
O ControlFlow é uma estrutura Python para a construção de fluxos de trabalho de IA agênticos.
O ControlFlow fornece uma estrutura estruturada e focada no desenvolvedor para definir fluxos de trabalho e delegar o trabalho ao LLMS, sem sacrificar o controle ou a transparência:
O fluxo de trabalho do ControlFlow mais simples tem uma tarefa, um agente padrão e gerenciamento automático de threads:
import controlflow as cf
result = cf . run ( "Write a short poem about artificial intelligence" )
print ( result )Resultado:
In circuits and code, a mind does bloom,
With algorithms weaving through the gloom.
A spark of thought in silicon's embrace,
Artificial intelligence finds its place.
O ControlFlow aborda os desafios da criação de aplicativos movidos a IA poderosos e previsíveis:
Instale o ControlFlow com pip :
pip install controlflow Em seguida, configure seu provedor LLM. O provedor padrão do ControlFlow é o OpenAI, que requer a variável de ambiente OPENAI_API_KEY :
export OPENAI_API_KEY=your-api-key
Para usar um provedor LLM diferente, consulte os documentos de configuração do LLM.
Aqui está um exemplo mais envolvido que mostra a interação do usuário, um fluxo de trabalho em várias etapas e saídas estruturadas:
import controlflow as cf
from pydantic import BaseModel
class ResearchProposal ( BaseModel ):
title : str
abstract : str
key_points : list [ str ]
@ cf . flow
def research_proposal_flow ():
# Task 1: Get the research topic from the user
user_input = cf . Task (
"Work with the user to choose a research topic" ,
interactive = True ,
)
# Task 2: Generate a structured research proposal
proposal = cf . run (
"Generate a structured research proposal" ,
result_type = ResearchProposal ,
depends_on = [ user_input ]
)
return proposal
result = research_proposal_flow ()
print ( result . model_dump_json ( indent = 2 ))Conversa:
Agent: Hello! I'm here to help you choose a research topic. Do you have any particular area of interest or field you would like to explore? If you have any specific ideas or requirements, please share them as well. User: Yes, I'm interested in LLM agentic workflowsProposta:
{ "title" : " AI Agentic Workflows: Enhancing Efficiency and Automation " , "abstract" : " This research proposal aims to explore the development and implementation of AI agentic workflows to enhance efficiency and automation in various domains. AI agents, equipped with advanced capabilities, can perform complex tasks, make decisions, and interact with other agents or humans to achieve specific goals. This research will investigate the underlying technologies, methodologies, and applications of AI agentic workflows, evaluate their effectiveness, and propose improvements to optimize their performance. " , "key_points" : [ " Introduction: Definition and significance of AI agentic workflows, Historical context and evolution of AI in workflows " , " Technological Foundations: AI technologies enabling agentic workflows (e.g., machine learning, natural language processing), Software and hardware requirements for implementing AI workflows " , " Methodologies: Design principles for creating effective AI agents, Workflow orchestration and management techniques, Interaction protocols between AI agents and human operators " , " Applications: Case studies of AI agentic workflows in various industries (e.g., healthcare, finance, manufacturing), Benefits and challenges observed in real-world implementations " , " Evaluation and Metrics: Criteria for assessing the performance of AI agentic workflows, Metrics for measuring efficiency, accuracy, and user satisfaction " , " Proposed Improvements: Innovations to enhance the capabilities of AI agents, Strategies for addressing limitations and overcoming challenges " , " Conclusion: Summary of key findings, Future research directions and potential impact on industry and society " ] }
Neste exemplo, o ControlFlow está gerenciando automaticamente um flow ou um contexto compartilhado para uma série de tarefas. Você pode alternar entre as funções Python padrão e as tarefas agênticas a qualquer momento, facilitando a criação de fluxos de trabalho complexos.
Para mergulhar mais fundo no ControlFlow: