feat: add ai writing imitation mode

This commit is contained in:
董宏凯 committed 2026-07-01 11:21:41 +08:00
1 parent 9268c73776
commit bb6b9bd84b
22 files changed
+714 -30

No files matched your search

@@ -13,20 +13,30 @@ GET /api/ai-writing/article-types 列出所有文章类型
POST /api/ai-writing/article-types 新增文章类型
PATCH /api/ai-writing/article-types/{id} 更新文章类型
DELETE /api/ai-writing/article-types/{id} 删除文章类型
POST /api/ai-writing/sample/extract 提取样文仿写上传文件文本
POST /api/ai-writing/admin/cleanup (admin)手动清理会话
"""
from __future__ import annotations
import logging
import tempfile
from pathlib import Path
from typing import Optional
from fastapi import APIRouter, HTTPException, Request
from fastapi import APIRouter, File, HTTPException, Request, UploadFile
from pydantic import BaseModel, Field
from app.gateway.authz import require_auth
from deerflow.utils.file_conversion import CONVERTIBLE_EXTENSIONS, convert_file_to_markdown
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/api/ai-writing", tags=["ai-writing"])
_SAMPLE_TEXT_EXTENSIONS = {".txt", ".md", ".markdown"}
_MAX_SAMPLE_BYTES = 20 * 1024 * 1024
_MAX_SAMPLE_TEXT_CHARS = 120_000
# ── 请求/响应模型 ─────────────────────────────────────────────────────────────
class RenameSessionRequest(BaseModel):
@@ -67,6 +77,13 @@ class SaveTranscriptRequest(BaseModel):
transcript: dict
class SampleExtractResponse(BaseModel):
filename: str
text: str
char_count: int
truncated: bool = False
class ArticleTypeRequest(BaseModel):
key: str
label: str
@@ -154,6 +171,52 @@ class SessionResponse(BaseModel):
updated_at: str
async def _extract_sample_text(file: UploadFile) -> tuple[str, str]:
name = file.filename or "sample"
ext = Path(name).suffix.lower()
raw = await file.read()
if not raw:
raise HTTPException(status_code=400, detail="文件为空")
if len(raw) > _MAX_SAMPLE_BYTES:
raise HTTPException(status_code=413, detail=f"文件过大,最大支持 {_MAX_SAMPLE_BYTES // (1024 * 1024)}MB")
if ext in _SAMPLE_TEXT_EXTENSIONS:
text = raw.decode("utf-8", errors="ignore")
elif ext in CONVERTIBLE_EXTENSIONS:
with tempfile.TemporaryDirectory() as tmp:
tmp_path = Path(tmp) / f"sample{ext}"
tmp_path.write_bytes(raw)
md_path = await convert_file_to_markdown(tmp_path)
if md_path is None:
raise HTTPException(status_code=422, detail=f"无法解析文件:{name}")
text = md_path.read_text(encoding="utf-8", errors="ignore")
else:
raise HTTPException(status_code=415, detail=f"不支持的文件类型:{ext or '未知'}(支持 doc/docx/pdf/md/txt)")
text = text.strip()
if not text:
raise HTTPException(status_code=422, detail="文件内容为空或无法提取文本")
return name, text
@router.post("/sample/extract", response_model=SampleExtractResponse)
@require_auth
async def extract_sample_article(request: Request, file: UploadFile = File(...)) -> SampleExtractResponse:
"""Extract text from a sample article for AI-writing imitation mode."""
_ = request
name, text = await _extract_sample_text(file)
char_count = len(text)
truncated = char_count > _MAX_SAMPLE_TEXT_CHARS
if truncated:
text = text[:_MAX_SAMPLE_TEXT_CHARS]
return SampleExtractResponse(
filename=name,
text=text,
char_count=char_count,
truncated=truncated,
)
# ── 路由 ──────────────────────────────────────────────────────────────────────
@router.get("/sessions", response_model=list[SessionResponse])
async def list_sessions(request: Request):