Skip to main content
LangChain.js supports Convex as a vector store, and supports the standard similarity search.

​
Setup

​
Create project

Get a working Convex project set up, for example by using: 
npm create convex@latest

​
Add database accessors

Add query and mutation helpers to convex/langchain/db.ts:
convex/langchain/db.ts
export * from "@langchain/community/utils/convex";

​
Configure your schema

Set up your schema (for vector indexing):
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,
  }),
});

​
Usage

See this section for general instructions on installing LangChain packages.
npm
npm install @langchain/openai @langchain/community @langchain/core

​
Ingestion

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 }
    );
  },
});

"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);
  },
});
Edit the source of this page on GitHub
⌘I