mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-05 15:09:22 +00:00
* 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>
147 lines
4.7 KiB
Plaintext
147 lines
4.7 KiB
Plaintext
---
|
|
title: Ferramenta LlamaIndex
|
|
description: A `LlamaIndexTool` é um wrapper para ferramentas e mecanismos de consulta do LlamaIndex.
|
|
icon: address-book
|
|
mode: "wide"
|
|
---
|
|
|
|
# `LlamaIndexTool`
|
|
|
|
## Descrição
|
|
|
|
A `LlamaIndexTool` foi projetada para ser um wrapper geral em torno das ferramentas e mecanismos de consulta do LlamaIndex, permitindo que você aproveite os recursos do LlamaIndex em pipelines de RAG/agent como ferramentas que podem ser acopladas aos agentes do CrewAI. Essa ferramenta permite integrar de forma transparente as poderosas capacidades de processamento e recuperação de dados do LlamaIndex em seus fluxos de trabalho com o CrewAI.
|
|
|
|
## Instalação
|
|
|
|
Para utilizar esta ferramenta, é necessário instalar o LlamaIndex:
|
|
|
|
```shell
|
|
uv add llama-index
|
|
```
|
|
|
|
## Passos para Começar
|
|
|
|
Para utilizar a `LlamaIndexTool` de forma eficaz, siga os passos abaixo:
|
|
|
|
1. **Instale o LlamaIndex**: Instale o pacote LlamaIndex usando o comando acima.
|
|
2. **Configure o LlamaIndex**: Siga a [documentação do LlamaIndex](https://docs.llamaindex.ai/) para configurar um pipeline de RAG/agent.
|
|
3. **Crie uma Ferramenta ou Mecanismo de Consulta**: Crie uma ferramenta ou mecanismo de consulta do LlamaIndex que você deseja usar com o CrewAI.
|
|
|
|
## Exemplo
|
|
|
|
Os exemplos a seguir demonstram como inicializar a ferramenta a partir de diferentes componentes do LlamaIndex:
|
|
|
|
### A partir de uma ferramenta do LlamaIndex
|
|
|
|
```python Code
|
|
from crewai_tools import LlamaIndexTool
|
|
from crewai import Agent
|
|
from llama_index.core.tools import FunctionTool
|
|
|
|
# Exemplo 1: Inicializando a partir do FunctionTool
|
|
def search_data(query: str) -> str:
|
|
"""Busca por informações nos dados."""
|
|
# Sua implementação aqui
|
|
return f"Results for: {query}"
|
|
|
|
# Criação de um LlamaIndex FunctionTool
|
|
og_tool = FunctionTool.from_defaults(
|
|
search_data,
|
|
name="DataSearchTool",
|
|
description="Search for information in the data"
|
|
)
|
|
|
|
# Envolvendo com a LlamaIndexTool
|
|
tool = LlamaIndexTool.from_tool(og_tool)
|
|
|
|
# Definindo um agente que utiliza a ferramenta
|
|
@agent
|
|
def researcher(self) -> Agent:
|
|
'''
|
|
Este agente usa a LlamaIndexTool para buscar informações.
|
|
'''
|
|
return Agent(
|
|
config=self.agents_config["researcher"],
|
|
tools=[tool]
|
|
)
|
|
```
|
|
|
|
### A partir de Ferramentas do LlamaHub
|
|
|
|
```python Code
|
|
from crewai_tools import LlamaIndexTool
|
|
from llama_index.tools.wolfram_alpha import WolframAlphaToolSpec
|
|
|
|
# Inicializando a partir das ferramentas do LlamaHub
|
|
wolfram_spec = WolframAlphaToolSpec(app_id="your_app_id")
|
|
wolfram_tools = wolfram_spec.to_tool_list()
|
|
tools = [LlamaIndexTool.from_tool(t) for t in wolfram_tools]
|
|
```
|
|
|
|
### A partir de um mecanismo de consulta do LlamaIndex
|
|
|
|
```python Code
|
|
from crewai_tools import LlamaIndexTool
|
|
from llama_index.core import VectorStoreIndex
|
|
from llama_index.core.readers import SimpleDirectoryReader
|
|
|
|
# Carregar documentos
|
|
documents = SimpleDirectoryReader("./data").load_data()
|
|
|
|
# Criar um índice
|
|
index = VectorStoreIndex.from_documents(documents)
|
|
|
|
# Criar um mecanismo de consulta
|
|
query_engine = index.as_query_engine()
|
|
|
|
# Criar uma LlamaIndexTool a partir do mecanismo de consulta
|
|
query_tool = LlamaIndexTool.from_query_engine(
|
|
query_engine,
|
|
name="Company Data Query Tool",
|
|
description="Use this tool to lookup information in company documents"
|
|
)
|
|
```
|
|
|
|
## Métodos da Classe
|
|
|
|
A `LlamaIndexTool` oferece dois métodos de classe principais para criar instâncias:
|
|
|
|
### from_tool
|
|
|
|
Cria uma `LlamaIndexTool` a partir de uma ferramenta do LlamaIndex.
|
|
|
|
```python Code
|
|
@classmethod
|
|
def from_tool(cls, tool: Any, **kwargs: Any) -> "LlamaIndexTool":
|
|
# Implementation details
|
|
```
|
|
|
|
### from_query_engine
|
|
|
|
Cria uma `LlamaIndexTool` a partir de um mecanismo de consulta do LlamaIndex.
|
|
|
|
```python Code
|
|
@classmethod
|
|
def from_query_engine(
|
|
cls,
|
|
query_engine: Any,
|
|
name: Optional[str] = None,
|
|
description: Optional[str] = None,
|
|
return_direct: bool = False,
|
|
**kwargs: Any,
|
|
) -> "LlamaIndexTool":
|
|
# Implementation details
|
|
```
|
|
|
|
## Parâmetros
|
|
|
|
O método `from_query_engine` aceita os seguintes parâmetros:
|
|
|
|
- **query_engine**: Obrigatório. O mecanismo de consulta do LlamaIndex a ser envolvido.
|
|
- **name**: Opcional. O nome da ferramenta.
|
|
- **description**: Opcional. A descrição da ferramenta.
|
|
- **return_direct**: Opcional. Define se deve retornar a resposta diretamente. O padrão é `False`.
|
|
|
|
## Conclusão
|
|
|
|
A `LlamaIndexTool` oferece uma maneira poderosa de integrar as capacidades do LlamaIndex aos agentes do CrewAI. Ao envolver ferramentas e mecanismos de consulta do LlamaIndex, ela permite que os agentes utilizem funcionalidades sofisticadas de recuperação e processamento de dados, aprimorando sua capacidade de trabalhar com fontes de informação complexas. |