Skip to main content

Convex

LangChain.js 支持 Convex 作为 向量存储，并支持标准的相似性搜索。

安装设置​

创建项目​

首先创建一个可用的 Convex 项目，例如使用以下命令：

npm create convex@latest

添加数据库访问器​

将查询和变更的辅助工具添加到 convex/langchain/db.ts 文件中：

convex/langchain/db.ts
export * from "@langchain/community/utils/convex";

配置你的数据库模式​

配置你的模式（用于向量索引）：

convex/schema.ts
import { defineSchema, defineTable } from "convex/server";
import { v } from "convex/values";

export default defineSchema({
  documents: defineTable({
    embedding: v.array(v.number()),
    text: v.string(),
    metadata: v.any(),
  }).vectorIndex("byEmbedding", {
    vectorField: "embedding",
    dimensions: 1536,
  }),
});

使用​

:::提示 请参阅安装集成包的一般说明部分。 :::

npm install @langchain/openai @langchain/community @langchain/core

数据导入​

convex/myActions.ts
"use node";

import { ConvexVectorStore } from "@langchain/community/vectorstores/convex";
import { OpenAIEmbeddings } from "@langchain/openai";
import { action } from "./_generated/server.js";

export const ingest = action({
  args: {},
  handler: async (ctx) => {
    await ConvexVectorStore.fromTexts(
      ["Hello world", "Bye bye", "What's this?"],
      [{ prop: 2 }, { prop: 1 }, { prop: 3 }],
      new OpenAIEmbeddings(),
      { ctx }
    );
  },
});

API Reference:

搜索​

convex/myActions.ts
"use node";

import { ConvexVectorStore } from "@langchain/community/vectorstores/convex";
import { OpenAIEmbeddings } from "@langchain/openai";
import { v } from "convex/values";
import { action } from "./_generated/server.js";

export const search = action({
  args: {
    query: v.string(),
  },
  handler: async (ctx, args) => {
    const vectorStore = new ConvexVectorStore(new OpenAIEmbeddings(), { ctx });

    const resultOne = await vectorStore.similaritySearch(args.query, 1);
    console.log(resultOne);
  },
});

API Reference:

相关内容​

Was this page helpful?


You can also leave detailed feedback on GitHub.