20260625:很多新内容
This commit is contained in:
45
concepts/context-enriched-embeddings.md
Normal file
45
concepts/context-enriched-embeddings.md
Normal file
@@ -0,0 +1,45 @@
|
||||
---
|
||||
title: "上下文增强嵌入 — Context Enriched Embeddings"
|
||||
created: 2026-06-19
|
||||
updated: 2026-06-19
|
||||
type: concept
|
||||
tags: [embeddings, context-enrichment, vector-retrieval, tool-discovery]
|
||||
sources:
|
||||
- https://arxiv.org/abs/2509.20386
|
||||
---
|
||||
|
||||
# 上下文增强嵌入(Context Enriched Embeddings)
|
||||
|
||||
## 定义
|
||||
|
||||
Dynamic ReAct 论文中的关键向量检索优化策略:使用 LLM(Sonnet 4)**程序化增强工具描述**——生成隐式功能和用例描述——再嵌入。将 Top-5 检索准确率从 40% 提升至 60%(+50% 相对提升)。
|
||||
|
||||
## 为什么需要增强
|
||||
|
||||
工具文档通常只描述**显式功能**(参数、返回类型),缺少:
|
||||
- 隐式功能("send email" 暗示需要 SMTP 能力)
|
||||
- 用例上下文(什么场景下用这个工具)
|
||||
- 工具间的关系(这个工具通常和哪些工具配合)
|
||||
|
||||
## 实验数据
|
||||
|
||||
| 策略 | Top-5 | Top-10 |
|
||||
|------|-------|--------|
|
||||
| OpenAI text-embedding-3-large (baseline) | 40% | 64% |
|
||||
| voyage-context-3 | 48% | 68% |
|
||||
| **voyage-context-3 + Sonnet context enrichment** | **60%** | 68% |
|
||||
| + BM25 hybrid | 56% | 72% |
|
||||
|
||||
Sonnet 增强带来 **+12pp**(vs voyage-context-3 alone)。BM25 混合提升 recall(+4pp Top-10)但降 precision(-4pp Top-5),因为关键词重叠引入误匹配。
|
||||
|
||||
## 实际案例
|
||||
|
||||
查询 "send email":
|
||||
- Baseline(OpenAI):resend__send_email #4,google_mail__send_email #6,outlook__send_mail 未进 Top-10
|
||||
- Optimized(Voyage + Context):outlook__send_mail #1,google_mail__send_email #2,resend__send_email #4 ——三个期望工具全进 Top-5
|
||||
|
||||
## 参考
|
||||
|
||||
- [[dynamic-react|Dynamic ReAct]]
|
||||
- [[gaurav-dynamic-react-2025|论文]]
|
||||
- [[search-and-load|Search and Load]]
|
||||
Reference in New Issue
Block a user