
ControlFlow adalah kerangka kerja Python untuk membangun alur kerja AI agen.
ControlFlow menyediakan kerangka kerja terstruktur dan berfokus pada pengembang untuk mendefinisikan alur kerja dan mendelegasikan pekerjaan kepada LLM, tanpa mengorbankan kontrol atau transparansi:
Alur kerja ControlFlow paling sederhana memiliki satu tugas, agen default, dan manajemen utas otomatis:
import controlflow as cf
result = cf . run ( "Write a short poem about artificial intelligence" )
print ( result )Hasil:
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 mengatasi tantangan membangun aplikasi bertenaga AI yang kuat dan dapat diprediksi:
Pasang ControlFlow dengan pip :
pip install controlflow Selanjutnya, konfigurasikan penyedia LLM Anda. Penyedia default ControlFlow adalah OpenAI, yang membutuhkan variabel lingkungan OPENAI_API_KEY :
export OPENAI_API_KEY=your-api-key
Untuk menggunakan penyedia LLM yang berbeda, lihat dokumen konfigurasi LLM.
Berikut adalah contoh yang lebih terlibat yang menampilkan interaksi pengguna, alur kerja multi-langkah, dan output terstruktur:
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 ))Percakapan:
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 workflowsUsul:
{ "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 " ] }
Dalam contoh ini, ControlFlow secara otomatis mengelola flow , atau konteks bersama untuk serangkaian tugas. Anda dapat beralih antara fungsi Python standar dan tugas agen kapan saja, membuatnya mudah untuk membangun alur kerja yang kompleks secara bertahap.
Untuk menyelam lebih dalam ke ControlFlow: