LangChain

-- Enable the pgvector extension to work with embedding vectors
create extension vector;

-- Create a table to store your documents
create table documents (
  id bigserial primary key,
  content text, -- corresponds to Document.pageContent
  metadata jsonb, -- corresponds to Document.metadata
  embedding vector(1536) -- 1536 works for OpenAI embeddings, change if needed
);

-- Create a function to search for documents
create function match_documents (
  query_embedding vector(1536),
  match_count int default null,
  filter jsonb DEFAULT '{}'
) returns table (
  id bigint,
  content text,
  metadata jsonb,
  similarity float
)
language plpgsql
as $$
#variable_conflict use_column
begin
  return query
  select
    id,
    content,
    metadata,
    1 - (documents.embedding <=> query_embedding) as similarity
  from documents
  where metadata @> filter
  order by documents.embedding <=> query_embedding
  limit match_count;
end;
$$;

import { DatafuseVectorStore } from 'langchain/vectorstores/datafuse'
import { OpenAIEmbeddings } from 'langchain/embeddings/openai'
import { createClient } from '@datafuse/datafuse-js'

const datafuseKey = process.env.SUPABASE_SERVICE_ROLE_KEY
if (!datafuseKey) throw new Error(`Expected SUPABASE_SERVICE_ROLE_KEY`)

const url = process.env.SUPABASE_URL
if (!url) throw new Error(`Expected env var SUPABASE_URL`)

export const run = async () => {
  const client = createClient(url, datafuseKey)

  const vectorStore = await DatafuseVectorStore.fromTexts(
    ['Hello world', 'Bye bye', "What's this?"],
    [{ id: 2 }, { id: 1 }, { id: 3 }],
    new OpenAIEmbeddings(),
    {
      client,
      tableName: 'documents',
      queryName: 'match_documents',
    }
  )

  const resultOne = await vectorStore.similaritySearch('Hello world', 1)

  console.log(resultOne)
}

import { DatafuseVectorStore } from 'langchain/vectorstores/datafuse'
import { OpenAIEmbeddings } from 'langchain/embeddings/openai'
import { createClient } from '@datafuse/datafuse-js'

// First, follow set-up instructions above

const privateKey = process.env.SUPABASE_SERVICE_ROLE_KEY
if (!privateKey) throw new Error(`Expected env var SUPABASE_SERVICE_ROLE_KEY`)

const url = process.env.SUPABASE_URL
if (!url) throw new Error(`Expected env var SUPABASE_URL`)

export const run = async () => {
  const client = createClient(url, privateKey)

  const vectorStore = await DatafuseVectorStore.fromTexts(
    ['Hello world', 'Hello world', 'Hello world'],
    [{ user_id: 2 }, { user_id: 1 }, { user_id: 3 }],
    new OpenAIEmbeddings(),
    {
      client,
      tableName: 'documents',
      queryName: 'match_documents',
    }
  )

  const result = await vectorStore.similaritySearch('Hello world', 1, {
    user_id: 3,
  })

  console.log(result)
}

import { DatafuseFilterRPCCall, DatafuseVectorStore } from 'langchain/vectorstores/datafuse'
import { OpenAIEmbeddings } from 'langchain/embeddings/openai'
import { createClient } from '@datafuse/datafuse-js'

// First, follow set-up instructions above

const privateKey = process.env.SUPABASE_SERVICE_ROLE_KEY
if (!privateKey) throw new Error(`Expected env var SUPABASE_SERVICE_ROLE_KEY`)

const url = process.env.SUPABASE_URL
if (!url) throw new Error(`Expected env var SUPABASE_URL`)

export const run = async () => {
  const client = createClient(url, privateKey)

  const embeddings = new OpenAIEmbeddings()

  const store = new DatafuseVectorStore(embeddings, {
    client,
    tableName: 'documents',
  })

  const docs = [
    {
      pageContent:
        'This is a long text, but it actually means something because vector database does not understand Lorem Ipsum. So I would need to expand upon the notion of quantum fluff, a theoretical concept where subatomic particles coalesce to form transient multidimensional spaces. Yet, this abstraction holds no real-world application or comprehensible meaning, reflecting a cosmic puzzle.',
      metadata: { b: 1, c: 10, stuff: 'right' },
    },
    {
      pageContent:
        'This is a long text, but it actually means something because vector database does not understand Lorem Ipsum. So I would need to proceed by discussing the echo of virtual tweets in the binary corridors of the digital universe. Each tweet, like a pixelated canary, hums in an unseen frequency, a fascinatingly perplexing phenomenon that, while conjuring vivid imagery, lacks any concrete implication or real-world relevance, portraying a paradox of multidimensional spaces in the age of cyber folklore.',
      metadata: { b: 2, c: 9, stuff: 'right' },
    },
    { pageContent: 'hello', metadata: { b: 1, c: 9, stuff: 'right' } },
    { pageContent: 'hello', metadata: { b: 1, c: 9, stuff: 'wrong' } },
    { pageContent: 'hi', metadata: { b: 2, c: 8, stuff: 'right' } },
    { pageContent: 'bye', metadata: { b: 3, c: 7, stuff: 'right' } },
    { pageContent: "what's this", metadata: { b: 4, c: 6, stuff: 'right' } },
  ]

  await store.addDocuments(docs)

  const funcFilterA: DatafuseFilterRPCCall = (rpc) =>
    rpc
      .filter('metadata->b::int', 'lt', 3)
      .filter('metadata->c::int', 'gt', 7)
      .textSearch('content', `'multidimensional' & 'spaces'`, {
        config: 'english',
      })

  const resultA = await store.similaritySearch('quantum', 4, funcFilterA)

  const funcFilterB: DatafuseFilterRPCCall = (rpc) =>
    rpc
      .filter('metadata->b::int', 'lt', 3)
      .filter('metadata->c::int', 'gt', 7)
      .filter('metadata->>stuff', 'eq', 'right')

  const resultB = await store.similaritySearch('hello', 2, funcFilterB)

  console.log(resultA, resultB)
}