SDK da plataforma Singlow — LLMs, Agentes e ML white label
Project description
🚀 Singlow SDK
SDK oficial da plataforma Singlow (Singularity Low) — LLMs, agentes autónomos e Machine Learning.
📦 Instalação
pip install singlow
⚙️ Configuração
export SINGLOW_API_KEY="sk-singlow-xxxxxxxxxxxxxxxx"
export SINGLOW_BASE_URL="https://singlow.onrender.com/v1"
⚡ Uso Rápido
🧠 LLMs — Acesso direto aos modelos
from singlow import LLM
llm = LLM(modelo="singlow-fast")
print(llm.chat("Explica backpropagation numa frase."))
🔄 Streaming
for token in llm.chat_stream("Conta até 5 devagar."): print(token, end="", flush=True)
🤖 Agentes
🧠 Agente com memória
from singlow import Agent
agente = Agent(nome="Marcus", modelo="singlow-fast", memoria=True)
agente.executar("O meu nome é Marius.") print(agente.executar("Qual é o meu nome?")) # Marius
🛠️ Agente com ferramentas
from singlow import Agent, Tool
def criar_ficheiro(nome, conteudo): with open(nome, "w") as f: f.write(conteudo) return f"✅ {nome} criado!"
ferramenta = Tool("criar", criar_ficheiro, "Cria ficheiro: nome, conteudo")
agente = Agent(nome="Dev", modelo="singlow-code", ferramentas=[ferramenta])
agente.executar('Cria um ficheiro "ola.txt" com "Olá mundo!"')
🤝 Múltiplos agentes
arquiteto = Agent(nome="Luna", modelo="singlow-reasoning", memoria=True) programador = Agent(nome="Marcus", modelo="singlow-code", ferramentas=[ferramenta], memoria=True)
plano = arquiteto.executar("Cria um plano para uma calculadora Python.") codigo = programador.executar(f"Implementa este plano: {plano}")
🧩 Modelos Disponíveis
- singlow-fast → Respostas rápidas e curtas
- singlow-reasoning → Raciocínio profundo
- singlow-code → Geração de código
📊 Machine Learning
from singlow import Regressor, Classifier
Regressão
modelo = Regressor(algoritmo="random_forest") modelo.treinar("casas.csv", "preco") previsao = modelo.prever({"tamanho_m2": 120, "quartos": 3})
Classificação
modelo = Classifier(algoritmo="logistic") modelo.treinar("clientes.csv", "aprovado") resultado = modelo.prever({"renda": 5000, "idade": 30})
📚 Documentação
https://singlow.onrender.com/docs
📄 Licença
MIT License — ver ficheiro LICENSE
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file singlow-0.3.0.tar.gz.
File metadata
- Download URL: singlow-0.3.0.tar.gz
- Upload date:
- Size: 6.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
319d9da13c74ee8e80ab5f48dbb7ae2d510c97c0089f1d7f5f32048ea15ee805
|
|
| MD5 |
977afb3ec05c5e2013a4e6929f8dc3ac
|
|
| BLAKE2b-256 |
2999b4329967b28782f9ea6d79198cfc93e28a192d5ff9c1a9ec8b86e03445a3
|
File details
Details for the file singlow-0.3.0-py3-none-any.whl.
File metadata
- Download URL: singlow-0.3.0-py3-none-any.whl
- Upload date:
- Size: 7.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0244b678750be41849827333f42cc2b86f8a5bcc187fce4663557d73ff0a6e7a
|
|
| MD5 |
dca8779901aec33b43de4711e53d06ce
|
|
| BLAKE2b-256 |
ded35eb0922d3955607b2dbb42ae4b8e40ec6e2b0c5520c9db02e1e201c145a5
|