup(text), source: 'image-ocr' };
+  }
+  throw Object.assign(new Error(`Неподдерживаемый формат: ${mime || filename}`), {
+    code: 'UNSUPPORTED_MIME',
+  });
+}
+
+async function extractFromPdf(buf: Buffer): Promise<Extracted> {
+  const parsed = await pdfParse(buf);
+  const text = cleanup(parsed.text);
+  // Эвристика: если текст-слой даёт меньше 60 символов на страницу — это сканированный PDF.
+  const charsPerPage = parsed.numpages > 0 ? text.length / parsed.numpages : text.length;
+  if (text.length > 200 && charsPerPage > 60) {
+    return { text, source: 'pdf-text', pageCount: parsed.numpages };
+  }
+  // OCR pipeline
+  const ocr = await ocrPdfBuffer(buf);
+  return { text: cleanup(ocr), source: 'pdf-ocr', pageCount: parsed.numpages };
+}
+
+async function ocrImageBuffer(buf: Buffer, ext: string): Promise<string> {
+  const dir = await mkdtemp(join(tmpdir(), 'docmgr-ocr-'));
+  try {
+    const inFile = join(dir, `in${ext}`);
+    await writeFile(inFile, buf);
+    const { stdout } = await execFileP('tesseract', [inFile, 'stdout', '-l', OCR_LANGS], {
+      maxBuffer: 32 * 1024 * 1024,
+    });
+    return stdout;
+  } catch (e) {
+    if ((e as { code?: string }).code === 'ENOENT') {
+      throw Object.assign(new Error('Tesseract не установлен в окружении. PDF-сканы обработать не получится.'), {
+        code: 'NO_OCR',
+      });
+    }
+    throw e;
+  } finally {
+    await rm(dir, { recursive: true, force: true });
+  }
+}
+
+async function ocrPdfBuffer(buf: Buffer): Promise<string> {
+  const dir = await mkdtemp(join(tmpdir(), 'docmgr-pdf-'));
+  try {
+    const inFile = join(dir, 'in.pdf');
+    await writeFile(inFile, buf);
+    // pdftoppm input.pdf out -png -r 200 → out-1.png, out-2.png ...
+    try {
+      await execFileP('pdftoppm', [inFile, join(dir, 'out'), '-png', '-r', '200']);
+    } catch (e) {
+      if ((e as { code?: string }).code === 'ENOENT') {
+        throw Object.assign(new Error('pdftoppm (poppler-utils) не установлен.'), { code: 'NO_OCR' });
+      }
+      throw e;
+    }
+    const files = (await readdir(dir)).filter((f) => f.startsWith('out-') && f.endsWith('.png')).sort();
+    const parts: string[] = [];
+    for (const f of files) {
+      const pageBuf = await readFile(join(dir, f));
+      parts.push(await ocrImageBuffer(pageBuf, '.png'));
+    }
+    return parts.join('\n\n');
+  } finally {
+    await rm(dir, { recursive: true, force: true });
+  }
+}
+
+function cleanup(s: string): string {
+  return s
+    .replace(/­/g, '') // soft hyphens
+    .replace(/[ \t]+\n/g, '\n')
+    .replace(/\n{3,}/g, '\n\n')
+    .trim();
+}

apps/api/src/modules/templates/import.routes.ts

@@ -0,0 +1,95 @@
+import type { FastifyInstance } from 'fastify';
+import { Prisma } from '@prisma/client';
+import { prisma } from '../../db.js';
+import { getOrganizationId } from '../../lib/org.js';
+import { extractText } from './extract.js';
+import { recognizeTemplate } from './recognize.js';
+
+const MAX_BYTES = 20 * 1024 * 1024; // 20 MB
+
+export async function templatesImportRoutes(app: FastifyInstance) {
+  app.post(
+    '/api/templates/import',
+    { preHandler: app.requireDocPermission('user') },
+    async (req, reply) => {
+      const orgId = getOrganizationId(req);
+      const file = await req.file({ limits: { fileSize: MAX_BYTES } });
+      if (!file) {
+        reply.code(400).send({ error: 'no_file' });
+        return;
+      }
+      const buf = await file.toBuffer();
+      const filename = file.filename || 'template';
+      const mime = file.mimetype || '';
+
+      // Опц. имя/тип передаются полями формы; если нет — определит LLM
+      const fields = (file.fields ?? {}) as Record<string, { value?: string }>;
+      const userName = typeof fields.name?.value === 'string' ? fields.name.value : null;
+      const userDocType = typeof fields.docType?.value === 'string' ? fields.docType.value : null;
+
+      try {
+        // 1) Извлекаем текст
+        const extracted = await extractText(buf, mime, filename);
+        if (extracted.text.trim().length < 30) {
+          reply.code(422).send({
+            error: 'empty_extracted_text',
+            message: 'Не удалось извлечь читаемый текст. Возможно, скан плохого качества.',
+            source: extracted.source,
+          });
+          return;
+        }
+
+        // 2) Распознаём через DeepSeek
+        const recognized = await recognizeTemplate(extracted.text);
+        const docType = (userDocType as 'contract' | 'invoice' | 'act' | 'upd') ?? recognized.docType;
+        const name = userName?.trim() || recognized.title || `Импорт ${new Date().toLocaleDateString('ru-RU')}`;
+
+        const created = await prisma.documentTemplate.create({
+          data: {
+            organizationId: orgId,
+            docType,
+            name,
+            body: recognized.docBody as Prisma.InputJsonValue,
+          },
+        });
+
+        reply.code(201).send({
+          template: created,
+          extractedFrom: extracted.source,
+          textLength: extracted.text.length,
+        });
+      } catch (e) {
+        const err = e as { code?: string; message?: string; status?: number };
+        if (err.code === 'NO_DEEPSEEK_KEY') {
+          reply.code(503).send({ error: 'no_deepseek_key', message: err.message });
+          return;
+        }
+        if (err.code === 'NO_OCR') {
+          reply.code(503).send({ error: 'no_ocr', message: err.message });
+          return;
+        }
+        if (err.code === 'UNSUPPORTED_MIME') {
+          reply.code(415).send({ error: 'unsupported_mime', message: err.message });
+          return;
+        }
+        if (err.code === 'INVALID_DOC_BODY') {
+          reply.code(502).send({
+            error: 'invalid_doc_body',
+            message: 'LLM вернула структуру, не прошедшую валидацию. Попробуйте загрузить ещё раз или отредактировать вручную.',
+          });
+          return;
+        }
+        if (err.code === 'DEEPSEEK_HTTP_ERROR') {
+          reply.code(502).send({
+            error: 'deepseek_error',
+            message: err.message,
+            status: err.status ?? 502,
+          });
+          return;
+        }
+        app.log.error({ err: e }, 'template import failed');
+        reply.code(500).send({ error: 'import_failed', message: err.message ?? 'unknown' });
+      }
+    },
+  );
+}

apps/api/src/modules/templates/recognize.ts

@@ -0,0 +1,156 @@
+import type { DocType } from '@prisma/client';
+import { DocBody as DocBodySchema } from '@doc-manager/shared';
+import { deepseekJsonChat } from './deepseek.js';
+
+// LLM возвращает упрощённую структуру (string text вместо TipTap-JSON).
+// Конвертим её в полный DocBody с RichText на нашей стороне.
+
+type LlmBlock =
+  | { type: 'heading'; level: 1 | 2 | 3; text: string }
+  | { type: 'paragraph'; text: string }
+  | { type: 'party'; role: 'executor' | 'customer'; bind: { kind: 'self' | 'client' } }
+  | { type: 'services_table'; columns?: string[]; lines?: [] }
+  | { type: 'totals'; showVat?: boolean; showInWords?: boolean }
+  | { type: 'terms'; text: string }
+  | { type: 'signatures'; sides: ('executor' | 'customer')[] }
+  | { type: 'custom_text'; text: string }
+  | { type: 'page_break' };
+
+type LlmResult = {
+  docType?: 'contract' | 'invoice' | 'act' | 'upd';
+  title?: string;
+  blocks: LlmBlock[];
+};
+
+const SYSTEM_PROMPT = `Ты — парсер юридических документов на русском языке. Получаешь plain-text договора, счёта, акта или УПД и возвращаешь его структуру строго в JSON формате DocBody.
+
+Цель: создать ШАБЛОН, в котором конкретные данные сторон, номера, даты — заменены на плейсхолдеры. Шаблон потом будет инстансироваться для конкретного клиента и документа.
+
+Правила замены на плейсхолдеры (заменяй ТОЛЬКО эти сущности, остальной текст оставь как есть):
+- Конкретный номер договора/счёта → {{contract.number}}
+- Конкретная дата документа → {{contract.date}}
+- Текущая дата (на момент рендера) → {{today}}
+- Реквизиты исполнителя (наша компания):
+  {{executor.name}}, {{executor.inn}}, {{executor.kpp}}, {{executor.ogrn}}, {{executor.legalAddress}},
+  {{executor.signatoryName}}, {{executor.signatoryPosition}},
+  {{executor.bankName}}, {{executor.bankBik}}, {{executor.bankAccount}}
+- Реквизиты заказчика (клиента):
+  {{customer.name}}, {{customer.inn}}, {{customer.kpp}}, {{customer.address}},
+  {{customer.email}}, {{customer.phone}}, {{customer.contactPerson}}
+
+Структура ответа (JSON-объект):
+{
+  "docType": "contract" | "invoice" | "act" | "upd",
+  "title": "Договор оказания услуг",
+  "blocks": [
+    { "type": "heading", "level": 1, "text": "Договор оказания услуг № {{contract.number}} от {{contract.date}}" },
+    { "type": "paragraph", "text": "..." },
+    { "type": "party", "role": "executor", "bind": { "kind": "self" } },
+    { "type": "party", "role": "customer", "bind": { "kind": "client" } },
+    { "type": "services_table", "columns": ["name","qty","unit","price","vat","sum"], "lines": [] },
+    { "type": "totals", "showVat": true, "showInWords": true },
+    { "type": "terms", "text": "..." },
+    { "type": "signatures", "sides": ["executor","customer"] },
+    { "type": "custom_text", "text": "..." },
+    { "type": "page_break" }
+  ]
+}
+
+Важные правила:
+1. Если в документе встречается реквизитный блок одной из сторон (ИНН/КПП/адрес/банк) — выдай ОДИН блок "party" с правильным role, не добавляй параграф с текстовым перечислением реквизитов.
+2. Услуги/работы в табличной форме — НЕ переписывай построчно, ставь блок "services_table" (lines пустой массив, строки пользователь добавит вручную).
+3. Если есть итоговые суммы (Итого, в т.ч. НДС, сумма прописью) — ставь блок "totals" со включенными нужными опциями.
+4. Подписи в конце — блок "signatures" с указанием каких сторон видно.
+5. Нумерованные пункты «1. Предмет договора», «2. Цена и порядок расчётов» и т.п. — каждый раздел как блок "terms" (заголовок раздела можно положить отдельным "heading" level 2).
+6. Не выдумывай блоки, которых нет в документе.
+7. text внутри блоков — обычная строка (не TipTap JSON), может содержать \\n для новых параграфов внутри блока.
+8. Заполняй "title" коротким названием документа.
+9. Если не уверен в типе документа — ставь "contract".`;
+
+function uid(): string {
+  return Math.random().toString(36).slice(2, 11);
+}
+
+function plainToRich(text: string): unknown {
+  const lines = text.split(/\r?\n/);
+  return {
+    type: 'doc',
+    content: lines.map((line) => ({
+      type: 'paragraph',
+      content: line ? [{ type: 'text', text: line }] : [],
+    })),
+  };
+}
+
+function llmToDocBody(result: LlmResult): { docBody: unknown; docType: DocType; title: string } {
+  const docType: DocType = (result.docType as DocType) ?? 'contract';
+  const title = result.title ?? 'Документ';
+  const blocks = (result.blocks ?? []).map((b) => {
+    const id = uid();
+    switch (b.type) {
+      case 'heading':
+        return { id, type: 'heading', level: clampLevel(b.level), text: plainToRich(b.text) };
+      case 'paragraph':
+        return { id, type: 'paragraph', text: plainToRich(b.text) };
+      case 'party':
+        return {
+          id,
+          type: 'party',
+          role: b.role,
+          bind: b.bind?.kind === 'self' ? { kind: 'self' as const } : { kind: 'client' as const },
+        };
+      case 'services_table':
+        return {
+          id,
+          type: 'services_table',
+          columns: ['name', 'qty', 'unit', 'price', 'vat', 'sum'] as const,
+          lines: [],
+        };
+      case 'totals':
+        return { id, type: 'totals', showVat: b.showVat ?? true, showInWords: b.showInWords ?? true };
+      case 'terms':
+        return { id, type: 'terms', text: plainToRich(b.text) };
+      case 'signatures':
+        return { id, type: 'signatures', sides: b.sides?.length ? b.sides : (['executor', 'customer'] as const) };
+      case 'custom_text':
+        return { id, type: 'custom_text', text: plainToRich(b.text) };
+      case 'page_break':
+        return { id, type: 'page_break' };
+      default:
+        return { id, type: 'custom_text', text: plainToRich('') };
+    }
+  });
+  const docBody = { version: 1, blocks, vars: {} };
+  return { docBody, docType, title };
+}
+
+function clampLevel(l: number): 1 | 2 | 3 {
+  if (l === 1 || l === 2 || l === 3) return l;
+  return 1;
+}
+
+export async function recognizeTemplate(text: string): Promise<{ docBody: unknown; docType: DocType; title: string; raw?: unknown }> {
+  // Документ может быть длинным — DeepSeek-chat умеет до 64k context, сожмём только если совсем огромный
+  const trimmed = text.length > 60_000 ? text.slice(0, 60_000) + '\n\n…[документ обрезан]' : text;
+
+  const llm = await deepseekJsonChat<LlmResult>(
+    [
+      { role: 'system', content: SYSTEM_PROMPT },
+      { role: 'user', content: trimmed },
+    ],
+    { temperature: 0.1, maxTokens: 8000 },
+  );
+
+  const built = llmToDocBody(llm);
+
+  // Финальная валидация на нашей стороне
+  const parsed = DocBodySchema.safeParse(built.docBody);
+  if (!parsed.success) {
+    throw Object.assign(new Error('DocBody после LLM не прошёл валидацию'), {
+      code: 'INVALID_DOC_BODY',
+      issues: parsed.error.flatten(),
+      raw: built.docBody,
+    });
+  }
+  return { ...built, docBody: parsed.data, raw: llm };
+}

apps/api/src/server.ts

@@ -3,6 +3,7 @@ import Fastify from 'fastify';
 import cookie from '@fastify/cookie';
 import cors from '@fastify/cors';
 import helmet from '@fastify/helmet';
+import multipart from '@fastify/multipart';
 import { env } from './env.js';
 import authPlugin from './plugins/auth.js';
 import { healthRoutes } from './routes/health.js';
@@ -14,6 +15,7 @@ import { servicesRoutes } from './modules/services/routes.js';
 import { documentsRoutes } from './modules/documents/routes.js';
 import { documentsPdfRoutes } from './modules/documents/pdf.routes.js';
 import { templatesRoutes } from './modules/templates/routes.js';
+import { templatesImportRoutes } from './modules/templates/import.routes.js';
 import { dadataRoutes } from './modules/dadata/routes.js';
 import { shutdownBrowser } from './modules/documents/pdf.js';
 import activeOrgPlugin from './plugins/activeOrg.js';
@@ -38,6 +40,7 @@ async function main() {
     credentials: true,
   });
   await app.register(cookie);
+  await app.register(multipart, { limits: { fileSize: 25 * 1024 * 1024 } });
   await app.register(authPlugin);
   await app.register(activeOrgPlugin);
 
@@ -50,6 +53,7 @@ async function main() {
   await app.register(documentsRoutes);
   await app.register(documentsPdfRoutes);
   await app.register(templatesRoutes);
+  await app.register(templatesImportRoutes);
   await app.register(dadataRoutes);
 
   app.addHook('onClose', async () => {

apps/web/src/pages/Templates.tsx

@@ -1,8 +1,9 @@
-import { useEffect, useState } from 'react';
+import { useEffect, useRef, useState } from 'react';
 import { Link, useNavigate } from 'react-router-dom';
-import { api, type DocBody, type DocType, type DocumentTemplate } from '../api.js';
+import { api, ApiError, type DocBody, type DocType, type DocumentTemplate } from '../api.js';
 import { Button, EmptyState, Field, Modal, Select } from '../components/ui.js';
 import { emptyRich } from '../lib/richtext.js';
+import { redirectToLogin } from '../auth.js';
 
 const DOC_TYPE_LABEL: Record<DocType, string> = {
   contract: 'Договор', invoice: 'Счёт', act: 'Акт', upd: 'УПД',
@@ -22,10 +23,18 @@ function emptyBody(): DocBody {
   };
 }
 
+type ImportState =
+  | { stage: 'idle' }
+  | { stage: 'uploading' | 'analyzing'; filename: string }
+  | { stage: 'error'; message: string };
+
 export function TemplatesPage() {
   const [items, setItems] = useState<DocumentTemplate[] | null>(null);
   const [creating, setCreating] = useState<{ name: string; docType: DocType } | null>(null);
+  const [importState, setImportState] = useState<ImportState>({ stage: 'idle' });
+  const [importDocType, setImportDocType] = useState<DocType>('contract');
   const [error, setError] = useState<string | null>(null);
+  const fileInputRef = useRef<HTMLInputElement>(null);
   const navigate = useNavigate();
 
   async function load() {
@@ -76,15 +85,99 @@ export function TemplatesPage() {
     }
   }
 
+  async function importFile(file: File) {
+    setImportState({ stage: 'uploading', filename: file.name });
+    const fd = new FormData();
+    fd.append('docType', importDocType);
+    fd.append('file', file);
+    try {
+      const res = await fetch('/api/templates/import', {
+        method: 'POST',
+        credentials: 'include',
+        body: fd,
+      });
+      if (res.status === 401) redirectToLogin();
+      setImportState({ stage: 'analyzing', filename: file.name });
+      const text = await res.text();
+      const data = text ? JSON.parse(text) : {};
+      if (!res.ok) {
+        const msg =
+          data.error === 'no_deepseek_key'
+            ? 'DeepSeek API ключ не настроен на сервере.'
+            : data.error === 'no_ocr'
+              ? 'OCR (tesseract) недоступен на сервере. Загрузка сканов невозможна.'
+              : data.error === 'unsupported_mime'
+                ? 'Неподдерживаемый формат файла. DOCX, PDF, PNG, JPG.'
+                : data.error === 'empty_extracted_text'
+                  ? 'Не удалось извлечь текст (плохое качество скана).'
+                  : data.error === 'invalid_doc_body'
+                    ? 'LLM вернула невалидную структуру. Попробуйте ещё раз.'
+                    : data.message || `${data.error} (HTTP ${res.status})`;
+        setImportState({ stage: 'error', message: msg });
+        return;
+      }
+      const tpl: DocumentTemplate = data.template;
+      setImportState({ stage: 'idle' });
+      navigate(`/templates/${tpl.id}`);
+    } catch (e) {
+      setImportState({ stage: 'error', message: String(e) });
+    }
+  }
+
+  function onPickFile(e: React.ChangeEvent<HTMLInputElement>) {
+    const f = e.target.files?.[0];
+    if (f) void importFile(f);
+    e.target.value = '';
+  }
+
   return (
     <main className="content">
       <header className="page-head">
         <h2>Шаблоны</h2>
+        <div style={{ display: 'flex', gap: 8, alignItems: 'center' }}>
+          <Select
+            label=""
+            value={importDocType}
+            onChange={(v) => setImportDocType(v as DocType)}
+            options={[
+              { value: 'contract', label: 'Договор' },
+              { value: 'invoice', label: 'Счёт' },
+              { value: 'act', label: 'Акт' },
+              { value: 'upd', label: 'УПД' },
+            ]}
+          />
+          <Button onClick={() => fileInputRef.current?.click()} disabled={importState.stage !== 'idle' && importState.stage !== 'error'}>
+            ⤴ Загрузить документ
+          </Button>
+          <input
+            ref={fileInputRef}
+            type="file"
+            accept=".docx,.pdf,.png,.jpg,.jpeg,.tif,.tiff,application/pdf,image/*"
+            style={{ display: 'none' }}
+            onChange={onPickFile}
+          />
           <Button variant="primary" onClick={() => setCreating({ name: '', docType: 'contract' })}>
             + Новый шаблон
           </Button>
+        </div>
       </header>
 
+      {importState.stage === 'uploading' || importState.stage === 'analyzing' ? (
+        <div className="import-banner">
+          <div className="spinner" />
+          <span>
+            {importState.stage === 'uploading' ? 'Загружаю' : 'Распознаю'} «{importState.filename}»…
+            {importState.stage === 'analyzing' ? ' DeepSeek анализирует структуру (10–60 сек).' : ''}
+          </span>
+        </div>
+      ) : null}
+      {importState.stage === 'error' ? (
+        <div className="error-text">
+          Импорт не удался: {importState.message}
+          <Button variant="ghost" onClick={() => setImportState({ stage: 'idle' })}>×</Button>
+        </div>
+      ) : null}
+
       {error ? <div className="error-text">{error}</div> : null}
 
       {items === null ? (

apps/web/src/styles.css

@@ -275,6 +275,23 @@ body {
   .tabs { border-bottom-color: #2a2e35; }
 }
 
+/* === import banner === */
+.import-banner {
+  display: flex; align-items: center; gap: 12px;
+  padding: 12px 16px; margin: 12px 0;
+  background: #eff6ff; border: 1px solid #bfdbfe; color: #1e40af;
+  border-radius: 8px;
+}
+.spinner {
+  width: 16px; height: 16px; border-radius: 50%;
+  border: 2px solid #bfdbfe; border-top-color: #2563eb;
+  animation: spin 0.8s linear infinite;
+}
+@keyframes spin { to { transform: rotate(360deg); } }
+@media (prefers-color-scheme: dark) {
+  .import-banner { background: #14213d; border-color: #1e3a8a; color: #93c5fd; }
+}
+
 /* === inn lookup === */
 .inn-lookup { margin-top: 6px; display: flex; flex-direction: column; gap: 4px; }
 .inn-lookup__error { font-size: 12px; color: #c0392b; }

docker/Dockerfile.api

@@ -13,7 +13,12 @@ RUN apk add --no-cache \
     ca-certificates \
     ttf-dejavu \
     ttf-liberation \
-    font-noto-cjk
+    font-noto-cjk \
+    tesseract-ocr \
+    tesseract-ocr-data-rus \
+    tesseract-ocr-data-eng \
+    poppler-utils \
+    imagemagick
 
 ENV PUPPETEER_EXECUTABLE_PATH=/usr/bin/chromium-browser
 ENV PUPPETEER_SKIP_DOWNLOAD=true

docker/docker-compose.yml

@@ -42,6 +42,9 @@ services:
       TOCHKA_JWT_KEY: ${TOCHKA_JWT_KEY:-}
       TOCHKA_WEBHOOK_SECRET: ${TOCHKA_WEBHOOK_SECRET:-}
       DADATA_API_KEY: ${DADATA_API_KEY:-}
+      DEEPSEEK_API_KEY: ${DEEPSEEK_API_KEY:-}
+      DEEPSEEK_BASE_URL: ${DEEPSEEK_BASE_URL:-https://api.deepseek.com}
+      DEEPSEEK_MODEL: ${DEEPSEEK_MODEL:-deepseek-chat}
       DEFAULT_ORGANIZATION_ID: ${DEFAULT_ORGANIZATION_ID:-00000000-0000-0000-0000-000000000001}
       DEV_BYPASS_AUTH: "0"
     expose:

package-lock.json

@@ -26,15 +26,20 @@
         "@fastify/cookie": "^9.4.0",
         "@fastify/cors": "^9.0.1",
         "@fastify/helmet": "^11.1.1",
+        "@fastify/multipart": "^10.0.0",
         "@prisma/client": "^5.22.0",
         "fastify": "^4.28.1",
         "fastify-plugin": "^4.5.1",
         "jose": "^5.9.6",
+        "mammoth": "^1.12.0",
+        "node-tesseract-ocr": "^2.2.1",
+        "pdf-parse": "^2.4.5",
         "puppeteer-core": "^24.42.0",
         "zod": "^3.23.8"
       },
       "devDependencies": {
         "@types/node": "^20.16.0",
+        "@types/pdf-parse": "^1.1.5",
         "embedded-postgres": "^18.3.0-beta.17",
         "pino-pretty": "^11.3.0",
         "prisma": "^5.22.0",
@@ -950,6 +955,12 @@
         "fast-uri": "^2.0.0"
       }
     },
+    "node_modules/@fastify/busboy": {
+      "version": "3.2.0",
+      "resolved": "https://registry.npmjs.org/@fastify/busboy/-/busboy-3.2.0.tgz",
+      "integrity": "sha512-m9FVDXU3GT2ITSe0UaMA5rU3QkfC/UXtCU8y0gSN/GugTqtVldOBWIB5V6V3sbmenVZUIpU6f+mPEO2+m5iTaA==",
+      "license": "MIT"
+    },
     "node_modules/@fastify/cookie": {
       "version": "9.4.0",
       "resolved": "https://registry.npmjs.org/@fastify/cookie/-/cookie-9.4.0.tgz",
@@ -970,6 +981,22 @@
         "mnemonist": "0.39.6"
       }
     },
+    "node_modules/@fastify/deepmerge": {
+      "version": "3.2.1",
+      "resolved": "https://registry.npmjs.org/@fastify/deepmerge/-/deepmerge-3.2.1.tgz",
+      "integrity": "sha512-N5Oqvltoa2r9z1tbx4xjky0oRR60v+T47Ic4J1ukoVQcptLOrIdRnCSdTGmOmajZuHVKlTnfcmrjyqsGEW1ztA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fastify"
+        },
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/fastify"
+        }
+      ],
+      "license": "MIT"
+    },
     "node_modules/@fastify/error": {
       "version": "3.4.1",
       "resolved": "https://registry.npmjs.org/@fastify/error/-/error-3.4.1.tgz",
@@ -1004,6 +1031,77 @@
         "fast-deep-equal": "^3.1.3"
       }
     },
+    "node_modules/@fastify/multipart": {
+      "version": "10.0.0",
+      "resolved": "https://registry.npmjs.org/@fastify/multipart/-/multipart-10.0.0.tgz",
+      "integrity": "sha512-pUx3Z1QStY7E7kwvDTIvB6P+rF5lzP+iqPgZyJyG3yBJVPvQaZxzDHYbQD89rbY0ciXrMOyGi8ezHDVexLvJDA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fastify"
+        },
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/fastify"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "@fastify/busboy": "^3.0.0",
+        "@fastify/deepmerge": "^3.0.0",
+        "@fastify/error": "^4.0.0",
+        "fastify-plugin": "^5.0.0",
+        "secure-json-parse": "^4.0.0"
+      }
+    },
+    "node_modules/@fastify/multipart/node_modules/@fastify/error": {
+      "version": "4.2.0",
+      "resolved": "https://registry.npmjs.org/@fastify/error/-/error-4.2.0.tgz",
+      "integrity": "sha512-RSo3sVDXfHskiBZKBPRgnQTtIqpi/7zhJOEmAxCiBcM7d0uwdGdxLlsCaLzGs8v8NnxIRlfG0N51p5yFaOentQ==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fastify"
+        },
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/fastify"
+        }
+      ],
+      "license": "MIT"
+    },
+    "node_modules/@fastify/multipart/node_modules/fastify-plugin": {
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/fastify-plugin/-/fastify-plugin-5.1.0.tgz",
+      "integrity": "sha512-FAIDA8eovSt5qcDgcBvDuX/v0Cjz0ohGhENZ/wpc3y+oZCY2afZ9Baqql3g/lC+OHRnciQol4ww7tuthOb9idw==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fastify"
+        },
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/fastify"
+        }
+      ],
+      "license": "MIT"
+    },
+    "node_modules/@fastify/multipart/node_modules/secure-json-parse": {
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/secure-json-parse/-/secure-json-parse-4.1.0.tgz",
+      "integrity": "sha512-l4KnYfEyqYJxDwlNVyRfO2E4NTHfMKAWdUuA8J0yve2Dz/E/PdBepY03RvyJpssIpRFwJoCD55wA+mEDs6ByWA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fastify"
+        },
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/fastify"
+        }
+      ],
+      "license": "BSD-3-Clause"
+    },
     "node_modules/@jridgewell/gen-mapping": {
       "version": "0.3.13",
       "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.13.tgz",
@@ -1054,6 +1152,205 @@
         "@jridgewell/sourcemap-codec": "^1.4.14"
       }
     },
+    "node_modules/@napi-rs/canvas": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas/-/canvas-0.1.80.tgz",
+      "integrity": "sha512-DxuT1ClnIPts1kQx8FBmkk4BQDTfI5kIzywAaMjQSXfNnra5UFU9PwurXrl+Je3bJ6BGsp/zmshVVFbCmyI+ww==",
+      "license": "MIT",
+      "workspaces": [
+        "e2e/*"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "optionalDependencies": {
+        "@napi-rs/canvas-android-arm64": "0.1.80",
+        "@napi-rs/canvas-darwin-arm64": "0.1.80",
+        "@napi-rs/canvas-darwin-x64": "0.1.80",
+        "@napi-rs/canvas-linux-arm-gnueabihf": "0.1.80",
+        "@napi-rs/canvas-linux-arm64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-arm64-musl": "0.1.80",
+        "@napi-rs/canvas-linux-riscv64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-x64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-x64-musl": "0.1.80",
+        "@napi-rs/canvas-win32-x64-msvc": "0.1.80"
+      }
+    },
+    "node_modules/@napi-rs/canvas-android-arm64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-android-arm64/-/canvas-android-arm64-0.1.80.tgz",
+      "integrity": "sha512-sk7xhN/MoXeuExlggf91pNziBxLPVUqF2CAVnB57KLG/pz7+U5TKG8eXdc3pm0d7Od0WreB6ZKLj37sX9muGOQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-darwin-arm64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-arm64/-/canvas-darwin-arm64-0.1.80.tgz",
+      "integrity": "sha512-O64APRTXRUiAz0P8gErkfEr3lipLJgM6pjATwavZ22ebhjYl/SUbpgM0xcWPQBNMP1n29afAC/Us5PX1vg+JNQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-darwin-x64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-x64/-/canvas-darwin-x64-0.1.80.tgz",
+      "integrity": "sha512-FqqSU7qFce0Cp3pwnTjVkKjjOtxMqRe6lmINxpIZYaZNnVI0H5FtsaraZJ36SiTHNjZlUB69/HhxNDT1Aaa9vA==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm-gnueabihf": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm-gnueabihf/-/canvas-linux-arm-gnueabihf-0.1.80.tgz",
+      "integrity": "sha512-eyWz0ddBDQc7/JbAtY4OtZ5SpK8tR4JsCYEZjCE3dI8pqoWUC8oMwYSBGCYfsx2w47cQgQCgMVRVTFiiO38hHQ==",
+      "cpu": [
+        "arm"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-gnu/-/canvas-linux-arm64-gnu-0.1.80.tgz",
+      "integrity": "sha512-qwA63t8A86bnxhuA/GwOkK3jvb+XTQaTiVML0vAWoHyoZYTjNs7BzoOONDgTnNtr8/yHrq64XXzUoLqDzU+Uuw==",
+      "cpu": [
+        "arm64"
+      ],
+      "libc": [
+        "glibc"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm64-musl": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-musl/-/canvas-linux-arm64-musl-0.1.80.tgz",
+      "integrity": "sha512-1XbCOz/ymhj24lFaIXtWnwv/6eFHXDrjP0jYkc6iHQ9q8oXKzUX1Lc6bu+wuGiLhGh2GS/2JlfORC5ZcXimRcg==",
+      "cpu": [
+        "arm64"
+      ],
+      "libc": [
+        "musl"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-riscv64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-riscv64-gnu/-/canvas-linux-riscv64-gnu-0.1.80.tgz",
+      "integrity": "sha512-XTzR125w5ZMs0lJcxRlS1K3P5RaZ9RmUsPtd1uGt+EfDyYMu4c6SEROYsxyatbbu/2+lPe7MPHOO/0a0x7L/gw==",
+      "cpu": [
+        "riscv64"
+      ],
+      "libc": [
+        "glibc"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-x64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-gnu/-/canvas-linux-x64-gnu-0.1.80.tgz",
+      "integrity": "sha512-BeXAmhKg1kX3UCrJsYbdQd3hIMDH/K6HnP/pG2LuITaXhXBiNdh//TVVVVCBbJzVQaV5gK/4ZOCMrQW9mvuTqA==",
+      "cpu": [
+        "x64"
+      ],
+      "libc": [
+        "glibc"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-x64-musl": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-musl/-/canvas-linux-x64-musl-0.1.80.tgz",
+      "integrity": "sha512-x0XvZWdHbkgdgucJsRxprX/4o4sEed7qo9rCQA9ugiS9qE2QvP0RIiEugtZhfLH3cyI+jIRFJHV4Fuz+1BHHMg==",
+      "cpu": [
+        "x64"
+      ],
+      "libc": [
+        "musl"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-win32-x64-msvc": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-win32-x64-msvc/-/canvas-win32-x64-msvc-0.1.80.tgz",
+      "integrity": "sha512-Z8jPsM6df5V8B1HrCHB05+bDiCxjE9QA//3YrkKIdVDEwn5RKaqOxCJDRJkl48cJbylcrJbW4HxZbTte8juuPg==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
     "node_modules/@pinojs/redact": {
       "version": "0.4.0",
       "resolved": "https://registry.npmjs.org/@pinojs/redact/-/redact-0.4.0.tgz",
@@ -1634,6 +1931,16 @@
         "undici-types": "~6.21.0"
       }
     },
+    "node_modules/@types/pdf-parse": {
+      "version": "1.1.5",
+      "resolved": "https://registry.npmjs.org/@types/pdf-parse/-/pdf-parse-1.1.5.tgz",
+      "integrity": "sha512-kBfrSXsloMnUJOKi25s3+hRmkycHfLK6A09eRGqF/N8BkQoPUmaCr+q8Cli5FnfohEz/rsv82zAiPz/LXtOGhA==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@types/node": "*"
+      }
+    },
     "node_modules/@types/prop-types": {
       "version": "15.7.15",
       "resolved": "https://registry.npmjs.org/@types/prop-types/-/prop-types-15.7.15.tgz",
@@ -1693,6 +2000,15 @@
         "vite": "^4.2.0 || ^5.0.0 || ^6.0.0 || ^7.0.0"
       }
     },
+    "node_modules/@xmldom/xmldom": {
+      "version": "0.8.13",
+      "resolved": "https://registry.npmjs.org/@xmldom/xmldom/-/xmldom-0.8.13.tgz",
+      "integrity": "sha512-KRYzxepc14G/CEpEGc3Yn+JKaAeT63smlDr+vjB8jRfgTBBI9wRj/nkQEO+ucV8p8I9bfKLWp37uHgFrbntPvw==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=10.0.0"
+      }
+    },
     "node_modules/abort-controller": {
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz",
@@ -1794,6 +2110,15 @@
         "url": "https://github.com/chalk/ansi-styles?sponsor=1"
       }
     },
+    "node_modules/argparse": {
+      "version": "1.0.10",
+      "resolved": "https://registry.npmjs.org/argparse/-/argparse-1.0.10.tgz",
+      "integrity": "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg==",
+      "license": "MIT",
+      "dependencies": {
+        "sprintf-js": "~1.0.2"
+      }
+    },
     "node_modules/ast-types": {
       "version": "0.13.4",
       "resolved": "https://registry.npmjs.org/ast-types/-/ast-types-0.13.4.tgz",
@@ -1930,7 +2255,6 @@
       "version": "1.5.1",
       "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
       "integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==",
-      "dev": true,
       "funding": [
         {
           "type": "github",
@@ -1969,6 +2293,12 @@
         "node": ">=10.0.0"
       }
     },
+    "node_modules/bluebird": {
+      "version": "3.4.7",
+      "resolved": "https://registry.npmjs.org/bluebird/-/bluebird-3.4.7.tgz",
+      "integrity": "sha512-iD3898SR7sWVRHbiQv+sHUtHnMvC1o3nW5rAcqnq3uOn07DSAppZYUkIGslDz6gXC7HfunPe7YVBgoEJASPcHA==",
+      "license": "MIT"
+    },
     "node_modules/browserslist": {
       "version": "4.28.2",
       "resolved": "https://registry.npmjs.org/browserslist/-/browserslist-4.28.2.tgz",
@@ -2190,6 +2520,12 @@
         "node": ">=6.6.0"
       }
     },
+    "node_modules/core-util-is": {
+      "version": "1.0.3",
+      "resolved": "https://registry.npmjs.org/core-util-is/-/core-util-is-1.0.3.tgz",
+      "integrity": "sha512-ZQBvi1DcpJ4GDqanjucZ2Hj3wEO5pZDS89BWbkcrvdxksJorwUDDZamX9ldFkp9aw2lmBDLgkObEA4DWNJ9FYQ==",
+      "license": "MIT"
+    },
     "node_modules/csstype": {
       "version": "3.2.3",
       "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.2.3.tgz",
@@ -2253,6 +2589,21 @@
       "integrity": "sha512-kRfgp8vWVjBu/fbYCiVFiOqsCk3CrMKEo3WbgGT2NXK2dG7vawWPBljixajVgGK9II8rDO9G0oD0zLt3I1daRg==",
       "license": "BSD-3-Clause"
     },
+    "node_modules/dingbat-to-unicode": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/dingbat-to-unicode/-/dingbat-to-unicode-1.0.1.tgz",
+      "integrity": "sha512-98l0sW87ZT58pU4i61wa2OHwxbiYSbuxsCBozaVnYX2iCnr3bLM3fIes1/ej7h1YdOKuKt/MLs706TVnALA65w==",
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/duck": {
+      "version": "0.1.12",
+      "resolved": "https://registry.npmjs.org/duck/-/duck-0.1.12.tgz",
+      "integrity": "sha512-wkctla1O6VfP89gQ+J/yDesM0S7B7XLXjKGzXxMDVFg7uEn706niAtyYovKbyq1oT9YwDcly721/iUWoc8MVRg==",
+      "license": "BSD",
+      "dependencies": {
+        "underscore": "^1.13.1"
+      }
+    },
     "node_modules/electron-to-chromium": {
       "version": "1.5.345",
       "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.345.tgz",
@@ -2777,6 +3128,18 @@
       ],
       "license": "BSD-3-Clause"
     },
+    "node_modules/immediate": {
+      "version": "3.0.6",
+      "resolved": "https://registry.npmjs.org/immediate/-/immediate-3.0.6.tgz",
+      "integrity": "sha512-XXOFtyqDjNDAQxVfYxuF7g9Il/IbWmmlQg2MYKOH8ExIT1qg6xc4zyS3HaEEATgs1btfzxq15ciUiY7gjSXRGQ==",
+      "license": "MIT"
+    },
+    "node_modules/inherits": {
+      "version": "2.0.4",
+      "resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz",
+      "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==",
+      "license": "ISC"
+    },
     "node_modules/ip-address": {
       "version": "10.1.1",
       "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.1.1.tgz",
@@ -2804,6 +3167,12 @@
         "node": ">=8"
       }
     },
+    "node_modules/isarray": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/isarray/-/isarray-1.0.0.tgz",
+      "integrity": "sha512-VLghIWNM6ELQzo7zwmcg0NmTVyWKYjvIeM83yjp0wRDTmUnrM678fQbcKBo6n2CJEF0szoG//ytg+TKla89ALQ==",
+      "license": "MIT"
+    },
     "node_modules/jose": {
       "version": "5.10.0",
       "resolved": "https://registry.npmjs.org/jose/-/jose-5.10.0.tgz",
@@ -2870,6 +3239,57 @@
         "node": ">=6"
       }
     },
+    "node_modules/jszip": {
+      "version": "3.10.1",
+      "resolved": "https://registry.npmjs.org/jszip/-/jszip-3.10.1.tgz",
+      "integrity": "sha512-xXDvecyTpGLrqFrvkrUSoxxfJI5AH7U8zxxtVclpsUtMCq4JQ290LY8AW5c7Ggnr/Y/oK+bQMbqK2qmtk3pN4g==",
+      "license": "(MIT OR GPL-3.0-or-later)",
+      "dependencies": {
+        "lie": "~3.3.0",
+        "pako": "~1.0.2",
+        "readable-stream": "~2.3.6",
+        "setimmediate": "^1.0.5"
+      }
+    },
+    "node_modules/jszip/node_modules/readable-stream": {
+      "version": "2.3.8",
+      "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-2.3.8.tgz",
+      "integrity": "sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA==",
+      "license": "MIT",
+      "dependencies": {
+        "core-util-is": "~1.0.0",
+        "inherits": "~2.0.3",
+        "isarray": "~1.0.0",
+        "process-nextick-args": "~2.0.0",
+        "safe-buffer": "~5.1.1",
+        "string_decoder": "~1.1.1",
+        "util-deprecate": "~1.0.1"
+      }
+    },
+    "node_modules/jszip/node_modules/safe-buffer": {
+      "version": "5.1.2",
+      "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.1.2.tgz",
+      "integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==",
+      "license": "MIT"
+    },
+    "node_modules/jszip/node_modules/string_decoder": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.1.1.tgz",
+      "integrity": "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg==",
+      "license": "MIT",
+      "dependencies": {
+        "safe-buffer": "~5.1.0"
+      }
+    },
+    "node_modules/lie": {
+      "version": "3.3.0",
+      "resolved": "https://registry.npmjs.org/lie/-/lie-3.3.0.tgz",
+      "integrity": "sha512-UaiMJzeWRlEujzAuw5LokY1L5ecNQYZKfmyZ9L7wDHb/p5etKaxXhohBcrw0EYby+G/NA52vRSN4N39dxHAIwQ==",
+      "license": "MIT",
+      "dependencies": {
+        "immediate": "~3.0.5"
+      }
+    },
     "node_modules/light-my-request": {
       "version": "5.14.0",
       "resolved": "https://registry.npmjs.org/light-my-request/-/light-my-request-5.14.0.tgz",
@@ -2893,6 +3313,17 @@
         "loose-envify": "cli.js"
       }
     },
+    "node_modules/lop": {
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/lop/-/lop-0.4.2.tgz",
+      "integrity": "sha512-RefILVDQ4DKoRZsJ4Pj22TxE3omDO47yFpkIBoDKzkqPRISs5U1cnAdg/5583YPkWPaLIYHOKRMQSvjFsO26cw==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "duck": "^0.1.12",
+        "option": "~0.2.1",
+        "underscore": "^1.13.1"
+      }
+    },
     "node_modules/lru-cache": {
       "version": "5.1.1",
       "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-5.1.1.tgz",
@@ -2903,6 +3334,30 @@
         "yallist": "^3.0.2"
       }
     },
+    "node_modules/mammoth": {
+      "version": "1.12.0",
+      "resolved": "https://registry.npmjs.org/mammoth/-/mammoth-1.12.0.tgz",
+      "integrity": "sha512-cwnK1RIcRdDMi2HRx2EXGYlxqIEh0Oo3bLhorgnsVJi2UkbX1+jKxuBNR9PC5+JaX7EkmJxFPmo6mjLpqShI2w==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "@xmldom/xmldom": "^0.8.6",
+        "argparse": "~1.0.3",
+        "base64-js": "^1.5.1",
+        "bluebird": "~3.4.0",
+        "dingbat-to-unicode": "^1.0.1",
+        "jszip": "^3.7.1",
+        "lop": "^0.4.2",
+        "path-is-absolute": "^1.0.0",
+        "underscore": "^1.13.1",
+        "xmlbuilder": "^10.0.0"
+      },
+      "bin": {
+        "mammoth": "bin/mammoth"
+      },
+      "engines": {
+        "node": ">=12.0.0"
+      }
+    },
     "node_modules/minimist": {
       "version": "1.2.8",
       "resolved": "https://registry.npmjs.org/minimist/-/minimist-1.2.8.tgz",
@@ -2969,6 +3424,15 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/node-tesseract-ocr": {
+      "version": "2.2.1",
+      "resolved": "https://registry.npmjs.org/node-tesseract-ocr/-/node-tesseract-ocr-2.2.1.tgz",
+      "integrity": "sha512-Q9cD79JGpPNQBxbi1fV+OAsTxYKLpx22sagsxSyKbu1u+t6UarApf5m32uVc8a5QAP1Wk7fIPN0aJFGGEE9DyQ==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=10"
+      }
+    },
     "node_modules/obliterator": {
       "version": "2.0.5",
       "resolved": "https://registry.npmjs.org/obliterator/-/obliterator-2.0.5.tgz",
@@ -2993,6 +3457,12 @@
         "wrappy": "1"
       }
     },
+    "node_modules/option": {
+      "version": "0.2.4",
+      "resolved": "https://registry.npmjs.org/option/-/option-0.2.4.tgz",
+      "integrity": "sha512-pkEqbDyl8ou5cpq+VsnQbe/WlEy5qS7xPzMS1U55OCG9KPvwFD46zDbxQIj3egJSFc3D+XhYOPUzz49zQAVy7A==",
+      "license": "BSD-2-Clause"
+    },
     "node_modules/pac-proxy-agent": {
       "version": "7.2.0",
       "resolved": "https://registry.npmjs.org/pac-proxy-agent/-/pac-proxy-agent-7.2.0.tgz",
@@ -3025,6 +3495,53 @@
         "node": ">= 14"
       }
     },
+    "node_modules/pako": {
+      "version": "1.0.11",
+      "resolved": "https://registry.npmjs.org/pako/-/pako-1.0.11.tgz",
+      "integrity": "sha512-4hLB8Py4zZce5s4yd9XzopqwVv/yGNhV1Bl8NTmCq1763HeK2+EwVTv+leGeL13Dnh2wfbqowVPXCIO0z4taYw==",
+      "license": "(MIT AND Zlib)"
+    },
+    "node_modules/path-is-absolute": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/path-is-absolute/-/path-is-absolute-1.0.1.tgz",
+      "integrity": "sha512-AVbw3UJ2e9bq64vSaS9Am0fje1Pa8pbGqTTsmXfaIiMpnr5DlDhfJOuLj9Sf95ZPVDAUerDfEk88MPmPe7UCQg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
+    "node_modules/pdf-parse": {
+      "version": "2.4.5",
+      "resolved": "https://registry.npmjs.org/pdf-parse/-/pdf-parse-2.4.5.tgz",
+      "integrity": "sha512-mHU89HGh7v+4u2ubfnevJ03lmPgQ5WU4CxAVmTSh/sxVTEDYd1er/dKS/A6vg77NX47KTEoihq8jZBLr8Cxuwg==",
+      "license": "Apache-2.0",
+      "dependencies": {
+        "@napi-rs/canvas": "0.1.80",
+        "pdfjs-dist": "5.4.296"
+      },
+      "bin": {
+        "pdf-parse": "bin/cli.mjs"
+      },
+      "engines": {
+        "node": ">=20.16.0 <21 || >=22.3.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/mehmet-kozan"
+      }
+    },
+    "node_modules/pdfjs-dist": {
+      "version": "5.4.296",
+      "resolved": "https://registry.npmjs.org/pdfjs-dist/-/pdfjs-dist-5.4.296.tgz",
+      "integrity": "sha512-DlOzet0HO7OEnmUmB6wWGJrrdvbyJKftI1bhMitK7O2N8W2gc757yyYBbINy9IDafXAV9wmKr9t7xsTaNKRG5Q==",
+      "license": "Apache-2.0",
+      "engines": {
+        "node": ">=20.16.0 || >=22.3.0"
+      },
+      "optionalDependencies": {
+        "@napi-rs/canvas": "^0.1.80"
+      }
+    },
     "node_modules/pend": {
       "version": "1.2.0",
       "resolved": "https://registry.npmjs.org/pend/-/pend-1.2.0.tgz",
@@ -3316,6 +3833,12 @@
         "node": ">= 0.6.0"
       }
     },
+    "node_modules/process-nextick-args": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/process-nextick-args/-/process-nextick-args-2.0.1.tgz",
+      "integrity": "sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag==",
+      "license": "MIT"
+    },
     "node_modules/process-warning": {
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/process-warning/-/process-warning-3.0.0.tgz",
@@ -3683,6 +4206,12 @@
       "integrity": "sha512-oeM1lpU/UvhTxw+g3cIfxXHyJRc/uidd3yK1P242gzHds0udQBYzs3y8j4gCCW+ZJ7ad0yctld8RYO+bdurlvw==",
       "license": "MIT"
     },
+    "node_modules/setimmediate": {
+      "version": "1.0.5",
+      "resolved": "https://registry.npmjs.org/setimmediate/-/setimmediate-1.0.5.tgz",
+      "integrity": "sha512-MATJdZp8sLqDl/68LfQmbP8zKPLQNV6BIZoIgrscFDQ+RsvK/BxeDQOgyxKKoh0y/8h3BqVFnCqQ/gd+reiIXA==",
+      "license": "MIT"
+    },
     "node_modules/shell-quote": {
       "version": "1.8.3",
       "resolved": "https://registry.npmjs.org/shell-quote/-/shell-quote-1.8.3.tgz",
@@ -3772,6 +4301,12 @@
         "node": ">= 10.x"
       }
     },
+    "node_modules/sprintf-js": {
+      "version": "1.0.3",
+      "resolved": "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.0.3.tgz",
+      "integrity": "sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g==",
+      "license": "BSD-3-Clause"
+    },
     "node_modules/streamx": {
       "version": "2.25.0",
       "resolved": "https://registry.npmjs.org/streamx/-/streamx-2.25.0.tgz",
@@ -3994,6 +4529,12 @@
         "node": ">=14.17"
       }
     },
+    "node_modules/underscore": {
+      "version": "1.13.8",
+      "resolved": "https://registry.npmjs.org/underscore/-/underscore-1.13.8.tgz",
+      "integrity": "sha512-DXtD3ZtEQzc7M8m4cXotyHR+FAS18C64asBYY5vqZexfYryNNnDc02W4hKg3rdQuqOYas1jkseX0+nZXjTXnvQ==",
+      "license": "MIT"
+    },
     "node_modules/undici-types": {
       "version": "6.21.0",
       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.21.0.tgz",
@@ -4032,6 +4573,12 @@
         "browserslist": ">= 4.21.0"
       }
     },
+    "node_modules/util-deprecate": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz",
+      "integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==",
+      "license": "MIT"
+    },
     "node_modules/vite": {
       "version": "5.4.21",
       "resolved": "https://registry.npmjs.org/vite/-/vite-5.4.21.tgz",
@@ -4572,6 +5119,15 @@
         }
       }
     },
+    "node_modules/xmlbuilder": {
+      "version": "10.1.1",
+      "resolved": "https://registry.npmjs.org/xmlbuilder/-/xmlbuilder-10.1.1.tgz",
+      "integrity": "sha512-OyzrcFLL/nb6fMGHbiRDuPup9ljBycsdCypwuyg5AAHvyWzGfChJpCXMG88AGTIMFhGZ9RccFN1e6lhg3hkwKg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=4.0"
+      }
+    },
     "node_modules/xtend": {
       "version": "4.0.2",
       "resolved": "https://registry.npmjs.org/xtend/-/xtend-4.0.2.tgz",