mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-01 21:28:10 +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>
78 lines
2.9 KiB
Plaintext
78 lines
2.9 KiB
Plaintext
---
|
|
title: Busca RAG em XML
|
|
description: O `XMLSearchTool` foi projetado para realizar uma busca RAG (Geração Aumentada por Recuperação) dentro do conteúdo de um arquivo XML.
|
|
icon: file-xml
|
|
mode: "wide"
|
|
---
|
|
|
|
# `XMLSearchTool`
|
|
|
|
<Note>
|
|
Ainda estamos trabalhando na melhoria das ferramentas, então pode haver comportamentos inesperados ou mudanças no futuro.
|
|
</Note>
|
|
|
|
## Descrição
|
|
|
|
O XMLSearchTool é uma ferramenta RAG de ponta, desenvolvida para realizar buscas semânticas em arquivos XML.
|
|
Ideal para usuários que precisam analisar e extrair informações do conteúdo XML de forma eficiente, esta ferramenta permite inserir uma consulta de busca e um caminho opcional para o arquivo XML.
|
|
Ao especificar um caminho de arquivo XML, o usuário pode direcionar sua busca de forma mais precisa ao conteúdo daquele arquivo, obtendo assim resultados mais relevantes.
|
|
|
|
## Instalação
|
|
|
|
Para começar a usar o XMLSearchTool, é necessário instalar primeiro o pacote crewai_tools. Isso pode ser feito facilmente com o seguinte comando:
|
|
|
|
```shell
|
|
pip install 'crewai[tools]'
|
|
```
|
|
|
|
## Exemplo
|
|
|
|
Aqui estão dois exemplos demonstrando como usar o XMLSearchTool.
|
|
O primeiro exemplo mostra a busca dentro de um arquivo XML específico, enquanto o segundo exemplo ilustra como iniciar uma busca sem definir previamente um caminho XML, oferecendo flexibilidade no escopo da busca.
|
|
|
|
```python Code
|
|
from crewai_tools import XMLSearchTool
|
|
|
|
# Permite que agentes busquem no conteúdo de qualquer arquivo XML
|
|
# conforme aprendem seus caminhos durante a execução
|
|
tool = XMLSearchTool()
|
|
|
|
# OU
|
|
|
|
# Inicializa a ferramenta com um caminho específico para arquivo XML
|
|
# para busca exclusiva dentro desse documento
|
|
tool = XMLSearchTool(xml='path/to/your/xmlfile.xml')
|
|
```
|
|
|
|
## Argumentos
|
|
|
|
- `xml`: Este é o caminho para o arquivo XML que você deseja buscar.
|
|
Este parâmetro é opcional durante a inicialização da ferramenta, mas deve ser fornecido ou na inicialização ou como parte dos argumentos do método `run` para executar a busca.
|
|
|
|
## Modelo customizado e embeddings
|
|
|
|
Por padrão, a ferramenta utiliza a OpenAI tanto para embeddings quanto para sumarização. Para personalizar o modelo, você pode usar um dicionário de configuração conforme o exemplo a seguir:
|
|
|
|
```python Code
|
|
from chromadb.config import Settings
|
|
|
|
tool = XMLSearchTool(
|
|
config={
|
|
"embedding_model": {
|
|
"provider": "openai",
|
|
"config": {
|
|
"model": "text-embedding-3-small",
|
|
# "api_key": "sk-...",
|
|
},
|
|
},
|
|
"vectordb": {
|
|
"provider": "chromadb", # ou "qdrant"
|
|
"config": {
|
|
# "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
|
|
# from qdrant_client.models import VectorParams, Distance
|
|
# "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
|
|
}
|
|
},
|
|
}
|
|
)
|
|
``` |