mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-02 13:48:09 +00:00
a237ebabba
* 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> * style: resolve linter issues --------- Co-authored-by: Cursor <cursoragent@cursor.com>
108 lines
4.2 KiB
Plaintext
108 lines
4.2 KiB
Plaintext
---
|
|
title: Integração Langfuse
|
|
description: Saiba como integrar o Langfuse ao CrewAI via OpenTelemetry usando OpenLit
|
|
icon: vials
|
|
mode: "wide"
|
|
---
|
|
|
|
# Integre o Langfuse ao CrewAI
|
|
|
|
Este notebook demonstra como integrar o **Langfuse** ao **CrewAI** usando OpenTelemetry via o SDK **OpenLit**. Ao final deste notebook, você será capaz de rastrear suas aplicações CrewAI com o Langfuse para melhorar a observabilidade e a depuração.
|
|
|
|
> **O que é Langfuse?** [Langfuse](https://langfuse.com) é uma plataforma open-source de engenharia LLM. Ela fornece recursos de rastreamento e monitoramento para aplicações LLM, ajudando desenvolvedores a depurar, analisar e otimizar seus sistemas de IA. O Langfuse se integra com várias ferramentas e frameworks através de integrações nativas, OpenTelemetry e APIs/SDKs.
|
|
|
|
[](https://langfuse.com/watch-demo)
|
|
|
|
## Primeiros Passos
|
|
|
|
Vamos passar por um exemplo simples usando CrewAI e integrando ao Langfuse via OpenTelemetry utilizando o OpenLit.
|
|
|
|
### Passo 1: Instale as Dependências
|
|
|
|
```python
|
|
%pip install langfuse openlit crewai crewai_tools
|
|
```
|
|
|
|
### Passo 2: Configure as Variáveis de Ambiente
|
|
|
|
Defina suas chaves de API do Langfuse e configure as opções de exportação do OpenTelemetry para enviar os traces ao Langfuse. Consulte a [Documentação Langfuse OpenTelemetry](https://langfuse.com/docs/opentelemetry/get-started) para mais informações sobre o endpoint Langfuse OpenTelemetry `/api/public/otel` e autenticação.
|
|
|
|
```python
|
|
import os
|
|
|
|
# Obtenha as chaves do seu projeto na página de configurações do projeto: https://cloud.langfuse.com
|
|
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..."
|
|
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
|
|
os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com" # 🇪🇺 Região UE
|
|
# os.environ["LANGFUSE_HOST"] = "https://us.cloud.langfuse.com" # 🇺🇸 Região EUA
|
|
|
|
|
|
# Sua chave OpenAI
|
|
os.environ["OPENAI_API_KEY"] = "sk-proj-..."
|
|
```
|
|
Com as variáveis de ambiente configuradas, agora podemos inicializar o cliente Langfuse. A função get_client() inicializa o cliente Langfuse usando as credenciais fornecidas nas variáveis de ambiente.
|
|
|
|
```python
|
|
from langfuse import get_client
|
|
|
|
langfuse = get_client()
|
|
|
|
# Verificar conexão
|
|
if langfuse.auth_check():
|
|
print("Cliente Langfuse autenticado e pronto!")
|
|
else:
|
|
print("Falha na autenticação. Verifique suas credenciais e host.")
|
|
```
|
|
|
|
### Passo 3: Inicialize o OpenLit
|
|
|
|
Inicialize o SDK de instrumentação OpenTelemetry do OpenLit para começar a capturar traces do OpenTelemetry.
|
|
|
|
```python
|
|
import openlit
|
|
|
|
openlit.init()
|
|
```
|
|
|
|
### Passo 4: Crie uma Aplicação Simples CrewAI
|
|
|
|
Vamos criar uma aplicação simples CrewAI onde múltiplos agentes colaboram para responder à pergunta de um usuário.
|
|
|
|
```python
|
|
from crewai import Agent, Task, Crew
|
|
|
|
from crewai_tools import (
|
|
WebsiteSearchTool
|
|
)
|
|
|
|
web_rag_tool = WebsiteSearchTool()
|
|
|
|
escritor = Agent(
|
|
role="Escritor",
|
|
goal="Você torna a matemática envolvente e compreensível para crianças pequenas através de poesias",
|
|
backstory="Você é especialista em escrever haicais mas não sabe nada de matemática.",
|
|
tools=[web_rag_tool],
|
|
)
|
|
|
|
tarefa = Task(description=("O que é {multiplicação}?"),
|
|
expected_output=("Componha um haicai que inclua a resposta."),
|
|
agent=escritor)
|
|
|
|
equipe = Crew(
|
|
agents=[escritor],
|
|
tasks=[tarefa],
|
|
share_crew=False
|
|
)
|
|
```
|
|
|
|
### Passo 5: Veja os Traces no Langfuse
|
|
|
|
Após rodar o agente, você pode visualizar os traces gerados pela sua aplicação CrewAI no [Langfuse](https://cloud.langfuse.com). Você verá etapas detalhadas das interações do LLM, o que pode ajudar na depuração e otimização do seu agente de IA.
|
|
|
|
|
|
|
|
_[Exemplo público de trace no Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/e2cf380ffc8d47d28da98f136140642b?timestamp=2025-02-05T15%3A12%3A02.717Z&observation=3b32338ee6a5d9af)_
|
|
|
|
## Referências
|
|
|
|
- [Documentação Langfuse OpenTelemetry](https://langfuse.com/docs/opentelemetry/get-started) |