Rain-Bus
21f16e6756
- Split summarizer into summary_generator and summary_persister modules - Refactor pdf_image_extractor to two-phase pipeline with PicoDet layout detection - Add layout_detector service for PicoDet-S_layout_3cls integration - Add exceptions module with ConflictError and NotFoundError - Improve admin dashboard with better statistics and task management - Add design review document with system optimization suggestions - Add new tests for crawler, pdf_downloader, pipeline, and summary_utils - Update dependencies and configuration - Clean up dead code and improve error handling
54 lines
2.0 KiB
Bash
54 lines
2.0 KiB
Bash
# ─── 应用 ────────────────────────────────
|
|
APP_HOST=127.0.0.1
|
|
APP_PORT=8000
|
|
APP_DEBUG=false
|
|
BASE_URL=http://127.0.0.1:8000
|
|
APP_TIMEZONE=Asia/Shanghai
|
|
|
|
# ─── 安全 ────────────────────────────────
|
|
ADMIN_USERNAME=admin
|
|
ADMIN_PASSWORD=your_secure_password
|
|
SECRET_KEY=your_random_secret_key
|
|
|
|
# ─── HuggingFace / arXiv ────────────────
|
|
HF_API_BASE=https://huggingface.co/api
|
|
HF_PROXY=
|
|
TOP_N=20
|
|
HTTP_TIMEOUT_SECONDS=30
|
|
HTTP_MAX_RETRIES=3
|
|
HTTP_USER_AGENT=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36
|
|
|
|
# ─── AI 总结 ──────────────────────────────
|
|
# 总结后端：pi | claude
|
|
SUMMARY_BACKEND=pi
|
|
PI_BIN=
|
|
SUMMARY_SKILL=daily-paper-summary
|
|
CLAUDE_BIN=claude
|
|
SUMMARY_CONCURRENCY=3
|
|
SUMMARY_TIMEOUT_SECONDS=1200
|
|
SUMMARY_MAX_RETRIES=2
|
|
SUMMARY_PDF_MODE=auto
|
|
|
|
# ─── 调度 ─────────────────────────────────
|
|
SCHEDULER_ENABLED=false
|
|
SCHEDULE_HOUR=4
|
|
SCHEDULE_MINUTE=0
|
|
# 抓取时自动探测：先试今天，无数据则回退昨天（无需手动配置偏移）
|
|
APP_WORKERS=1
|
|
|
|
# ─── 数据库 ─────────────────────────────
|
|
DATABASE_URL=sqlite:///data/db/papers.db
|
|
|
|
# ─── 语义搜索 ─────────────────────────────
|
|
CHROMA_ENABLED=false
|
|
CHROMA_DIR=data/chroma
|
|
EMBED_API_BASE=https://api.siliconflow.cn/v1/embeddings
|
|
EMBED_API_KEY=your_api_key_here
|
|
EMBED_MODEL=Qwen/Qwen3-Embedding-4B
|
|
EMBED_DIMENSIONS=2560
|
|
|
|
# ─── 布局检测 ─────────────────────────────
|
|
# ONNX 模型路径（首次运行前执行 scripts/export_picodet_onnx.py 导出）
|
|
# LAYOUT_MODEL_PATH=data/models/picodet_layout_3cls.onnx
|
|
# LAYOUT_THRESHOLD=0.5
|