Files
crewAI/docs/edge/pt-BR/tools/overview.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

131 lines
4.2 KiB
Plaintext

---
title: "Visão Geral das Ferramentas"
description: "Descubra a vasta biblioteca do CrewAI com mais de 40 ferramentas para potencializar seus agentes de IA"
icon: "toolbox"
mode: "wide"
---
O CrewAI oferece uma biblioteca extensa de ferramentas pré-construídas para aprimorar as capacidades dos seus agentes. De processamento de arquivos a web scraping, consultas em bancos de dados a serviços de IA — temos tudo o que você precisa.
## **Categorias de Ferramentas**
<CardGroup cols={2}>
<Card
title="Arquivo & Documento"
icon="folder-open"
href="/pt-BR/tools/file-document/overview"
color="#3B82F6"
>
Leia, escreva e pesquise em diversos formatos de arquivo, incluindo PDF, DOCX, JSON, CSV e muito mais. Perfeito para fluxos de processamento de documentos.
</Card>
<Card
title="Web Scraping & Navegação"
icon="globe"
href="/pt-BR/tools/web-scraping/overview"
color="#10B981"
>
Extraia dados de sites, automatize interações com navegadores e faça scraping de conteúdo em escala com ferramentas como Firecrawl, Selenium e outras.
</Card>
<Card
title="Pesquisa & Busca"
icon="magnifying-glass"
href="/pt-BR/tools/search-research/overview"
color="#F59E0B"
>
Realize buscas na web, encontre repositórios de código, pesquise conteúdo no YouTube e descubra informações em toda a internet.
</Card>
<Card
title="Banco de Dados & Dados"
icon="database"
href="/pt-BR/tools/database-data/overview"
color="#8B5CF6"
>
Conecte-se a bancos de dados SQL, repositórios vetoriais e data warehouses. Consulte MySQL, PostgreSQL, Snowflake, Qdrant e Weaviate.
</Card>
<Card
title="IA & Aprendizado de Máquina"
icon="brain"
href="/pt-BR/tools/ai-ml/overview"
color="#EF4444"
>
Gere imagens com DALL-E, execute tarefas de visão computacional, integre com LangChain, construa sistemas RAG e aproveite interpretadores de código.
</Card>
<Card
title="Nuvem & Armazenamento"
icon="cloud"
href="/pt-BR/tools/cloud-storage/overview"
color="#06B6D4"
>
Interaja com serviços em nuvem incluindo AWS S3, Amazon Bedrock e outros serviços de armazenamento e IA na nuvem.
</Card>
<Card
title="Automação"
icon="bolt"
href="/pt-BR/tools/automation/overview"
color="#84CC16"
>
Automatize fluxos de trabalho com Apify, Composio e outras plataformas para conectar seus agentes a serviços externos.
</Card>
<Card
title="Integrações"
icon="plug"
href="/pt-BR/tools/tool-integrations/overview"
color="#0891B2"
>
Integre o CrewAI com sistemas externos como Amazon Bedrock e o toolkit de Automação do CrewAI.
</Card>
</CardGroup>
## **Acesso Rápido**
Precisa de uma ferramenta específica? Aqui estão algumas opções populares:
<CardGroup cols={3}>
<Card title="RAG Tool" icon="image" href="/pt-BR/tools/ai-ml/ragtool">
Implemente Geração com Recuperação de Dados (RAG)
</Card>
<Card title="Serper Dev" icon="book-atlas" href="/pt-BR/tools/search-research/serperdevtool">
API de busca do Google
</Card>
<Card title="File Read" icon="file" href="/pt-BR/tools/file-document/filereadtool">
Leia qualquer tipo de arquivo
</Card>
<Card title="Scrape Website" icon="globe" href="/pt-BR/tools/web-scraping/scrapewebsitetool">
Extraia conteúdo da web
</Card>
<Card title="Code Interpreter" icon="code" href="/pt-BR/tools/ai-ml/codeinterpretertool">
Execute código Python
</Card>
<Card title="S3 Reader" icon="cloud" href="/pt-BR/tools/cloud-storage/s3readertool">
Acesse arquivos no AWS S3
</Card>
</CardGroup>
## **Primeiros Passos**
Para usar qualquer ferramenta em seu projeto CrewAI:
1. **Importe** a ferramenta na configuração da sua crew
2. **Adicione** à lista de ferramentas do seu agente
3. **Configure** as chaves de API ou ajustes necessários
```python
from crewai_tools import FileReadTool, SerperDevTool
# Adicione as ferramentas ao seu agente
agent = Agent(
role="Research Analyst",
tools=[FileReadTool(), SerperDevTool()],
# ... outrAs configurações
)
```
Pronto para explorar? Escolha uma categoria acima para descobrir as ferramentas que se encaixam no seu caso de uso!