> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.
# 嵌入模型集成
> 使用 LangChain JavaScript 集成嵌入模型。
## 概述
本概述涵盖**基于文本的嵌入模型**。LangChain 目前暂不支持多模态嵌入。
嵌入模型将原始文本（如句子、段落或推文）转换为固定长度的数字向量，以捕捉其**语义含义**。这些向量使机器能够基于含义而非精确词汇来比较和搜索文本。
在实践中，这意味着具有相似思想的文本在向量空间中会被放置得很近。例如，嵌入不仅可以匹配短语 *"机器学习"*，还能检索出讨论相关概念的文档，即使使用了不同的措辞。
### 工作原理
1. **向量化** — 模型将每个输入字符串编码为一个高维向量。
2. **相似度评分** — 使用数学度量来比较向量，以衡量底层文本的关联程度。
### 相似度度量
比较嵌入时常用的几种度量方法：
* **余弦相似度** — 测量两个向量之间的夹角。
* **欧几里得距离** — 测量点之间的直线距离。
* **点积** — 测量一个向量在另一个向量上的投影量。
## 接口
LangChain 通过 [Embeddings](https://reference.langchain.com/javascript/langchain-core/embeddings/Embeddings) 接口为文本嵌入模型（例如 OpenAI、Cohere、Hugging Face）提供了标准接口。
提供两个主要方法：
* `embedDocuments(documents: string[]) → number[][]`：嵌入文档列表。
* `embedQuery(text: string) → number[]`：嵌入单个查询。
该接口允许查询和文档使用不同的策略进行嵌入，尽管在实践中大多数提供商会以相同的方式处理它们。
## 安装与使用
安装依赖项：
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm i @langchain/openai
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/openai
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/openai
```
添加环境变量：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
OPENAI_API_KEY=your-api-key
```
实例化模型：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { OpenAIEmbeddings } from "@langchain/openai";
const embeddings = new OpenAIEmbeddings({
model: "text-embedding-3-large"
});
```
安装依赖项
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm i @langchain/openai
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/openai
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/openai
```
添加环境变量：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
AZURE_OPENAI_API_INSTANCE_NAME=
AZURE_OPENAI_API_KEY=
AZURE_OPENAI_API_VERSION="2024-02-01"
```
实例化模型：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { AzureOpenAIEmbeddings } from "@langchain/openai";
const embeddings = new AzureOpenAIEmbeddings({
azureOpenAIApiEmbeddingsDeploymentName: "text-embedding-ada-002"
});
```
安装依赖项：
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm i @langchain/aws
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/aws
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/aws
```
添加环境变量：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
BEDROCK_AWS_REGION=your-region
```
实例化模型：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { BedrockEmbeddings } from "@langchain/aws";
const embeddings = new BedrockEmbeddings({
model: "amazon.titan-embed-text-v1"
});
```
安装依赖项：
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm i @langchain/google-genai
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/google-genai
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/google-genai
```
添加环境变量：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
GOOGLE_API_KEY=your-api-key
```
实例化模型：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { GoogleGenerativeAIEmbeddings } from "@langchain/google-genai";
const embeddings = new GoogleGenerativeAIEmbeddings({
model: "text-embedding-004"
});
```
安装依赖项：
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm i @langchain/google-vertexai
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/google-vertexai
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/google-vertexai
```
添加环境变量：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
GOOGLE_APPLICATION_CREDENTIALS=credentials.json
```
实例化模型：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { VertexAIEmbeddings } from "@langchain/google-vertexai";
const embeddings = new VertexAIEmbeddings({
model: "gemini-embedding-001"
});
```
安装依赖项：
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm i @langchain/mistralai
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/mistralai
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/mistralai
```
添加环境变量：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
MISTRAL_API_KEY=your-api-key
```
实例化模型：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { MistralAIEmbeddings } from "@langchain/mistralai";
const embeddings = new MistralAIEmbeddings({
model: "mistral-embed"
});
```
安装依赖项：
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm i @langchain/cohere
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/cohere
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/cohere
```
添加环境变量：
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
COHERE_API_KEY=your-api-key
```
实例化模型：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { CohereEmbeddings } from "@langchain/cohere";
const embeddings = new CohereEmbeddings({
model: "embed-english-v3.0"
});
```
安装依赖项：
```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm i @langchain/ollama
```
```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
yarn add @langchain/ollama
```
```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
pnpm add @langchain/ollama
```
实例化模型：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { OllamaEmbeddings } from "@langchain/ollama";
const embeddings = new OllamaEmbeddings({
model: "llama2",
baseUrl: "http://localhost:11434", // 默认值
});
```
## 缓存
嵌入可以被存储或临时缓存，以避免重复计算。
可以使用 `CacheBackedEmbeddings` 来缓存嵌入。这个包装器将嵌入存储在键值存储中，其中文本被哈希处理，哈希值用作缓存中的键。
初始化 `CacheBackedEmbeddings` 的主要支持方式是 `fromBytesStore`。它接受以下参数：
* **underlyingEmbeddings**：用于嵌入的嵌入器。
* **documentEmbeddingStore**：用于缓存文档嵌入的任何 [`BaseStore`](/oss/javascript/integrations/stores/)。
* **options.namespace**：（可选，默认为 `""`）用于文档缓存的命名空间。有助于避免冲突（例如，将其设置为嵌入模型名称）。
- 使用不同的嵌入模型时，请始终设置 `namespace` 参数以避免冲突。
- `CacheBackedEmbeddings` 默认不缓存查询嵌入。要启用此功能，请指定一个 `query_embedding_store`。
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { CacheBackedEmbeddings } from "@langchain/classic/embeddings/cache_backed";
import { InMemoryStore } from "@langchain/core/stores";
const underlyingEmbeddings = new OpenAIEmbeddings();
const inMemoryStore = new InMemoryStore();
const cacheBackedEmbeddings = CacheBackedEmbeddings.fromBytesStore(
underlyingEmbeddings,
inMemoryStore,
{
namespace: underlyingEmbeddings.model,
}
);
// 示例：缓存查询嵌入
const tic = Date.now();
const queryEmbedding = cacheBackedEmbeddings.embedQuery("Hello, world!");
console.log(`首次调用耗时：${Date.now() - tic}ms`);
// 示例：缓存文档嵌入
const tic = Date.now();
const documentEmbedding = cacheBackedEmbeddings.embedDocuments(["Hello, world!"]);
console.log(`缓存创建时间：${Date.now() - tic}ms`);
```
在生产环境中，通常会使用更健壮的持久化存储，例如数据库或云存储。请参阅[存储集成](/oss/javascript/integrations/stores/)了解相关选项。
## 所有集成
***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\javascript\integrations\embeddings\index.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.