Files
crewAI/docs/edge/ko/learn/kickoff-async.mdx
Lucas Gomide 93dafe2637 feat: adopt directory-based docs versioning with Edge channel
Switch docs.crewai.com from navigation-only versioning (every version
selector entry rendered the same docs/<lang>/* source files) to
Mintlify's directory-based versioning so each version selector entry
renders its own snapshot. Add an "Edge" channel under docs/edge/<lang>/*
that always reflects main HEAD for unreleased work, eliminating
pre-release leakage onto frozen release labels. External links to
canonical /<lang>/* URLs are preserved via wildcard redirects that
always land on the current default version.

Layout:
- docs/edge/<lang>/*         rolling source (you edit here)
- docs/edge/enterprise-api.*.yaml
- docs/v<X.Y.Z>/<lang>/*     frozen, immutable snapshots
- docs/v<X.Y.Z>/enterprise-api.*.yaml
- docs/images/               shared, append-only
- docs/docs.json             nav + redirects

URLs follow the Mintlify-idiomatic shape: /edge/<lang>/<page> for
Edge, /v<X.Y.Z>/<lang>/<page> for every frozen snapshot. The wildcard
redirects /<lang>/:slug* -> /<default>/<lang>/:slug* keep stale links
working, and every freeze rewrites them (plus all per-section/per-page
redirects) so destinations always resolve to the current default
without depending on a second redirect hop.

Release flow integration (devtools release):
- New module crewai_devtools.docs_versioning.freeze() materialises
  docs/v<X.Y.Z>/ from docs/edge/, rewrites openapi: refs inside the
  snapshot, inserts the version into every language block in
  docs.json, and refreshes all redirect destinations.
- _update_docs_and_create_pr() in cli.py now calls that freeze during
  Phase 2 of devtools release. Edge changelogs are updated first (so
  the snapshot freeze picks them up), then the snapshot is staged
  alongside docs.json, branched as docs/freeze-v<X.Y.Z>, and the PR
  is titled [docs-freeze] docs: snapshot and changelog for v<X.Y.Z>
  — the title prefix the new CI guard reads.
- The PR still gates tag, GitHub release, PyPI publish, and the
  enterprise release as before; no new PRs are added.
- Pre-releases (1.X.YaN, 1.X.YbN, ...) skip the snapshot — they ride
  Edge — and the docs PR title omits the [docs-freeze] prefix.
- docs_check (AI-generated docs scaffolding) writes to
  docs/edge/<lang>/* so newly-generated unreleased docs land in Edge
  and never accidentally touch a frozen snapshot.

Migration scripts (one-shot):
- scripts/docs/freeze_historical_versions.py reconstructs all 16
  historical snapshots (v1.10.0 .. v1.14.7) from git tags via
  git archive | tar, rewriting openapi: MDX refs so each snapshot
  reads its own enterprise-api YAML rather than the live one.
- scripts/docs/prefix_version_paths.py one-shot-migrates docs.json:
  rewrites every page path in 16 versioned blocks to point under
  docs/v<X.Y.Z>/, inserts a new Edge entry per language, tags
  v1.14.7 as Latest (default), prunes pages whose target file
  doesn't exist in the snapshot (e.g. docs/ar/ didn't exist before
  v1.12.0), and writes the wildcard + per-section redirects.
- scripts/docs/freeze_current_edge.py is now a thin CLI wrapper
  around docs_versioning.freeze for manual one-off freezes (e.g.
  retroactively snapshotting a forgotten release).

CI guards (.github/workflows/docs-snapshots.yml):
- Frozen snapshots under docs/v[0-9]*/ are immutable; only PRs whose
  title contains [docs-freeze] (i.e. release-cut PRs generated by
  devtools release or the manual wrapper) may modify them.
- Images under docs/images/ are append-only since snapshots share a
  single image directory. Deleting or renaming an image breaks every
  historical snapshot that still references it.

Restored docs/images/crewai-otel-export.png from PR #3673; it was
deleted in PR #4908 but v1.10.0 / v1.10.1 snapshots still reference
it. Restoring instead of editing the snapshots preserves historical
rendering fidelity and validates the new append-only rule
retroactively.

Tests:
- lib/devtools/tests/test_docs_versioning.py covers the freeze: file
  copy, openapi rewrite, version insertion, default demotion, redirect
  upserts, per-section redirect rewriting, idempotency, and invalid
  inputs.

Verified locally with mintlify broken-links: 0 broken links across
the full site (Edge + 16 frozen versions, 4 locales).

AGENTS.md (repo root) is the contributor guide for the new model;
RELEASING.md is the release-cut runbook; README's Contribution
section links to both.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-17 11:08:45 -03:00

307 lines
9.6 KiB
Plaintext

---
title: Crew 비동기 시작
description: Crew를 비동기로 시작하기
icon: rocket-launch
mode: "wide"
---
## 소개
CrewAI는 crew를 비동기적으로 시작할 수 있는 기능을 제공합니다. 이를 통해 crew 실행을 블로킹(blocking) 없이 시작할 수 있습니다.
이 기능은 여러 개의 crew를 동시에 실행하거나 crew가 실행되는 동안 다른 작업을 수행해야 할 때 특히 유용합니다.
CrewAI는 비동기 실행을 위해 두 가지 접근 방식을 제공합니다:
| 메서드 | 타입 | 설명 |
|--------|------|-------------|
| `akickoff()` | 네이티브 async | 전체 실행 체인에서 진정한 async/await 사용 |
| `kickoff_async()` | 스레드 기반 | 동기 실행을 `asyncio.to_thread`로 래핑 |
<Note>
고동시성 워크로드의 경우 `akickoff()`가 권장됩니다. 이는 작업 실행, 메모리 작업, 지식 검색에 네이티브 async를 사용합니다.
</Note>
## `akickoff()`를 사용한 네이티브 비동기 실행
`akickoff()` 메서드는 작업 실행, 메모리 작업, 지식 쿼리를 포함한 전체 실행 체인에서 async/await를 사용하여 진정한 네이티브 비동기 실행을 제공합니다.
### 메서드 시그니처
```python Code
async def akickoff(self, inputs: dict) -> CrewOutput:
```
### 매개변수
- `inputs` (dict): 작업에 필요한 입력 데이터를 포함하는 딕셔너리입니다.
### 반환
- `CrewOutput`: crew 실행 결과를 나타내는 객체입니다.
### 예시: 네이티브 비동기 Crew 실행
```python Code
import asyncio
from crewai import Crew, Agent, Task
# 에이전트 생성
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
# 작업 생성
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
# Crew 생성
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
# 네이티브 비동기 실행
async def main():
result = await analysis_crew.akickoff(inputs={"ages": [25, 30, 35, 40, 45]})
print("Crew Result:", result)
asyncio.run(main())
```
### 예시: 여러 네이티브 비동기 Crew
`asyncio.gather()`를 사용하여 네이티브 async로 여러 crew를 동시에 실행:
```python Code
import asyncio
from crewai import Crew, Agent, Task
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
task_1 = Task(
description="Analyze the first dataset and calculate the average age. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
task_2 = Task(
description="Analyze the second dataset and calculate the average age. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
crew_1 = Crew(agents=[coding_agent], tasks=[task_1])
crew_2 = Crew(agents=[coding_agent], tasks=[task_2])
async def main():
results = await asyncio.gather(
crew_1.akickoff(inputs={"ages": [25, 30, 35, 40, 45]}),
crew_2.akickoff(inputs={"ages": [20, 22, 24, 28, 30]})
)
for i, result in enumerate(results, 1):
print(f"Crew {i} Result:", result)
asyncio.run(main())
```
### 예시: 여러 입력에 대한 네이티브 비동기
`akickoff_for_each()`를 사용하여 네이티브 async로 여러 입력에 대해 crew를 동시에 실행:
```python Code
import asyncio
from crewai import Crew, Agent, Task
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
data_analysis_task = Task(
description="Analyze the dataset and calculate the average age. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
async def main():
datasets = [
{"ages": [25, 30, 35, 40, 45]},
{"ages": [20, 22, 24, 28, 30]},
{"ages": [30, 35, 40, 45, 50]}
]
results = await analysis_crew.akickoff_for_each(datasets)
for i, result in enumerate(results, 1):
print(f"Dataset {i} Result:", result)
asyncio.run(main())
```
## `kickoff_async()`를 사용한 스레드 기반 비동기
`kickoff_async()` 메서드는 동기 `kickoff()`를 스레드로 래핑하여 비동기 실행을 제공합니다. 이는 더 간단한 비동기 통합이나 하위 호환성에 유용합니다.
### 메서드 시그니처
```python Code
async def kickoff_async(self, inputs: dict) -> CrewOutput:
```
### 매개변수
- `inputs` (dict): 작업에 필요한 입력 데이터를 포함하는 딕셔너리입니다.
### 반환
- `CrewOutput`: crew 실행 결과를 나타내는 객체입니다.
### 예시: 스레드 기반 비동기 실행
```python Code
import asyncio
from crewai import Crew, Agent, Task
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
data_analysis_task = Task(
description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
analysis_crew = Crew(
agents=[coding_agent],
tasks=[data_analysis_task]
)
async def async_crew_execution():
result = await analysis_crew.kickoff_async(inputs={"ages": [25, 30, 35, 40, 45]})
print("Crew Result:", result)
asyncio.run(async_crew_execution())
```
### 예시: 여러 스레드 기반 비동기 Crew
```python Code
import asyncio
from crewai import Crew, Agent, Task
coding_agent = Agent(
role="Python Data Analyst",
goal="Analyze data and provide insights using Python",
backstory="You are an experienced data analyst with strong Python skills.",
allow_code_execution=True
)
task_1 = Task(
description="Analyze the first dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
task_2 = Task(
description="Analyze the second dataset and calculate the average age of participants. Ages: {ages}",
agent=coding_agent,
expected_output="The average age of the participants."
)
crew_1 = Crew(agents=[coding_agent], tasks=[task_1])
crew_2 = Crew(agents=[coding_agent], tasks=[task_2])
async def async_multiple_crews():
result_1 = crew_1.kickoff_async(inputs={"ages": [25, 30, 35, 40, 45]})
result_2 = crew_2.kickoff_async(inputs={"ages": [20, 22, 24, 28, 30]})
results = await asyncio.gather(result_1, result_2)
for i, result in enumerate(results, 1):
print(f"Crew {i} Result:", result)
asyncio.run(async_multiple_crews())
```
## 비동기 스트리밍
두 비동기 메서드 모두 crew에 `stream=True`가 설정된 경우 스트리밍을 지원합니다:
```python Code
import asyncio
from crewai import Crew, Agent, Task
agent = Agent(
role="Researcher",
goal="Research and summarize topics",
backstory="You are an expert researcher."
)
task = Task(
description="Research the topic: {topic}",
agent=agent,
expected_output="A comprehensive summary of the topic."
)
crew = Crew(
agents=[agent],
tasks=[task],
stream=True # 스트리밍 활성화
)
async def main():
streaming_output = await crew.akickoff(inputs={"topic": "AI trends in 2024"})
# 스트리밍 청크에 대한 비동기 반복
async for chunk in streaming_output:
print(f"Chunk: {chunk.content}")
# 스트리밍 완료 후 최종 결과 접근
result = streaming_output.result
print(f"Final result: {result.raw}")
asyncio.run(main())
```
## 잠재적 사용 사례
- **병렬 콘텐츠 생성**: 여러 개의 독립적인 crew를 비동기적으로 시작하여, 각 crew가 다른 주제에 대한 콘텐츠 생성을 담당합니다. 예를 들어, 한 crew는 AI 트렌드에 대한 기사 조사 및 초안을 작성하는 반면, 또 다른 crew는 신제품 출시와 관련된 소셜 미디어 게시물을 생성할 수 있습니다.
- **동시 시장 조사 작업**: 여러 crew를 비동기적으로 시작하여 시장 조사를 병렬로 수행합니다. 한 crew는 업계 동향을 분석하고, 또 다른 crew는 경쟁사 전략을 조사하며, 또 다른 crew는 소비자 감정을 평가할 수 있습니다.
- **독립적인 여행 계획 모듈**: 각각 독립적으로 여행의 다양한 측면을 계획하도록 crew를 따로 실행합니다. 한 crew는 항공편 옵션을, 다른 crew는 숙박을, 세 번째 crew는 활동 계획을 담당할 수 있습니다.
## `akickoff()`와 `kickoff_async()` 선택하기
| 기능 | `akickoff()` | `kickoff_async()` |
|---------|--------------|-------------------|
| 실행 모델 | 네이티브 async/await | 스레드 기반 래퍼 |
| 작업 실행 | `aexecute_sync()`로 비동기 | 스레드 풀에서 동기 |
| 메모리 작업 | 비동기 | 스레드 풀에서 동기 |
| 지식 검색 | 비동기 | 스레드 풀에서 동기 |
| 적합한 용도 | 고동시성, I/O 바운드 워크로드 | 간단한 비동기 통합 |
| 스트리밍 지원 | 예 | 예 |