Pixeltable and LlamaIndex

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

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

if __name__ == '__main__':
    # After: pxt schema update app.py app
    docs = pxt.get_table('app.docs')
    docs.insert([{'document': 'handbook.pdf', 'title': 'Handbook'}])
    chunks = pxt.get_table('app.chunks')
    sim = chunks.text.similarity(string='What is the refund policy?')
    chunks.order_by(sim, asc=False).limit(5).select(chunks.text)

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.embeddings.openai import OpenAIEmbedding

# Starter path: developers.llamaindex.ai/python/framework/getting_started/starter_example
documents = SimpleDirectoryReader('data').load_data()
index = VectorStoreIndex.from_documents(
    documents,
    embed_model=OpenAIEmbedding(model='text-embedding-3-small'),
)
query_engine = index.as_query_engine()
response = query_engine.query('What is the refund policy?')
print(response)
# Images, versioning, and re-chunking on insert are still yours.
# Persist if you do not want to rebuild: index.storage_context.persist('storage')