Pixeltable and Railway

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

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(
        document=Docs.document, separators='sentence,token_limit', limit=512
    ),
):
    __indexes__ = [pxt.EmbeddingIndex(text, string_embed=embed)]

@pxt.query
def search_docs(query: str, limit: int = 5):
    sim = Chunks.text.similarity(string=query)
    return (
        Chunks.order_by(sim, asc=False)
        .limit(limit)
        .select(Chunks.text, Chunks.title, sim)
    )

api = FastAPIRouter(name='docs')
api.add_insert_route(Docs, path='/docs', inputs=[Docs.document, Docs.title])
api.add_query_route(path='/search', query=search_docs)
# pxt schema update app.py docs && pxt service update app.py docs
# Or mount the router on FastAPI and host that process on Railway.

# app.py hosted on Railway. The platform runs the container;
# object storage, the embed job, and the vector DB are still yours.
from fastapi import FastAPI

app = FastAPI()

@app.post('/docs')
def insert_doc(title: str, path: str):
    # upload to S3, enqueue a worker, upsert vectors...
    return {'ok': True}

@app.get('/search')
def search(q: str):
    # query the index you deployed beside this service
    return []

# Git: connect a GitHub repo; Railway builds with Railpack or a Dockerfile.
# CLI (https://docs.railway.com/guides/cli):
#   railway login
#   railway init
#   railway up
#   railway add --database postgres
# Start command: uvicorn app:app --host 0.0.0.0 --port $PORT