跳至主要内容

如何处理多个检索器

先决条件

本指南假定你熟悉以下内容

有时，查询分析技术可能允许选择要使用的检索器。要使用它，你需要添加一些逻辑来选择要执行的检索器。我们将展示一个简单的示例（使用模拟数据）来演示如何做到这一点。

设置​

安装依赖项​

提示

请参阅 本节，获取有关安装集成包的常规说明.

yarn add @langchain/community @langchain/openai @langchain/core zod chromadb

设置环境变量​

OPENAI_API_KEY=your-api-key

# Optional, use LangSmith for best-in-class observability
LANGSMITH_API_KEY=your-api-key
LANGCHAIN_TRACING_V2=true

# Reduce tracing latency if you are not in a serverless environment
# LANGCHAIN_CALLBACKS_BACKGROUND=true

创建索引​

我们将基于虚假信息创建向量存储。

import { Chroma } from "@langchain/community/vectorstores/chroma";
import { OpenAIEmbeddings } from "@langchain/openai";
import "chromadb";

const texts = ["Harrison worked at Kensho"];
const embeddings = new OpenAIEmbeddings({ model: "text-embedding-3-small" });
const vectorstore = await Chroma.fromTexts(texts, {}, embeddings, {
  collectionName: "harrison",
});
const retrieverHarrison = vectorstore.asRetriever(1);

const textsAnkush = ["Ankush worked at Facebook"];
const embeddingsAnkush = new OpenAIEmbeddings({
  model: "text-embedding-3-small",
});
const vectorstoreAnkush = await Chroma.fromTexts(
  textsAnkush,
  {},
  embeddingsAnkush,
  {
    collectionName: "ankush",
  }
);
const retrieverAnkush = vectorstoreAnkush.asRetriever(1);

查询分析​

我们将使用函数调用来构建输出。我们将让它返回多个查询。

import { z } from "zod";

const searchSchema = z.object({
  query: z.string().describe("Query to look up"),
  person: z
    .string()
    .describe(
      "Person to look things up for. Should be `HARRISON` or `ANKUSH`."
    ),
});

选择你的聊天模型

安装依赖项

提示

请参阅 本节，获取有关安装集成包的常规说明.

yarn add @langchain/openai

添加环境变量

OPENAI_API_KEY=your-api-key

实例化模型

import { ChatOpenAI } from "@langchain/openai";

const llm = new ChatOpenAI({
  model: "gpt-4o-mini",
  temperature: 0
});
import { ChatPromptTemplate } from "@langchain/core/prompts";
import {
  RunnableSequence,
  RunnablePassthrough,
} from "@langchain/core/runnables";

const system = `You have the ability to issue search queries to get information to help answer user information.`;
const prompt = ChatPromptTemplate.fromMessages([
  ["system", system],
  ["human", "{question}"],
]);
const llmWithTools = llm.withStructuredOutput(searchSchema, {
  name: "Search",
});
const queryAnalyzer = RunnableSequence.from([
  {
    question: new RunnablePassthrough(),
  },
  prompt,
  llmWithTools,
]);

我们可以看到这允许在检索器之间进行路由

await queryAnalyzer.invoke("where did Harrison Work");
{ query: "workplace of Harrison", person: "HARRISON" }
await queryAnalyzer.invoke("where did ankush Work");
{ query: "Workplace of Ankush", person: "ANKUSH" }

使用查询分析进行检索​

那么我们如何在链中包含它？我们只需要一些简单的逻辑来选择检索器并传入搜索查询

const retrievers = {
  HARRISON: retrieverHarrison,
  ANKUSH: retrieverAnkush,
};
import { RunnableConfig, RunnableLambda } from "@langchain/core/runnables";

const chain = async (question: string, config?: RunnableConfig) => {
  const response = await queryAnalyzer.invoke(question, config);
  const retriever = retrievers[response.person];
  return retriever.invoke(response.query, config);
};

const customChain = new RunnableLambda({ func: chain });
await customChain.invoke("where did Harrison Work");
[ Document { pageContent: "Harrison worked at Kensho", metadata: {} } ]
await customChain.invoke("where did ankush Work");
[ Document { pageContent: "Ankush worked at Facebook", metadata: {} } ]

下一步​

现在你已经学习了一些在查询分析系统中处理多个检索器的技巧。

接下来，查看本节中的一些其他查询分析指南，例如 如何处理没有生成查询的情况.

此页面对您有帮助吗？


你也可以在 GitHub 上留下详细的反馈 on GitHub.