Como criar um workflow no Windsurf - https://docs.windsurf.com/windsurf/cascade/workflows
Arquivo: code-quality-improvements.md
Aqui a dica é selecionar o arquivo ou trecho de código para executar esse workflow (passar um contexto).
Johni Douglas Marangon johnidm
BigQuery ML BQML is a powerful feature within Google BigQuery that allows users to create, train, and execute machine learning models directly using SQL queries.
This approach aims to democratize machine learning by enabling SQL practitioners to build models with their existing tools, eliminating the need to move large amounts of data to separate ML frameworks or services.
BigQuery ML supports a variety of machine learning models and algorithms, catering to different analytical needs. Here's a breakdown of the types you can use:
These models can be built directly within BigQuery ML using SQL:
Below is a clean, practical workflow to add DVC to an existing Git repo and start versioning your data and model artifacts (e.g., large/binary files). Adjust remote choices (S3, GCS, Azure, SSH, local) to your environment.
Prerequisites:
- Git installed and repository initialized
- DVC installed with S3/GCS/Azure support as needed (https://dvc.org/doc/install)
Verify:
KServe supports a wide variety of model formats across both predictive and generative AI inference.
spaCy models are not natively supported by KServe (as of 2025). However, you can serve spaCy models easily using KServe’s Python model server — the kserve SDK provides a way to deploy custom Python models (like spaCy NLP pipelines, HuggingFace models, or anything else in Python).
Formats:
Instead of await file.read(), you can save the file temporarily to disk and then process it:
import tempfile
from fastapi import UploadFile, HTTPException, status
async def process_file(file: UploadFile, mode: str):
if file.content_type != "application/pdf":
raise HTTPException(
You can give different weights to the fields in PostgreSQL full-text search by using setweight() inside your to_tsvector.
SELECT
id,
title,
area,
tags,
content,
url,
Install the dependency
pip install ruff
Foramt files
Design and develop a modern question and answer (Q&A) web application using Next.js and TypeScript. The application should prioritize a clean user experience, efficient data management, and adherence to current web development best practices.
Don't implement user Authentication:
# Core Features:
Question Management:
from openai import OpenAI
import base64
from pydantic import BaseModel
Prompt que executa uma analise no seu perfil do Linkedin com o objetivo de melhorar ele.
Salve o seu perfil em PDF.
Fazer o upload do PDF em alguma LLM e executar o prompt abaixo.
NewerOlder