Back to Details

vector-memory

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Vector Memory Skill

Vector Memory Skill

This skill provides vector-based semantic memory storage using embeddings for intelligent recall by meaning.
该技能通过嵌入技术提供基于向量的语义记忆存储，实现基于语义的智能召回。

When to Use

适用场景

  • You need semantic search (find memories by meaning, not keywords)
  • You want to retrieve similar documents or conversations
  • You're building an agent that needs context-aware memory
  • You need to cluster or group related memories
  • 需要语义搜索（按语义而非关键词查找记忆）
  • 希望检索相似文档或对话
  • 正在构建具备上下文感知记忆的Agent
  • 需要对相关记忆进行聚类或分组

Capabilities

功能特性

  • vstore: Store text with automatic embedding generation
  • vsearch: Search memories by semantic similarity
  • vdelete: Remove a memory by ID
  • vlist: List all stored memories
  • vsimilar: Find memories similar to a given ID
  • vclear: Clear all memories
  • vstore：存储文本并自动生成嵌入向量
  • vsearch：按语义相似度搜索记忆
  • vdelete：通过ID删除记忆
  • vlist：列出所有已存储的记忆
  • vsimilar：查找与指定ID相似的记忆
  • vclear：清空所有记忆

How It Works

工作原理

  1. Text is converted to embeddings using OpenAI's API
  2. Embeddings are stored in JSON with metadata
  3. Search uses cosine similarity to find semantically related memories
  4. No external vector database required - pure JSON storage
  1. 通过OpenAI API将文本转换为嵌入向量
  2. 嵌入向量与元数据一起存储在JSON中
  3. 搜索通过余弦相似度查找语义相关的记忆
  4. 无需外部向量数据库，采用纯JSON存储

Environment Variables

环境变量

Required:
  • OPENAI_API_KEY
    - For generating embeddings
Optional:
  • VECTOR_MEMORY_DIM
    - Embedding dimensions (default: 1536 for text-embedding-ada-002)
必填项：
  • OPENAI_API_KEY
    - 用于生成嵌入向量
可选项：
  • VECTOR_MEMORY_DIM
    - 嵌入向量维度（默认：text-embedding-ada-002模型为1536）

Usage Examples

使用示例

javascript
// Store a memory with semantic embedding
vstore('Meeting notes: Discussed Q1 roadmap and budget allocation')
// Returns: "Stored memory with ID: mem_abc123"

// Search by meaning (not keywords)
vsearch('What did we talk about regarding money?')
// Returns: Memories about budget, funding, financial discussions

// Find similar memories
vsimilar('mem_abc123')
// Returns: Semantically similar memories

// List all memories
vlist()
// Returns: List of stored memories with metadata

// Clear all
vclear()
// Returns: "Cleared all vector memories"
javascript
// 存储带有语义嵌入的记忆
vstore('Meeting notes: Discussed Q1 roadmap and budget allocation')
// 返回："已存储记忆，ID: mem_abc123"

// 按语义搜索（而非关键词）
vsearch('What did we talk about regarding money?')
// 返回：与预算、资金、财务讨论相关的记忆

// 查找相似记忆
vsimilar('mem_abc123')
// 返回：语义相似的记忆

// 列出所有记忆
vlist()
// 返回：包含元数据的已存储记忆列表

// 清空所有记忆
vclear()
// 返回："已清空所有向量记忆"

Features

特性

  • Semantic search:Find by meaning, not keywords
  • Similarity scoring: Results ranked by relevance score
  • Automatic embeddings: No manual vector generation needed
  • Metadata support: Store timestamps and tags with memories
  • Pure JSON: No external database dependencies
  • 语义搜索：按语义而非关键词查找
  • 相似度评分：结果按相关度评分排序
  • 自动嵌入：无需手动生成向量
  • 元数据支持：可随记忆存储时间戳和标签
  • 纯JSON存储：无外部数据库依赖