Multimodal backend

Insert a document. The iterator explodes it into chunks. The embedding index stays current. pxt service update starts the insert and search endpoints. Create the tables with pxt schema update app.py my_app, then open them with t = pxt.get_table('my_app.docs'). Cookbooks on this topic use pxt.create_table() so you can run cells without a project. An app puts the same columns on a TableModel in app.py and creates the tables with pxt schema update.

import pixeltable as pxt
import pixeltable.functions as pxtf
from pixeltable.serving import FastAPIRouter

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


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


class Chunks(
    TableModel,
    name='chunks',
    base=Docs,
    iterator=pxtf.document.document_splitter(
        Docs.document, separators='token_limit', limit=300
    ),
):
    __indexes__ = [
        pxt.EmbeddingIndex(text, embedding=embed, name='chunks_embed')
    ]


@pxt.query
def search_docs(query_text: str):
    sim = Chunks.text.similarity(string=query_text)
    return Chunks.order_by(sim, asc=False).limit(10).select(Chunks.text, sim)


api = FastAPIRouter(name='rag')
api.add_insert_route(
    Docs,
    path='/docs',
    uploadfile_inputs=[Docs.document],
    outputs=[Docs.document],
)
api.add_query_route(path='/search', query=search_docs, method='post')

pxt schema update app.py my_app
pxt service update app.py my_app

docs = pxt.get_table('my_app.docs')
docs.insert([{'document': 'report.pdf'}])

pxt service list prints the URL. POST /docs to insert. POST /search with {"query_text": "..."} to rank chunks. On Cloud, create an API key in the dashboard, set PIXELTABLE_API_KEY, then run pxt db update, pxt schema update, and pxt service update against pxt://org:mydb. Export those tables for training: Datasets from media. Tool calls as columns: Agents.

RAG pipeline

POST /docs to insert. Chunks stay current.

Semantic text search

Rank chunks with {"query_text": "..."}.

Similar images

The same index pattern on images.

HTTP serving

Insert and search routes from the same file.

Use Cases

Topics

RAG pipeline

Semantic text search

Similar images

HTTP serving