Pixeltable vs Turso

import pixeltable as pxt
from pixeltable.functions.huggingface import clip

TableModel = pxt.model_base()
image_embed = clip.using(model_id='openai/clip-vit-base-patch32')

class Catalog(TableModel, name='catalog'):
    image: pxt.Image
    product_name: pxt.String
    __indexes__ = [pxt.EmbeddingIndex(image, image_embed=image_embed)]

# pxt schema update app.py store
catalog = pxt.get_table('store.catalog')
catalog.insert([{'image': 'sneaker_white.jpg', 'product_name': 'Running Shoe'}])

# Query visually similar items in-engine
sim = catalog.image.similarity(image='query_shoe.jpg')
matches = catalog.order_by(sim, asc=False).limit(3).select(catalog.product_name, sim)

# 1. Turso libSQL schema
# CREATE TABLE catalog (
#   id TEXT PRIMARY KEY,
#   product_name TEXT,
#   image_url TEXT,
#   embedding F32_BLOB(512)
# );

import libsql_experimental as libsql
import torch
from PIL import Image
from transformers import CLIPProcessor, CLIPModel

model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
conn = libsql.connect("turso.db", sync_url="libsql://...", auth_token="...")

def ingest_product(prod_id, name, img_path):
    # 1. Upload image to S3 (external code)
    s3_url = upload_s3(img_path)
    
    # 2. Compute embedding
    image = Image.open(img_path)
    inputs = processor(images=image, return_tensors="pt")
    with torch.no_grad():
        emb = model.get_image_features(**inputs).squeeze().tolist()
    
    # 3. Insert into Turso with vector blob
    conn.execute(
        "INSERT INTO catalog VALUES (?, ?, ?, vector32(?))",
        (prod_id, name, s3_url, str(emb))
    )
    conn.commit()
    conn.sync()
# Must manage: S3 upload failures, CLIP GPU worker queue, retry logic

# Upgrade embedder in app.py:
new_embed = clip.using(model_id='openai/clip-vit-large-patch14')

class Catalog(TableModel, name='catalog'):
    image: pxt.Image
    __indexes__ = [pxt.EmbeddingIndex(image, image_embed=new_embed)]

# Run: pxt schema update app.py store
# Pixeltable calculates missing embeddings and updates the index incrementally.

# 1. Alter Turso table
# ALTER TABLE catalog ADD COLUMN new_embedding F32_BLOB(768);

# 2. Run backfill script in Python
new_model = CLIPModel.from_pretrained("openai/clip-vit-large-patch14")
cursor = conn.execute("SELECT id, image_url FROM catalog WHERE new_embedding IS NULL")
rows = cursor.fetchall()

for row_id, img_url in rows:
    img = download_from_s3(img_url)
    inputs = processor(images=img, return_tensors="pt")
    with torch.no_grad():
        v = new_model.get_image_features(**inputs).squeeze().tolist()
    conn.execute("UPDATE catalog SET new_embedding = vector32(?) WHERE id = ?", (str(v), row_id))
conn.commit()
conn.sync()
# Fragile under concurrency, requires manual checkpointing if process crashes