181 lines
5.9 KiB
Python
181 lines
5.9 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
"""
|
|||
|
|
Anchor Search Engine
|
|||
|
|
多维加权检索引擎。
|
|||
|
|
结合关键词匹配、情感共鸣、时间接近度、重要性进行排序。
|
|||
|
|
"""
|
|||
|
|
import os
|
|||
|
|
import math
|
|||
|
|
import yaml
|
|||
|
|
import json
|
|||
|
|
from datetime import datetime
|
|||
|
|
|
|||
|
|
VAULT_DIR = "/Users/fyah/Documents/如梦初醒/memory/test/Anchor-Memory"
|
|||
|
|
|
|||
|
|
# 检索权重配置
|
|||
|
|
W_TOPIC = 4.0 # 主题域/关键词权重
|
|||
|
|
W_EMOTION = 2.0 # 情感共鸣权重
|
|||
|
|
W_TIME = 1.5 # 时间接近度权重
|
|||
|
|
W_IMPORTANCE = 1.0 # 重要性权重
|
|||
|
|
MAX_RESULTS = 5 # 返回结果数量
|
|||
|
|
|
|||
|
|
def parse_yaml_frontmatter(content):
|
|||
|
|
"""极简 YAML 解析，兼容无 YAML 头的纯 Markdown"""
|
|||
|
|
if content.startswith("---"):
|
|||
|
|
parts = content.split("---", 2)
|
|||
|
|
if len(parts) >= 2:
|
|||
|
|
try:
|
|||
|
|
return yaml.safe_load(parts[1]), parts[2]
|
|||
|
|
except:
|
|||
|
|
pass
|
|||
|
|
# 如果没有 YAML 头，返回空字典和全文
|
|||
|
|
# 提取标题作为默认 title
|
|||
|
|
title = "Untitled"
|
|||
|
|
if content.startswith("# "):
|
|||
|
|
title = content.split("\n")[0][2:].strip()
|
|||
|
|
return {"title": title, "status": "active", "importance": 5}, content
|
|||
|
|
|
|||
|
|
def calc_keyword_score(query: str, metadata: dict, body: str) -> float:
|
|||
|
|
"""计算关键词匹配得分"""
|
|||
|
|
q_lower = query.lower()
|
|||
|
|
score = 0.0
|
|||
|
|
|
|||
|
|
# 标题匹配
|
|||
|
|
title = metadata.get("title", "").lower()
|
|||
|
|
if q_lower in title:
|
|||
|
|
score += 3.0
|
|||
|
|
|
|||
|
|
# 标签匹配
|
|||
|
|
tags = metadata.get("tags", [])
|
|||
|
|
if isinstance(tags, list):
|
|||
|
|
for tag in tags:
|
|||
|
|
if q_lower in tag.lower():
|
|||
|
|
score += 2.0
|
|||
|
|
|
|||
|
|
# 内容匹配
|
|||
|
|
body_lower = body.lower()
|
|||
|
|
if q_lower in body_lower:
|
|||
|
|
score += 1.0
|
|||
|
|
|
|||
|
|
# 模糊匹配（简单版：计算重叠词）
|
|||
|
|
query_words = set(q_lower.split())
|
|||
|
|
body_words = set(body_lower.split())
|
|||
|
|
overlap = len(query_words & body_words)
|
|||
|
|
if overlap > 0:
|
|||
|
|
score += overlap * 0.5
|
|||
|
|
|
|||
|
|
return score
|
|||
|
|
|
|||
|
|
def calc_emotion_score(query_emotion: dict, metadata: dict) -> float:
|
|||
|
|
"""计算情感共鸣得分（基于 Russell 环形模型距离）"""
|
|||
|
|
try:
|
|||
|
|
q_val = query_emotion.get("valence", 0.5)
|
|||
|
|
q_arousal = query_emotion.get("arousal", 0.3)
|
|||
|
|
|
|||
|
|
m_val = metadata.get("valence", 0.5)
|
|||
|
|
m_arousal = metadata.get("arousal", 0.3)
|
|||
|
|
|
|||
|
|
# 计算欧氏距离（归一化到 0~1，0 表示完全一致，1 表示完全相反）
|
|||
|
|
distance = math.sqrt((q_val - m_val)**2 + (q_arousal - m_arousal)**2)
|
|||
|
|
max_distance = math.sqrt(1.0**2 + 1.0**2) # 最大距离约 1.414
|
|||
|
|
|
|||
|
|
# 距离越近，得分越高
|
|||
|
|
return max(0.0, 1.0 - (distance / max_distance))
|
|||
|
|
except:
|
|||
|
|
return 0.0
|
|||
|
|
|
|||
|
|
def calc_time_score(metadata: dict) -> float:
|
|||
|
|
"""计算时间接近度得分（越近越好）"""
|
|||
|
|
try:
|
|||
|
|
date_str = metadata.get("date", "")
|
|||
|
|
mem_date = datetime.strptime(str(date_str), "%Y-%m-%d %H:%M")
|
|||
|
|
days_diff = (datetime.now() - mem_date).total_seconds() / 86400
|
|||
|
|
|
|||
|
|
# 指数衰减：越久远的记忆得分越低
|
|||
|
|
return math.exp(-0.1 * days_diff)
|
|||
|
|
except:
|
|||
|
|
return 0.0
|
|||
|
|
|
|||
|
|
def calc_importance_score(metadata: dict) -> float:
|
|||
|
|
"""计算重要性得分（归一化到 0~1）"""
|
|||
|
|
try:
|
|||
|
|
imp = metadata.get("importance", 5)
|
|||
|
|
return float(imp) / 10.0
|
|||
|
|
except:
|
|||
|
|
return 0.5
|
|||
|
|
|
|||
|
|
def search_memories(query: str, emotion_hint: dict = None):
|
|||
|
|
"""执行多维检索"""
|
|||
|
|
print(f"[*] 开始检索: '{query}'")
|
|||
|
|
results = []
|
|||
|
|
|
|||
|
|
# 遍历所有活跃记忆（跳过归档目录）
|
|||
|
|
for root, dirs, files in os.walk(VAULT_DIR):
|
|||
|
|
if "Archive" in root:
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
for file in files:
|
|||
|
|
if not file.endswith(".md"):
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
filepath = os.path.join(root, file)
|
|||
|
|
try:
|
|||
|
|
with open(filepath, "r", encoding="utf-8") as f:
|
|||
|
|
content = f.read()
|
|||
|
|
|
|||
|
|
metadata, body = parse_yaml_frontmatter(content)
|
|||
|
|
if not metadata or metadata.get("status") == "archived":
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 计算各维度得分
|
|||
|
|
k_score = calc_keyword_score(query, metadata, body)
|
|||
|
|
e_score = calc_emotion_score(emotion_hint or {}, metadata)
|
|||
|
|
t_score = calc_time_score(metadata)
|
|||
|
|
i_score = calc_importance_score(metadata)
|
|||
|
|
|
|||
|
|
# 加权总分
|
|||
|
|
total_score = (
|
|||
|
|
k_score * W_TOPIC +
|
|||
|
|
e_score * W_EMOTION +
|
|||
|
|
t_score * W_TIME +
|
|||
|
|
i_score * W_IMPORTANCE
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
if total_score > 0:
|
|||
|
|
results.append({
|
|||
|
|
"file": file,
|
|||
|
|
"path": os.path.relpath(filepath, VAULT_DIR),
|
|||
|
|
"title": metadata.get("title", "Untitled"),
|
|||
|
|
"score": total_score,
|
|||
|
|
"metadata": metadata,
|
|||
|
|
"preview": body[:200].strip()
|
|||
|
|
})
|
|||
|
|
except Exception as e:
|
|||
|
|
print(f" [!] 读取失败 {file}: {e}")
|
|||
|
|
|
|||
|
|
# 按得分排序
|
|||
|
|
results.sort(key=lambda x: x["score"], reverse=True)
|
|||
|
|
|
|||
|
|
# 返回 Top N
|
|||
|
|
top_results = results[:MAX_RESULTS]
|
|||
|
|
|
|||
|
|
if not top_results:
|
|||
|
|
print(f"[-] 未找到相关记忆。")
|
|||
|
|
return []
|
|||
|
|
|
|||
|
|
print(f"[+] 找到 {len(top_results)} 条相关记忆（Top {MAX_RESULTS}）：")
|
|||
|
|
for r in top_results:
|
|||
|
|
print(f"\n📄 {r['title']} (得分: {r['score']:.2f})")
|
|||
|
|
print(f"📍 {r['path']}")
|
|||
|
|
print(f"👁️ {r['preview']}...")
|
|||
|
|
|
|||
|
|
return top_results
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
import sys
|
|||
|
|
if len(sys.argv) > 1:
|
|||
|
|
query = " ".join(sys.argv[1:])
|
|||
|
|
search_memories(query)
|
|||
|
|
else:
|
|||
|
|
print("用法: python3 anchor_search.py <查询内容>")
|