
Controlflow es un marco de Python para construir flujos de trabajo de IA agente.
Controlflow proporciona un marco estructurado y centrado en el desarrollador para definir flujos de trabajo y delegar el trabajo a LLMS, sin sacrificar el control o la transparencia:
El flujo de trabajo Controlflow más simple tiene una tarea, un agente predeterminado y administración automática de subprocesos:
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.
Controlflow aborda los desafíos de construir aplicaciones con AI que son poderosas y predecibles:
Instalar Controlflow con pip :
pip install controlflow A continuación, configure su proveedor de LLM. El proveedor predeterminado de Controlflow es OpenAI, que requiere la variable de entorno OPENAI_API_KEY :
export OPENAI_API_KEY=your-api-key
Para usar un proveedor de LLM diferente, consulte los documentos de configuración de LLM.
Aquí hay un ejemplo más involucrado que muestra la interacción del usuario, un flujo de trabajo de varios pasos y salidas estructuradas:
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 ))Conversación:
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 workflowsPropuesta:
{ "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 " ] }
En este ejemplo, Controlflow administra automáticamente un flow o un contexto compartido para una serie de tareas. Puede cambiar entre funciones estándar de Python y tareas de agente en cualquier momento, lo que facilita la construcción de flujos de trabajo complejos incrementalmente.
Para sumergirse en el flujo de control: