
Controlflow - это рамка Python для строительных рабочих процессов AI.
Controlflow предоставляет структурированную, ориентированную на разработчиков структуру для определения рабочих процессов и делегирования работы в LLM, не жертвуя контролем или прозрачностью:
Самый простой рабочий процесс Controlflow имеет одну задачу, агент по умолчанию и автоматическое управление потоками:
import controlflow as cf
result = cf . run ( "Write a short poem about artificial intelligence" )
print ( result )Результат:
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 решает проблемы создания приложений с AI, которые являются мощными и предсказуемыми:
Установите Controlflow с pip :
pip install controlflow Затем настройте свой провайдер LLM. Поставщик по умолчанию Controlflow - это OpenAI, которая требует переменной среды OPENAI_API_KEY :
export OPENAI_API_KEY=your-api-key
Чтобы использовать другого поставщика LLM, см. Документы LLM Configuration.
Вот более сложный пример, который демонстрирует взаимодействие с пользователем, многоэтапный рабочий процесс и структурированные выходы:
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 ))Беседа:
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 workflowsПредложение:
{ "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 " ] }
В этом примере ControlFlow автоматически управляет flow или общим контекстом для ряда задач. Вы можете в любое время переключаться между стандартными функциями Python и агентскими задачами, что облегчает постепенное создание сложных рабочих процессов.
Чтобы глубже погрузиться в Controlflow: