Insert Embedding in Pinecone

After generating embeddings, you need to store them in a vector database for similarity search. The PineconeVector class provides methods to create indexes and insert embeddings into Pinecone, a managed vector database service. This example shows how to store embeddings in Pinecone for later retrieval.

import { MDocument, embed, PineconeVector } from '@mastra/rag';
 
const doc = MDocument.fromText('Your text content...');
 
const chunks = await doc.chunk();
 
const { embeddings } = await embed(chunks, {
  provider: 'OPEN_AI',
  model: 'text-embedding-ada-002',
  maxRetries: 3,
});
 
const pinecone = new PineconeVector('your-api-key');
 
await pinecone.createIndex('test_index', 1536);
 
await pinecone.upsert(
  'test_index',
  embeddings,
  chunks?.map(chunk => ({ text: chunk.text })),
);

View Example on GitHub

Embed Text with Cohere Insert Embedding in PgVector