Getting started with embeddings in JS

async function memoryToEmbedding(memory) {
  const embedding = openai.createEmbedding({
    model: 'text-embedding-ada-002',
    input: memory,
  });
  return embedding;
}

const title = 'First post!'
const body = 'Hello world!'
 
// Generate a vector using OpenAI
const embeddingResponse = await openai.createEmbedding({
  model: 'text-embedding-ada-002',
  input: body,
})
 
const [{ embedding }] = embeddingResponse.data.data
 
// Store the vector in Postgres
const { data, error } = await supabase.from('posts').insert({
  title,
  body,
  embedding,
})

create or replace function match_documents (
  query_embedding vector(1536),
  match_threshold float,
  match_count int
)
returns table (
  id bigint,
  content text,
  similarity float
)
language sql stable
as $$
  select
    documents.id,
    documents.content,
    1 - (documents.embedding <=> query_embedding) as similarity
  from documents
  where 1 - (documents.embedding <=> query_embedding) > match_threshold
  order by similarity desc
  limit match_count;
$$;

async function getRelevantMemories(queryString, limit = 5) {
  // turn the queryString into an embedding
  const embeddingResponse = await openai.createEmbedding({
    model: 'text-embedding-ada-002',
    input: queryString.toString(),
  })
 
  const [{ embedding }] = embeddingResponse.data.data
 
  // query the database for the most relevant memories
  const { data, error } = await supabase.rpc('match_documents', { 
    query_embedding: embedding,
    match_threshold: 0.78,
    match_count: limit
  });
 
  if (error) {
    console.error("Error fetching relevant user memory:", error);
    return null;
  }
 
  return data
}