How we build a Ritual Flow

CC0

Demo A 代表案例：科儀流程 + 法器 + 派別差異（三欄式：原文 / 派別差異 / 法器）。

科儀正一 vs 全真時間軸

🔒 重現條件鎖

MODEL    = "lius-cc/Daoism-Qwen3.5-9B"
DATASET  = "lius-cc/daoism-knowledge-rag@v1"
RAG_API  = "https://lius.cc/api/llm-rag"
SNAPSHOT = "2026-05-17"

雛形：儀式列表 + 派別並列

import requests

RITUALS = ["三朝醮", "發奏", "安胎祈嗣"]

for r_name in RITUALS:
    res = requests.post(
        "https://lius.cc/api/llm-rag",
        json={"q": f"{r_name} 流程", "n": 8, "types": ["ritual", "paper"]},
        timeout=10,
    )
    res.raise_for_status()
    r = res.json()
    rituals_hits = [h for h in r.get("hits", []) if h["type"] == "ritual"]
    print(f"\n=== {r_name} ===")
    for h in rituals_hits[:5]:
        print(f"  - {h['name']} (score {h['score']})")

# demo 將升級為：時間軸 + 法器卡 + 正一/全真並列 + 卷數頁碼

📜 本 recipe 採 CC0 1.0 · 改一行 prompt → 寫到論文裡 → 引用 LIUS API

引用建議：We use the open-source Daoism-Qwen3.5-9B with the public RAG API at https://lius.cc/api/llm-rag (Liu & Dingren Daoxue Lab, 2026).

← 回 Cookbook 索引