WeaviateStore 集成

// 如果在本地运行，请包含端口，例如 "localhost:8080"
process.env.WEAVIATE_URL = "YOUR_WEAVIATE_URL";
// 可选，用于云部署
process.env.WEAVIATE_API_KEY = "YOUR_API_KEY";

process.env.OPENAI_API_KEY = "YOUR_API_KEY";

// process.env.LANGSMITH_TRACING="true"
// process.env.LANGSMITH_API_KEY="your-api-key"

import { WeaviateStore } from "@langchain/weaviate";
import { OpenAIEmbeddings } from "@langchain/openai";
import weaviate from "weaviate-client";

const embeddings = new OpenAIEmbeddings({
  model: "text-embedding-3-small",
});

const weaviateClient = weaviate.connectToWeaviateCloud({
   clusterURL: process.env.WEAVIATE_URL!,
  options : {
      authCredentials: new weaviate.ApiKey(process.env.WEAVIATE_API_KEY || ""),
      headers: {
        "X-OpenAI-Api-Key": process.env.OPENAI_API_KEY || "",
        "X-Cohere-Api-Key": process.env.COHERE_API_KEY || "",
      },
    },
});

const vectorStore = new WeaviateStore(embeddings, {
  client: weaviateClient,
  indexName: "Langchainjs_test",
});

const vectorStore = new WeaviateStore(embeddings, {
  client: weaviateClient,
  schema: {
    name: "Langchainjs_test",
    description: "A simple dataset",
    properties: [
      {
        name: "title",
        dataType: dataType.TEXT,
      },
      {
        name: "foo",
        dataType: dataType.TEXT,
      },
    ],
    vectorizers: [
      vectorizer.text2VecOpenAI({
        name: "title",
        sourceProperties: ["title"], // （可选）设置源属性
        // vectorIndexConfig: configure.vectorIndex.hnsw()   // （可选）设置向量索引配置
      }),
    ],
    generative: weaviate.configure.generative.openAI(),
    reranker: weaviate.configure.reranker.cohere(),
  },
});

import type { Document } from "@langchain/core/documents";
import { v4 as uuidv4 } from "uuid";

const document1: Document = {
  pageContent: "The powerhouse of the cell is the mitochondria",
  metadata: { source: "https://example.com" }
};

const document2: Document = {
  pageContent: "Buildings are made out of brick",
  metadata: { source: "https://example.com" }
};

const document3: Document = {
  pageContent: "Mitochondria are made out of lipids",
  metadata: { source: "https://example.com" }
};

const document4: Document = {
  pageContent: "The 2024 Olympics are in Paris",
  metadata: { source: "https://example.com" }
}

const documents = [document1, document2, document3, document4];
const uuids = [uuidv4(), uuidv4(), uuidv4(), uuidv4()];

await vectorStore.addDocuments(documents, { ids: uuids });

[
  '610f9b92-9bee-473f-a4db-8f2ca6e3442d',
  '995160fa-441e-41a0-b476-cf3785518a0d',
  '0cdbe6d4-0df8-4f99-9b67-184009fee9a2',
  '18a8211c-0649-467b-a7c5-50ebb4b9ca9d'
]

await vectorStore.delete({ ids: [uuids[3]] });

import { Filters } from "weaviate-client";

const collection = client.collections.use('Langchainjs_test');

const filter = Filters.and(collection.filter.byProperty("source").equal("https://example.com"))

const similaritySearchResults = await vectorStore.similaritySearch("biology", 2, filter);

for (const doc of similaritySearchResults) {
  console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}

* The powerhouse of the cell is the mitochondria [{"source":"https://example.com"}]
* Mitochondria are made out of lipids [{"source":"https://example.com"}]

const similaritySearchWithScoreResults = await vectorStore.similaritySearchWithScore("biology", 2, filter)

for (const [doc, score] of similaritySearchWithScoreResults) {
  console.log(`* [SIM=${score.toFixed(3)}] ${doc.pageContent} [${JSON.stringify(doc.metadata)}]`);
}

* [SIM=0.835] The powerhouse of the cell is the mitochondria [{"source":"https://example.com"}]
* [SIM=0.852] Mitochondria are made out of lipids [{"source":"https://example.com"}]

const results = await vectorStore.hybridSearch("biology",
  {
    limit: 1,
    alpha: 0.25,
    targetVector: ["title"],
    rerank: {
      property: "title",
      query: "greeting",
    },
});

const results = await vectorStore.generate("hello world",
    {
        singlePrompt: {
            prompt: "Translate this into German: {title}",
        },
        config: generativeParameters.openAI({
            model: "gpt-3.5-turbo",
        }),
    },
    {
        limit: 2,
        targetVector: ["title"],
    }
);

const retriever = vectorStore.asRetriever({
  // 可选过滤器
  filter: filter,
  k: 2,
});
await retriever.invoke("biology");

[
  Document {
    pageContent: 'The powerhouse of the cell is the mitochondria',
    metadata: { source: 'https://example.com' },
    id: undefined
  },
  Document {
    pageContent: 'Mitochondria are made out of lipids',
    metadata: { source: 'https://example.com' },
    id: undefined
  }
]