simon
9aa44e610d
- system.yaml: llm.max_retries(死配置) 改为 llm.max_attempts；embedding 段新增 max_attempts - llm/client.py: LLMConfig 新增 max_attempts（默认 3 兜底），load_llm_config 读取配置 - llm/extractor.py: translate_and_extract(_async) max_attempts=None 时取 config.max_attempts - embedding/client.py: load_embedding_config 读取 embedding.max_attempts - scheduler/reporter.py: _call_llm_simple max_retries=None 时取 max_attempts-1 - 新增 2 个配置读取测试；已同步 pi5 验证
93 lines
4.3 KiB
YAML
93 lines
4.3 KiB
YAML
# ════════════════════════════════════════════════════
|
||
# 系统功能配置（非敏感）
|
||
# 密钥、API 地址 请在 .env 中配置
|
||
# ════════════════════════════════════════════════════
|
||
|
||
# ── 部署拓扑 ────────────────────────────────────────
|
||
# 海外服务器已弃用（M1-M6 全链路在 domestic 执行）
|
||
servers:
|
||
overseas_host: "ecs-user@8.217.19.253"
|
||
overseas_path: "/opt/intlgrab"
|
||
domestic_host: "pi@192.168.1.160"
|
||
domestic_path: "/home/pi/intlnews"
|
||
|
||
# ── HTTP 代理（Privoxy → ss-local → Shadowsocks 海外访问）──
|
||
proxy:
|
||
enabled: false # 通过 Profile 8g_headful 启用
|
||
url: "http://127.0.0.1:3128" # HTTP 代理地址
|
||
bypass_domains: [] # 不走代理的域名（如国内 CDN）
|
||
|
||
# ── 抓取 ────────────────────────────────────────────
|
||
crawler:
|
||
max_memory_mb: 1800 # 内存上限 MB（超限触发 GC）
|
||
source_timeout_sec: 7200 # 单源超时秒数（2h）
|
||
article_delay_sec: 3.0 # 文章间冷却间隔
|
||
page_timeout_sec: 45 # 单页加载超时
|
||
viewport_width: 1024
|
||
viewport_height: 768
|
||
user_agent: "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
|
||
headful: false # true=有头浏览器（需 X Server 或 xvfb），false=headless
|
||
xvfb_display: ":99" # headful 模式下的虚拟显示器（xvfb-run 自动设置）
|
||
|
||
# ── 正文提取 ──────────────────────────────────────────
|
||
extractor:
|
||
min_content_words: 50
|
||
trafilatura_fallback: true
|
||
|
||
# ── 去重 ────────────────────────────────────────────
|
||
dedup:
|
||
hamming_distance_threshold: 3
|
||
simhash_window_days: 30
|
||
min_content_length: 100
|
||
|
||
# ── LLM 翻译+事件抽取 ────────────────────────────────
|
||
llm:
|
||
provider: "deepseek"
|
||
deepseek_model: "deepseek-v4-flash"
|
||
qwen_model: "qwen-plus"
|
||
timeout_sec: 60
|
||
max_attempts: 3 # 单篇总尝试次数（含首次），失败后指数退避重试；日报 AI 摘要同用此值
|
||
max_tokens: 8192
|
||
temperature: 0.1
|
||
concurrency: 3
|
||
|
||
# ── Embedding 向量化 ────────────────────────────────
|
||
embedding:
|
||
provider: "dashscope"
|
||
dashscope_model: "text-embedding-v3"
|
||
dimension: 1024
|
||
batch_size: 10
|
||
max_attempts: 3 # 单批总尝试次数（含首次），失败后指数退避重试
|
||
timeout_sec: 30
|
||
|
||
# ── Qdrant ──────────────────────────────────────────
|
||
qdrant:
|
||
collection: "en_finance_news"
|
||
|
||
# ── 日报 ────────────────────────────────────────────
|
||
report:
|
||
max_events: 20
|
||
summary_max_chars: 500
|
||
importance_threshold: 4
|
||
upload_host: "simon@doorcome.cn"
|
||
upload_path: "/var/www/html/echart/research"
|
||
|
||
# ── 同步 (rsync) ─────────────────────────────────────
|
||
# 海外服务器已弃用，以下保留作为参考
|
||
sync:
|
||
port: 22
|
||
sentinel: "/tmp/en_news_sync_done"
|
||
pack_dir: "/tmp"
|
||
|
||
# ── 定时调度 ────────────────────────────────────────
|
||
# 全流程：M1 抓取 → M2→M6 管道 → 日报
|
||
# 每天 06:00 / 12:00 / 18:00 / 22:00 各执行一次
|
||
schedule:
|
||
day_cutoff_hour: 6
|
||
times: ["06:00", "12:00", "18:00", "22:00"]
|
||
|
||
# ── 日志 ────────────────────────────────────────────
|
||
logging:
|
||
level: "INFO"
|
||
dir: "logs"
|