Apify 数据集集成

process.env.APIFY_TOKEN = "your-apify-token"

import { ApifyDatasetLoader } from "@langchain/community/document_loaders/web/apify_dataset";
import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
import { OpenAIEmbeddings, ChatOpenAI } from "@langchain/openai";
import { Document } from "@langchain/core/documents";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { createStuffDocumentsChain } from "@langchain/classic/chains/combine_documents";
import { createRetrievalChain } from "@langchain/classic/chains/retrieval";

const APIFY_TOKEN = "YOUR-APIFY-TOKEN"; // 或设置为 process.env.APIFY_TOKEN
const OPENAI_API_KEY = "YOUR-OPENAI-API-KEY"; // 或设置为 process.env.OPENAI_API_KEY

/*
 * datasetMappingFunction 是一个函数，用于将您的 Apify 数据集格式映射到 LangChain 文档。
 * 在下面的示例中，Apify 数据集格式如下所示：
 * {
 *   "url": "https://apify.com",
 *   "text": "Apify is the best web scraping and automation platform."
 * }
 */
const loader = await ApifyDatasetLoader.fromActorCall(
  "apify/website-content-crawler",
  {
    maxCrawlPages: 10,
    crawlerType: "cheerio",
    startUrls: [{ url: "https://js.langchain.com/docs/" }],
  },
  {
    datasetMappingFunction: (item) =>
      new Document({
        pageContent: (item.text || "") as string,
        metadata: { source: item.url },
      }),
    clientOptions: {
      token: APIFY_TOKEN,
    },
  }
);

const docs = await loader.load();

const vectorStore = await HNSWLib.fromDocuments(
  docs,
  new OpenAIEmbeddings({ apiKey: OPENAI_API_KEY })
);

const model = new ChatOpenAI({
  model: "gpt-5-mini",
  temperature: 0,
  apiKey: OPENAI_API_KEY,
});

const questionAnsweringPrompt = ChatPromptTemplate.fromMessages([
  [
    "system",
    "Answer the user's questions based on the below context:\n\n{context}",
  ],
  ["human", "{input}"],
]);

const combineDocsChain = await createStuffDocumentsChain({
  llm: model,
  prompt: questionAnsweringPrompt,
});

const chain = await createRetrievalChain({
  retriever: vectorStore.asRetriever(),
  combineDocsChain,
});

const res = await chain.invoke({ input: "What is LangChain?" });

console.log(res.answer);
console.log(res.context.map((doc) => doc.metadata.source));

/*
  LangChain is a framework for developing applications powered by language models.
  [
    'https://js.langchain.com/docs/',
    'https://js.langchain.com/docs/modules/chains/',
    'https://js.langchain.com/docs/modules/chains/llmchain/',
    'https://js.langchain.com/docs/category/functions-4'
  ]
*/

import { ApifyDatasetLoader } from "@langchain/community/document_loaders/web/apify_dataset";
import { HNSWLib } from "@langchain/community/vectorstores/hnswlib";
import { OpenAIEmbeddings, ChatOpenAI } from "@langchain/openai";
import { Document } from "@langchain/core/documents";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { createRetrievalChain } from "@langchain/classic/chains/retrieval";
import { createStuffDocumentsChain } from "@langchain/classic/chains/combine_documents";

const APIFY_TOKEN = "YOUR-APIFY-TOKEN"; // 或设置为 process.env.APIFY_TOKEN
const OPENAI_API_KEY = "YOUR-OPENAI-API-KEY"; // 或设置为 process.env.OPENAI_API_KEY

/*
 * datasetMappingFunction 是一个函数，用于将您的 Apify 数据集格式映射到 LangChain 文档。
 * 在下面的示例中，Apify 数据集格式如下所示：
 * {
 *   "url": "https://apify.com",
 *   "text": "Apify is the best web scraping and automation platform."
 * }
 */
const loader = new ApifyDatasetLoader("your-dataset-id", {
  datasetMappingFunction: (item) =>
    new Document({
      pageContent: (item.text || "") as string,
      metadata: { source: item.url },
    }),
  clientOptions: {
    token: APIFY_TOKEN,
  },
});

const docs = await loader.load();

const vectorStore = await HNSWLib.fromDocuments(
  docs,
  new OpenAIEmbeddings({ apiKey: OPENAI_API_KEY })
);

const model = new ChatOpenAI({
  model: "gpt-5-mini",
  temperature: 0,
  apiKey: OPENAI_API_KEY,
});

const questionAnsweringPrompt = ChatPromptTemplate.fromMessages([
  [
    "system",
    "Answer the user's questions based on the below context:\n\n{context}",
  ],
  ["human", "{input}"],
]);

const combineDocsChain = await createStuffDocumentsChain({
  llm: model,
  prompt: questionAnsweringPrompt,
});

const chain = await createRetrievalChain({
  retriever: vectorStore.asRetriever(),
  combineDocsChain,
});

const res = await chain.invoke({ input: "What is LangChain?" });

console.log(res.answer);
console.log(res.context.map((doc) => doc.metadata.source));

/*
  LangChain is a framework for developing applications powered by language models.
  [
    'https://js.langchain.com/docs/',
    'https://js.langchain.com/docs/modules/chains/',
    'https://js.langchain.com/docs/modules/chains/llmchain/',
    'https://js.langchain.com/docs/category/functions-4'
  ]
*/

import { ApifyDatasetLoader } from "@langchain/community/document_loaders/web/apify_dataset";
import { Document } from "@langchain/core/documents";

const docs = await ApifyDatasetLoader.fromActorCall(
  "apify/instagram-scraper",
  {
    directUrls: ["https://www.instagram.com/p/ABC123/"],
    resultsType: "posts",
    resultsLimit: 10,
  },
  {
    datasetMappingFunction: (item) =>
      new Document({
        pageContent: item.caption || "",
        metadata: {
          source: item.url,
          likesCount: item.likesCount,
          commentsCount: item.commentsCount,
        },
      }),
    clientOptions: { token: process.env.APIFY_TOKEN },
  }
);

import { ApifyDatasetLoader } from "@langchain/community/document_loaders/web/apify_dataset";
import { Document } from "@langchain/core/documents";

const searchDocs = await ApifyDatasetLoader.fromActorCall(
  "apify/google-search-scraper",
  {
    queries: "langchain javascript tutorial",
    maxPagesPerQuery: 1,
    countryCode: "us",
    languageCode: "en",
  },
  {
    datasetMappingFunction: (item) => {
      const organicResults = Array.isArray(item.organicResults)
        ? item.organicResults
        : [];

      const pageContent = organicResults
        .map(
          (r) =>
            `${r.position}. ${r.title}\n${r.url}\n${r.description ?? ""}`.trim()
        )
        .join("\n\n");

      return new Document({
        pageContent,
        metadata: {
          source: item.searchQuery?.url ?? item.url,
          query: item.searchQuery?.term,
          page: item.searchQuery?.page,
        },
      });
    },
    clientOptions: { token: process.env.APIFY_TOKEN },
  }
);

Authorization: Bearer <APIFY_TOKEN>