Pixeltable vs Prisma Postgres

import pixeltable as pxt
from pixeltable.functions.huggingface import sentence_transformer
from pixeltable.functions.whisper import transcribe

TableModel = pxt.model_base()
embed = sentence_transformer.using(model_id='sentence-transformers/all-MiniLM-L6-v2')

class Recordings(TableModel, name='recordings'):
    audio: pxt.Audio
    title: pxt.String
    # Computed column: transcribes audio upon insert
    transcript = transcribe(audio, model='base').text.astype(pxt.String)
    __indexes__ = [pxt.EmbeddingIndex(transcript, embedding=embed)]

# pxt schema update app.py voice
recs = pxt.get_table('voice.recordings')
recs.insert([{'audio': 'meeting_01.mp3', 'title': 'Product Sync'}])

# Query semantically across transcripts
sim = recs.transcript.similarity(string='pricing tier feedback')
hits = recs.order_by(sim, asc=False).limit(3).select(recs.title, recs.transcript)

// 1. schema.prisma
// model Recording {
//   id          String   @id @default(uuid())
//   title       String
//   audioUrl    String
//   transcript  String?
//   embedding   Unsupported("vector(384)")?
// }

// 2. Application route / background job
import { PrismaClient } from '@prisma/client';
import OpenAI from 'openai';

const prisma = new PrismaClient();
const openai = new OpenAI();

export async function processRecording(title: string, audioFile: Buffer) {
  // Upload to S3, call Whisper API, generate embedding, then save to DB
  const audioUrl = await uploadToS3(audioFile);
  const transcription = await openai.audio.transcriptions.create({
    file: audioFile,
    model: 'whisper-1',
  });
  const embResponse = await openai.embeddings.create({
    model: 'text-embedding-3-small',
    input: transcription.text,
  });
  
  return await prisma.$executeRaw`
    INSERT INTO "Recording" (id, title, "audioUrl", transcript, embedding)
    VALUES (gen_random_uuid(), ${title}, ${audioUrl}, ${transcription.text}, ${embResponse.data[0].embedding}::vector)
  `;
  // Requires: S3 credentials, OpenAI rate limiting, retry queue, connection config
}

# Add computed column in app.py:
from pixeltable.functions.openai import chat_completions

class Recordings(TableModel, name='recordings'):
    audio: pxt.Audio
    transcript = transcribe(audio, model='base').text.astype(pxt.String)
    summary = chat_completions(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': 'Summarize in 2 sentences: ' + transcript}],
    )

# Run: pxt schema update app.py voice
# Pixeltable calculates missing summaries and backfills incrementally.

// 1. Run migration: npx prisma migrate dev --name add_summary
// ALTER TABLE "Recording" ADD COLUMN "summary" TEXT;

// 2. Write and run backfill script
import { PrismaClient } from '@prisma/client';
import OpenAI from 'openai';

const prisma = new PrismaClient();
const openai = new OpenAI();

async function backfillSummaries() {
  const records = await prisma.recording.findMany({
    where: { summary: null, transcript: { not: null } },
    take: 50,
  });
  for (const r of records) {
    const res = await openai.chat.completions.create({
      model: 'gpt-4o-mini',
      messages: [{ role: 'user', content: `Summarize: ${r.transcript}` }],
    });
    await prisma.recording.update({
      where: { id: r.id },
      data: { summary: res.choices[0].message.content },
    });
  }
}
// Risk: script interruption leaves partial state, rate-limiting must be hand-coded