import { MongoClient } from 'mongodb';

const client = new MongoClient(process.env.MONGODB_URI);
await client.connect();

const collection = client.db('vectordb').collection('embeddings');

// Criar índice vetorial
await collection.createIndex({
  embedding: {
    type: "vectorSearch"
  }
});

// Buscar documentos similares
const results = await collection.aggregate([
  {
    $vectorSearch: {
      queryVector: [0.1, 0.2, ...],
      path: "embedding",
      numCandidates: 100,
      limit: 10
    }
  }
]).toArray();

import { Pinecone } from '@pinecone-database/pinecone';

const pinecone = new Pinecone({
  apiKey: process.env.PINECONE_API_KEY,
});

const index = pinecone.index('my-index');

// Upsert vetores
await index.upsert([{
  id: '1',
  values: [0.1, 0.2, ...],
  metadata: { text: 'documento' }
}]);

// Buscar similares
const results = await index.query({
  vector: [0.1, 0.2, ...],
  topK: 10,
  includeMetadata: true
});

import { createClient } from '@supabase/supabase-js';

const supabase = createClient(
  process.env.SUPABASE_URL,
  process.env.SUPABASE_KEY
);

// Inserir embeddings
await supabase
  .from('documents')
  .insert({
    content: 'texto',
    embedding: [0.1, 0.2, ...]
  });

// Buscar similares
const { data } = await supabase
  .rpc('match_documents', {
    query_embedding: [0.1, 0.2, ...],
    match_threshold: 0.8,
    match_count: 10
  });

import { MilvusClient } from '@zilliz/milvus2-sdk-node';

const client = new MilvusClient({
  address: 'localhost:19530'
});

// Criar coleção
await client.createCollection({
  collection_name: 'documents',
  fields: [
    {
      name: 'id',
      data_type: DataType.Int64,
      is_primary_key: true,
    },
    {
      name: 'embedding',
      data_type: DataType.FloatVector,
      dim: 1536
    }
  ]
});

// Buscar similares
const results = await client.search({
  collection_name: 'documents',
  vector: [0.1, 0.2, ...],
  limit: 10
});

import { QdrantClient } from '@qdrant/qdrant-js';

const client = new QdrantClient({
  url: 'http://localhost:6333'
});

// Inserir pontos
await client.upsert('collection_name', {
  points: [{
    id: 1,
    vector: [0.1, 0.2, ...],
    payload: { text: 'documento' }
  }]
});

// Buscar similares
const results = await client.search('collection_name', {
  vector: [0.1, 0.2, ...],
  limit: 10
});