Skip to main content

如何处理多个检索器

预备知识

本指南假定您熟悉以下内容：

有时，查询分析技术可能会允许选择使用哪个检索器。要使用此功能，您需要添加一些逻辑来选择要使用的检索器。我们将展示一个简单的示例（使用模拟数据），说明如何实现这一点。

安裝​

安裝依賴項​

:::提示 请参阅安装集成包的一般说明部分。 :::

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

設定環境變數​

OPENAI_API_KEY=your-api-key

# 選用，使用 LangSmith 以獲得最佳的可觀測性
LANGSMITH_API_KEY=your-api-key
LANGSMITH_TRACING=true

# 如果你不在無伺服器環境中，可減少追蹤延遲
# LANGCHAIN_CALLBACKS_BACKGROUND=true

创建索引​

我们将在虚假信息上创建一个向量存储。

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结构化输出。我们会让其返回多个查询。

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`."
    ),
});

Pick your chat model:

Install dependencies

tip

See this section for general instructions on installing integration packages.

yarn add @langchain/groq

Add environment variables

GROQ_API_KEY=your-api-key

Instantiate the model

import { ChatGroq } from "@langchain/groq";

const llm = new ChatGroq({
  model: "llama-3.3-70b-versatile",
  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这一点呢？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​

你现在已经了解了一些在查询分析系统中处理多个检索器的技术。

接下来，查看本节中其他一些查询分析指南，例如如何处理未生成查询的情况。

Was this page helpful?


You can also leave detailed feedback on GitHub.