Back to Details

search-memory

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Search Memory

检索个人记忆

AI-powered semantic search across your personal knowledge base using Nowledge Mem.
基于Nowledge Mem的AI驱动语义检索，覆盖你的个人知识库。

When to Use

适用场景

Strong signals to search:
  • Continuity: Current topic connects to prior work
  • Pattern match: Problem resembles past solved issue
  • Decision context: "Why/how we chose X" implies documented rationale
  • Recurring theme: Topic discussed in past sessions
  • Implicit recall: "that approach", "like before"
Contextual signals:
  • Complex debugging (may match past root causes)
  • Architecture discussion (choices may be documented)
  • Domain-specific question (conventions likely stored)
Skip when:
  • Fundamentally new topic
  • Generic syntax questions
  • Fresh perspective explicitly requested
强烈建议检索的信号：
  • 连续性：当前主题与过往工作相关联
  • 模式匹配：当前问题与已解决的过往问题相似
  • 决策背景："我们为何/如何选择X"意味着存在记录的决策依据
  • 重复主题：过往会话中讨论过该主题
  • 隐含回忆："那种方法"、"和之前一样"
上下文信号：
  • 复杂调试（可能匹配过往的根本原因）
  • 架构讨论（相关选择可能已被记录）
  • 领域特定问题（相关惯例可能已存储）
无需检索的情况：
  • 全新主题
  • 通用语法问题
  • 明确要求提供全新视角

Prerequisites

前置条件

nmem CLI - Choose one option:
Option 1: uvx (Recommended)
bash
undefined
nmem CLI - 选择以下任一选项：
选项1：uvx（推荐）
bash
undefined

Install uv if needed

Install uv if needed

curl -LsSf https://astral.sh/uv/install.sh | sh
curl -LsSf https://astral.sh/uv/install.sh | sh

Run nmem directly (auto-downloads)

Run nmem directly (auto-downloads)

uvx --from nmem-cli nmem --version

**Option 2: pip**
```bash
pip install nmem-cli
nmem --version
Ensure Nowledge Mem server is running at 
http://localhost:14242
uvx --from nmem-cli nmem --version

**选项2：pip**
```bash
pip install nmem-cli
nmem --version
确保Nowledge Mem服务器运行在 
http://localhost:14242

Usage

使用方法

Use 
nmem
CLI with 
--json
flag for programmatic search:
bash
undefined
使用带
--json
参数的
nmem
CLI进行程序化检索：
bash
undefined

Basic search

Basic search

nmem --json m search "your query here"
nmem --json m search "your query here"

With importance filter

With importance filter

nmem --json m search "API design" --importance 0.8
nmem --json m search "API design" --importance 0.8

With labels (multiple labels use AND logic)

With labels (multiple labels use AND logic)

nmem --json m search "authentication" -l backend -l security
nmem --json m search "authentication" -l backend -l security

With time filter

With time filter

nmem --json m search "meeting notes" -t week
nmem --json m search "meeting notes" -t week

Limit results

Limit results

nmem --json m search "debugging tips" -n 5
undefined
nmem --json m search "debugging tips" -n 5
undefined

Query Guidelines

查询指南

  • Extract semantic core from user's request
  • Preserve domain terminology
  • Multi-language aware (works with any language)
  • Use 3-7 core concepts for best results
  • 从用户请求中提取语义核心
  • 保留领域术语
  • 支持多语言（适用于任意语言）
  • 使用3-7个核心概念以获得最佳结果

Available Filters

可用筛选器

FlagDescriptionExample
--importance MIN
Minimum importance (0.0-1.0)
--importance 0.7
-l, --label LABEL
Filter by label (repeatable)
-l frontend -l react
-t, --time RANGE
Time filter
-t today
, 
-t week
, 
-t month
-n NUM
Limit results
-n 5
参数描述示例
--importance MIN
最低重要性（0.0-1.0）
--importance 0.7
-l, --label LABEL
按标签筛选（可重复使用）
-l frontend -l react
-t, --time RANGE
时间筛选
-t today
, 
-t week
, 
-t month
-n NUM
限制结果数量
-n 5

Understanding Results

结果解读

Parse the 
memories
array from JSON response. Check 
score
field:
  • 0.6-1.0: Directly relevant - include in response
  • 0.3-0.6: Related context - may be useful
  • < 0.3: Skip - not relevant enough
解析JSON响应中的
memories
数组。查看
score
字段：
  • 0.6-1.0：直接相关 - 纳入回复
  • 0.3-0.6：相关上下文 - 可能有用
  • < 0.3：忽略 - 相关性不足

Response Guidelines

回复指南

Found relevant memories: Synthesize insights, cite when helpful
No results: State clearly, suggest distilling current discussion if valuable
找到相关记忆： 整合见解，必要时引用来源
无结果： 明确说明，若有价值可建议提炼当前讨论内容

Examples

示例

bash
undefined
bash
undefined

Search for React patterns

Search for React patterns

nmem --json m search "React hooks patterns" -l frontend
nmem --json m search "React hooks patterns" -l frontend

Find debugging solutions

Find debugging solutions

nmem --json m search "memory leak debugging" --importance 0.6
nmem --json m search "memory leak debugging" --importance 0.6

Recent project decisions

Recent project decisions

nmem --json m search "architecture decision" -t month -n 10
undefined
nmem --json m search "architecture decision" -t month -n 10
undefined

Links

链接