Pinecone Alternative: Pixeltable vs Pinecone

import pixeltable as pxt
from pixeltable.functions.document import document_splitter
from pixeltable.functions.huggingface import sentence_transformer

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

class Docs(TableModel, name='docs'):
    document: pxt.Document
    title: pxt.String
    category: pxt.String

class Chunks(
    TableModel,
    name='chunks',
    base=Docs,
    iterator=document_splitter(Docs.document, separators='sentence,token_limit', limit=512),
):
    __indexes__ = [pxt.EmbeddingIndex(text, embedding=embed)]

# pxt schema update app.py search
docs = pxt.get_table('search.docs')
docs.insert([
    {'document': 'papers/ml.pdf', 'title': 'Research Paper', 'category': 'research'},
])
chunks = pxt.get_table('search.chunks')
sim = chunks.text.similarity(string='machine learning algorithms')
chunks.order_by(sim, asc=False).limit(10).select(chunks.text, chunks.title)

from pinecone import Pinecone
from sentence_transformers import SentenceTransformer

pc = Pinecone(api_key='...')
index = pc.Index('docs')
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')

def upsert_docs(docs):
    vectors = []
    for doc in docs:
        text = extract_text(doc)  # you still write this
        vectors.append({
            'id': doc['id'],
            'values': model.encode(text).tolist(),
            'metadata': {'title': doc['title']},
        })
    index.upsert(vectors=vectors)

def search_docs(query, top_k=10):
    vector = model.encode(query).tolist()
    return index.query(vector=vector, top_k=top_k, include_metadata=True)