Knowledge

Visão Geral

Knowledge no CrewAI é um sistema poderoso que permite que agentes de IA acessem e utilizem fontes de informação externas durante suas tarefas. Pense nisso como dar aos seus agentes uma biblioteca de referência que eles podem consultar enquanto trabalham.

Exemplos de Início Rápido

Exemplo Básico de Knowledge com String

from crewai import Agent, Task, Crew, Process, LLM
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource

# Create a knowledge source
content = "Users name is John. He is 30 years old and lives in San Francisco."
string_source = StringKnowledgeSource(content=content)

# Create an LLM with a temperature of 0 to ensure deterministic outputs
llm = LLM(model="gpt-4o-mini", temperature=0)

# Create an agent with the knowledge store
agent = Agent(
    role="Sobre o Usuário",
    goal="Você sabe tudo sobre o usuário.",
    backstory="Você é mestre em entender pessoas e suas preferências.",
    verbose=True,
    allow_delegation=False,
    llm=llm,
)

task = Task(
    description="Responda às seguintes perguntas sobre o usuário: {question}",
    expected_output="Uma resposta para a pergunta.",
    agent=agent,
)

crew = Crew(
    agents=[agent],
    tasks=[task],
    verbose=True,
    process=Process.sequential,
    knowledge_sources=[string_source], # Enable knowledge by adding the sources here
)

result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})

Exemplo de Knowledge com Conteúdo Web

from crewai import LLM, Agent, Crew, Process, Task
from crewai.knowledge.source.crew_docling_source import CrewDoclingSource

# Create a knowledge source from web content
content_source = CrewDoclingSource(
    file_paths=[
        "https://lilianweng.github.io/posts/2024-11-28-reward-hacking",
        "https://lilianweng.github.io/posts/2024-07-07-hallucination",
    ],
)

# Create an LLM with a temperature of 0 to ensure deterministic outputs
llm = LLM(model="gpt-4o-mini", temperature=0)

# Create an agent with the knowledge store
agent = Agent(
    role="Sobre artigos",
    goal="Você sabe tudo sobre os artigos.",
    backstory="Você é mestre em entender artigos e seus conteúdos.",
    verbose=True,
    allow_delegation=False,
    llm=llm,
)

task = Task(
    description="Responda às seguintes perguntas sobre os artigos: {question}",
    expected_output="Uma resposta para a pergunta.",
    agent=agent,
)

crew = Crew(
    agents=[agent],
    tasks=[task],
    verbose=True,
    process=Process.sequential,
    knowledge_sources=[content_source],
)

result = crew.kickoff(
    inputs={"question": "What is the reward hacking paper about? Be sure to provide sources."}
)

Fontes de Knowledge Suportadas

O CrewAI suporta vários tipos de fontes de knowledge prontas para uso:

Fontes de Texto

Strings brutas
Arquivos de texto (.txt)
Documentos PDF

Dados Estruturados

Arquivos CSV
Planilhas Excel
Documentos JSON

Fonte de Knowledge de Arquivo de Texto

from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource

text_source = TextFileKnowledgeSource(
    file_paths=["document.txt", "another.txt"]
)

Fonte de Knowledge PDF

from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource

pdf_source = PDFKnowledgeSource(
    file_paths=["document.pdf", "another.pdf"]
)

Fonte de Knowledge CSV

from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource

csv_source = CSVKnowledgeSource(
    file_paths=["data.csv"]
)

Fonte de Knowledge Excel

from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource

excel_source = ExcelKnowledgeSource(
    file_paths=["spreadsheet.xlsx"]
)

Fonte de Knowledge JSON

from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource

json_source = JSONKnowledgeSource(
    file_paths=["data.json"]
)

Knowledge de Agente vs Crew: Guia Completo

Como a Inicialização de Knowledge Realmente Funciona

Aqui está exatamente o que acontece quando você usa knowledge:

Knowledge no Nível do Agente (Independente)

from crewai import Agent, Task, Crew
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource

# Agent with its own knowledge - NO crew knowledge needed
specialist_knowledge = StringKnowledgeSource(
    content="Specialized technical information for this agent only"
)

specialist_agent = Agent(
    role="Especialista Técnico",
    goal="Fornecer expertise técnica",
    backstory="Especialista em domínios técnicos especializados",
    knowledge_sources=[specialist_knowledge]  # Conhecimento específico do agente
)

task = Task(
    description="Responda perguntas técnicas",
    agent=specialist_agent,
    expected_output="Resposta técnica"
)

# No crew-level knowledge required
crew = Crew(
    agents=[specialist_agent],
    tasks=[task]
)

result = crew.kickoff()  # Agent knowledge works independently

O Que Acontece Durante `crew.kickoff()`

Quando você chama crew.kickoff(), aqui está a sequência exata:

# During kickoff
for agent in self.agents:
    agent.crew = self  # Agent gets reference to crew
    agent.set_knowledge(crew_embedder=self.embedder)  # Agent knowledge initialized
    agent.create_agent_executor()

Independência de Armazenamento

Cada nível de knowledge usa coleções de armazenamento independentes:

# Agent knowledge storage
agent_collection_name = agent.role  # e.g., "Especialista Técnico"

# Crew knowledge storage
crew_collection_name = "crew"

# Both stored in same ChromaDB instance but different collections
# Path: ~/.local/share/CrewAI/{project}/knowledge/
#   ├── crew/                    # Crew knowledge collection
#   ├── Especialista Técnico/    # Agent knowledge collection
#   └── Another Agent Role/      # Another agent's collection

Exemplos Completos Funcionais

Exemplo 1: Knowledge Apenas do Agente

from crewai import Agent, Task, Crew
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource

# Agent-specific knowledge
agent_knowledge = StringKnowledgeSource(
    content="Agent-specific information that only this agent needs"
)

agent = Agent(
    role="Especialista",
    goal="Use specialized knowledge",
    backstory="Expert with specific knowledge",
    knowledge_sources=[agent_knowledge],
    embedder={  # Agent can have its own embedder
        "provider": "openai",
        "config": {"model": "text-embedding-3-small"}
    }
)

task = Task(
    description="Answer using your specialized knowledge",
    agent=agent,
    expected_output="Answer based on agent knowledge"
)

# No crew knowledge needed
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()  # Works perfectly

Exemplo 2: Knowledge Tanto do Agente Quanto da Crew

# Crew-wide knowledge (shared by all agents)
crew_knowledge = StringKnowledgeSource(
    content="Company policies and general information for all agents"
)

# Agent-specific knowledge
specialist_knowledge = StringKnowledgeSource(
    content="Technical specifications only the specialist needs"
)

specialist = Agent(
    role="Especialista Técnico",
    goal="Fornecer expertise técnica",
    backstory="Especialista em domínios técnicos especializados",
    knowledge_sources=[specialist_knowledge]  # Conhecimento específico do agente
)

generalist = Agent(
    role="General Assistant",
    goal="Provide general assistance",
    backstory="General helper"
    # No agent-specific knowledge
)

crew = Crew(
    agents=[specialist, generalist],
    tasks=[...],
    knowledge_sources=[crew_knowledge]  # Crew-wide knowledge
)

# Result:
# - specialist gets: crew_knowledge + specialist_knowledge
# - generalist gets: crew_knowledge only

Exemplo 3: Múltiplos Agentes com Knowledge Diferente

# Different knowledge for different agents
sales_knowledge = StringKnowledgeSource(content="Sales procedures and pricing")
tech_knowledge = StringKnowledgeSource(content="Technical documentation")
support_knowledge = StringKnowledgeSource(content="Support procedures")

sales_agent = Agent(
    role="Sales Representative",
    knowledge_sources=[sales_knowledge],
    embedder={"provider": "openai", "config": {"model": "text-embedding-3-small"}}
)

tech_agent = Agent(
    role="Technical Expert",
    knowledge_sources=[tech_knowledge],
    embedder={"provider": "ollama", "config": {"model": "mxbai-embed-large"}}
)

support_agent = Agent(
    role="Support Specialist",
    knowledge_sources=[support_knowledge]
    # Will use crew embedder as fallback
)

crew = Crew(
    agents=[sales_agent, tech_agent, support_agent],
    tasks=[...],
    embedder={  # Fallback embedder for agents without their own
        "provider": "google",
        "config": {"model": "text-embedding-004"}
    }
)

# Each agent gets only their specific knowledge
# Each can use different embedding providers

Configuração de Knowledge

Você pode configurar a configuração de knowledge para a crew ou agente.

from crewai.knowledge.knowledge_config import KnowledgeConfig

knowledge_config = KnowledgeConfig(results_limit=10, score_threshold=0.5)

agent = Agent(
    ...
    knowledge_config=knowledge_config
)

Parâmetros de Knowledge Suportados

sources List[BaseKnowledgeSource] required

Lista de fontes de knowledge que fornecem conteúdo para ser armazenado e consultado. Pode incluir PDF, CSV, Excel, JSON, arquivos de texto ou conteúdo de string.

collection_name str

Nome da coleção onde o knowledge será armazenado. Usado para identificar diferentes conjuntos de knowledge. Padrão é “knowledge” se não fornecido.

storage Optional[KnowledgeStorage]

Configuração de armazenamento personalizada para gerenciar como o knowledge é armazenado e recuperado. Se não fornecido, um armazenamento padrão será criado.

Transparência do Armazenamento de Knowledge

Onde o CrewAI Armazena Arquivos de Knowledge

Por padrão, o CrewAI usa o mesmo sistema de armazenamento que a memória, armazenando knowledge em diretórios específicos da plataforma:

Localizações de Armazenamento Padrão por Plataforma

macOS:

~/Library/Application Support/CrewAI/{project_name}/
└── knowledge/                    # Knowledge ChromaDB files
    ├── chroma.sqlite3           # ChromaDB metadata
    ├── {collection_id}/         # Vector embeddings
    └── knowledge_{collection}/  # Named collections

Linux:

~/.local/share/CrewAI/{project_name}/
└── knowledge/
    ├── chroma.sqlite3
    ├── {collection_id}/
    └── knowledge_{collection}/

Windows:

C:\Users\{username}\AppData\Local\CrewAI\{project_name}\
└── knowledge\
    ├── chroma.sqlite3
    ├── {collection_id}\
    └── knowledge_{collection}\

Encontrando Sua Localização de Armazenamento de Knowledge

Para ver exatamente onde o CrewAI está armazenando seus arquivos de knowledge:

from crewai.utilities.paths import db_storage_path
import os

# Get the knowledge storage path
knowledge_path = os.path.join(db_storage_path(), "knowledge")
print(f"Knowledge storage location: {knowledge_path}")

# List knowledge collections and files
if os.path.exists(knowledge_path):
    print("\nKnowledge storage contents:")
    for item in os.listdir(knowledge_path):
        item_path = os.path.join(knowledge_path, item)
        if os.path.isdir(item_path):
            print(f"📁 Collection: {item}/")
            # Show collection contents
            try:
                for subitem in os.listdir(item_path):
                    print(f"   └── {subitem}")
            except PermissionError:
                print(f"   └── (permission denied)")
        else:
            print(f"📄 {item}")
else:
    print("No knowledge storage found yet.")

Controlando Localizações de Armazenamento de Knowledge

Opção 1: Variável de Ambiente (Recomendado)

import os
from crewai import Crew

# Set custom storage location for all CrewAI data
os.environ["CREWAI_STORAGE_DIR"] = "./my_project_storage"

# All knowledge will now be stored in ./my_project_storage/knowledge/
crew = Crew(
    agents=[...],
    tasks=[...],
    knowledge_sources=[...]
)

Opção 2: Armazenamento de Knowledge Personalizado

from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource

# Create custom storage with specific embedder
custom_storage = KnowledgeStorage(
    embedder={
        "provider": "ollama",
        "config": {"model": "mxbai-embed-large"}
    },
    collection_name="my_custom_knowledge"
)

# Use with knowledge sources
knowledge_source = StringKnowledgeSource(
    content="Your knowledge content here"
)
knowledge_source.storage = custom_storage

Opção 3: Armazenamento de Knowledge Específico do Projeto

import os
from pathlib import Path

# Store knowledge in project directory
project_root = Path(__file__).parent
knowledge_dir = project_root / "knowledge_storage"

os.environ["CREWAI_STORAGE_DIR"] = str(knowledge_dir)

# Now all knowledge will be stored in your project directory

Comportamento Padrão do Provedor de Embedding

Entendendo o Comportamento Padrão

from crewai import Agent, Crew, LLM
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource

# When using Claude as your LLM...
agent = Agent(
    role="Researcher",
    goal="Research topics",
    backstory="Expert researcher",
    llm=LLM(provider="anthropic", model="claude-3-sonnet")  # Using Claude
)

# CrewAI will still use OpenAI embeddings by default for knowledge
# This ensures consistency but may not match your LLM provider preference
knowledge_source = StringKnowledgeSource(content="Research data...")

crew = Crew(
    agents=[agent],
    tasks=[...],
    knowledge_sources=[knowledge_source]
    # Default: Uses OpenAI embeddings even with Claude LLM
)

Personalizando Provedores de Embedding de Knowledge

# Option 1: Use Voyage AI (recommended by Anthropic for Claude users)
crew = Crew(
    agents=[agent],
    tasks=[...],
    knowledge_sources=[knowledge_source],
    embedder={
        "provider": "voyageai",  # Recommended for Claude users
        "config": {
            "api_key": "your-voyage-api-key",
            "model": "voyage-3"  # or "voyage-3-large" for best quality
        }
    }
)

# Option 2: Use local embeddings (no external API calls)
crew = Crew(
    agents=[agent],
    tasks=[...],
    knowledge_sources=[knowledge_source],
    embedder={
        "provider": "ollama",
        "config": {
            "model": "mxbai-embed-large",
            "url": "http://localhost:11434/api/embeddings"
        }
    }
)

# Option 3: Agent-level embedding customization
agent = Agent(
    role="Researcher",
    goal="Research topics",
    backstory="Expert researcher",
    knowledge_sources=[knowledge_source],
    embedder={
        "provider": "google",
        "config": {
            "model": "models/text-embedding-004",
            "api_key": "your-google-key"
        }
    }
)

Configurando Embeddings do Azure OpenAI

Ao usar embeddings do Azure OpenAI:

Certifique-se de implantar o modelo de embedding na plataforma Azure primeiro
Então você precisa usar a seguinte configuração:

agent = Agent(
    role="Researcher",
    goal="Research topics",
    backstory="Expert researcher",
    knowledge_sources=[knowledge_source],
    embedder={
        "provider": "azure",
        "config": {
            "api_key": "your-azure-api-key",
            "model": "text-embedding-ada-002", # change to the model you are using and is deployed in Azure
            "api_base": "https://your-azure-endpoint.openai.azure.com/",
            "api_version": "2024-02-01"
        }
    }
)

Recursos Avançados

Reescrita de Consulta

O CrewAI implementa um mecanismo inteligente de reescrita de consulta para otimizar a recuperação de knowledge. Quando um agente precisa pesquisar nas fontes de knowledge, o prompt da tarefa bruto é automaticamente transformado em uma consulta de pesquisa mais eficaz.

Como a Reescrita de Consulta Funciona

Quando um agente executa uma tarefa com fontes de knowledge disponíveis, o método _get_knowledge_search_query é acionado
O LLM do agente é usado para transformar o prompt original da tarefa em uma consulta de pesquisa otimizada
Esta consulta otimizada é então usada para recuperar informações relevantes das fontes de knowledge

Benefícios da Reescrita de Consulta

Precisão de Recuperação Melhorada

Ao focar em conceitos-chave e remover conteúdo irrelevante, a reescrita de consulta ajuda a recuperar informações mais relevantes.

Consciência de Contexto

As consultas reescritas são projetadas para ser mais específicas e conscientes do contexto para recuperação de banco de dados vetorial.

Exemplo

# Original task prompt
task_prompt = "Answer the following questions about the user's favorite movies: What movie did John watch last week? Format your answer in JSON."

# Behind the scenes, this might be rewritten as:
rewritten_query = "What movies did John watch last week?"

A consulta reescrita é mais focada na necessidade de informação principal e remove instruções irrelevantes sobre formatação de saída.

Eventos de Knowledge

O CrewAI emite eventos durante o processo de recuperação de knowledge que você pode escutar usando o sistema de eventos. Esses eventos permitem que você monitore, depure e analise como o knowledge está sendo recuperado e usado pelos seus agentes.

Eventos de Knowledge Disponíveis

KnowledgeRetrievalStartedEvent: Emitido quando um agente começa a recuperar knowledge das fontes
KnowledgeRetrievalCompletedEvent: Emitido quando a recuperação de knowledge é concluída, incluindo a consulta usada e o conteúdo recuperado
KnowledgeQueryStartedEvent: Emitido quando uma consulta às fontes de knowledge começa
KnowledgeQueryCompletedEvent: Emitido quando uma consulta é concluída com sucesso
KnowledgeQueryFailedEvent: Emitido quando uma consulta às fontes de knowledge falha
KnowledgeSearchQueryFailedEvent: Emitido quando uma consulta de pesquisa falha

Exemplo: Monitorando Recuperação de Knowledge

from crewai.events import (
    KnowledgeRetrievalStartedEvent,
    KnowledgeRetrievalCompletedEvent,
    BaseEventListener,
)

class KnowledgeMonitorListener(BaseEventListener):
    def setup_listeners(self, crewai_event_bus):
        @crewai_event_bus.on(KnowledgeRetrievalStartedEvent)
        def on_knowledge_retrieval_started(source, event):
            print(f"Agent '{event.agent.role}' started retrieving knowledge")

        @crewai_event_bus.on(KnowledgeRetrievalCompletedEvent)
        def on_knowledge_retrieval_completed(source, event):
            print(f"Agent '{event.agent.role}' completed knowledge retrieval")
            print(f"Query: {event.query}")
            print(f"Retrieved {len(event.retrieved_knowledge)} knowledge chunks")

# Create an instance of your listener
knowledge_monitor = KnowledgeMonitorListener()

Para mais informações sobre como usar eventos, consulte a documentação Event Listeners.

Fontes de Knowledge Personalizadas

O CrewAI permite que você crie fontes de knowledge personalizadas para qualquer tipo de dados estendendo a classe BaseKnowledgeSource. Vamos criar um exemplo prático que busca e processa artigos de notícias espaciais.

Exemplo de Fonte de Knowledge de Notícias Espaciais

Code

from crewai import Agent, Task, Crew, Process, LLM
from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
import requests
from datetime import datetime
from typing import Dict, Any
from pydantic import BaseModel, Field

class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
    """Knowledge source that fetches data from Space News API."""

    api_endpoint: str = Field(description="API endpoint URL")
    limit: int = Field(default=10, description="Number of articles to fetch")

    def load_content(self) -> Dict[Any, str]:
        """Fetch and format space news articles."""
        try:
            response = requests.get(
                f"{self.api_endpoint}?limit={self.limit}"
            )
            response.raise_for_status()

            data = response.json()
            articles = data.get('results', [])

            formatted_data = self.validate_content(articles)
            return {self.api_endpoint: formatted_data}
        except Exception as e:
            raise ValueError(f"Failed to fetch space news: {str(e)}")

    def validate_content(self, articles: list) -> str:
        """Format articles into readable text."""
        formatted = "Space News Articles:\n\n"
        for article in articles:
            formatted += f"""
                Title: {article['title']}
                Published: {article['published_at']}
                Summary: {article['summary']}
                News Site: {article['news_site']}
                URL: {article['url']}
                -------------------"""
        return formatted

    def add(self) -> None:
        """Process and store the articles."""
        content = self.load_content()
        for _, text in content.items():
            chunks = self._chunk_text(text)
            self.chunks.extend(chunks)

        self._save_documents()

# Create knowledge source
recent_news = SpaceNewsKnowledgeSource(
    api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
    limit=10,
)

# Create specialized agent
space_analyst = Agent(
    role="Space News Analyst",
    goal="Answer questions about space news accurately and comprehensively",
    backstory="""You are a space industry analyst with expertise in space exploration,
    satellite technology, and space industry trends. You excel at answering questions
    about space news and providing detailed, accurate information.""",
    knowledge_sources=[recent_news],
    llm=LLM(model="gpt-4", temperature=0.0)
)

# Create task that handles user questions
analysis_task = Task(
    description="Answer this question about space news: {user_question}",
    expected_output="A detailed answer based on the recent space news articles",
    agent=space_analyst
)

# Create and run the crew
crew = Crew(
    agents=[space_analyst],
    tasks=[analysis_task],
    verbose=True,
    process=Process.sequential
)

# Example usage
result = crew.kickoff(
    inputs={"user_question": "What are the latest developments in space exploration?"}
)

# Agent: Space News Analyst
## Task: Answer this question about space news: What are the latest developments in space exploration?


# Agent: Space News Analyst
## Final Answer:
The latest developments in space exploration, based on recent space news articles, include the following:

1. SpaceX has received the final regulatory approvals to proceed with the second integrated Starship/Super Heavy launch, scheduled for as soon as the morning of Nov. 17, 2023. This is a significant step in SpaceX's ambitious plans for space exploration and colonization. [Source: SpaceNews](https://spacenews.com/starship-cleared-for-nov-17-launch/)

2. SpaceX has also informed the US Federal Communications Commission (FCC) that it plans to begin launching its first next-generation Starlink Gen2 satellites. This represents a major upgrade to the Starlink satellite internet service, which aims to provide high-speed internet access worldwide. [Source: Teslarati](https://www.teslarati.com/spacex-first-starlink-gen2-satellite-launch-2022/)

3. AI startup Synthetaic has raised $15 million in Series B funding. The company uses artificial intelligence to analyze data from space and air sensors, which could have significant applications in space exploration and satellite technology. [Source: SpaceNews](https://spacenews.com/ai-startup-synthetaic-raises-15-million-in-series-b-funding/)

4. The Space Force has formally established a unit within the U.S. Indo-Pacific Command, marking a permanent presence in the Indo-Pacific region. This could have significant implications for space security and geopolitics. [Source: SpaceNews](https://spacenews.com/space-force-establishes-permanent-presence-in-indo-pacific-region/)

5. Slingshot Aerospace, a space tracking and data analytics company, is expanding its network of ground-based optical telescopes to increase coverage of low Earth orbit. This could improve our ability to track and analyze objects in low Earth orbit, including satellites and space debris. [Source: SpaceNews](https://spacenews.com/slingshots-space-tracking-network-to-extend-coverage-of-low-earth-orbit/)

6. The National Natural Science Foundation of China has outlined a five-year project for researchers to study the assembly of ultra-large spacecraft. This could lead to significant advancements in spacecraft technology and space exploration capabilities. [Source: SpaceNews](https://spacenews.com/china-researching-challenges-of-kilometer-scale-ultra-large-spacecraft/)

7. The Center for AEroSpace Autonomy Research (CAESAR) at Stanford University is focusing on spacecraft autonomy. The center held a kickoff event on May 22, 2024, to highlight the industry, academia, and government collaboration it seeks to foster. This could lead to significant advancements in autonomous spacecraft technology. [Source: SpaceNews](https://spacenews.com/stanford-center-focuses-on-spacecraft-autonomy/)

Depuração e Solução de Problemas

Depurando Problemas de Knowledge

Verificar Inicialização de Knowledge do Agente

from crewai import Agent, Crew, Task
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource

knowledge_source = StringKnowledgeSource(content="Test knowledge")

agent = Agent(
    role="Test Agent",
    goal="Test knowledge",
    backstory="Testing",
    knowledge_sources=[knowledge_source]
)

crew = Crew(agents=[agent], tasks=[Task(...)])

# Before kickoff - knowledge not initialized
print(f"Before kickoff - Agent knowledge: {getattr(agent, 'knowledge', None)}")

crew.kickoff()

# After kickoff - knowledge initialized
print(f"After kickoff - Agent knowledge: {agent.knowledge}")
print(f"Agent knowledge collection: {agent.knowledge.storage.collection_name}")
print(f"Number of sources: {len(agent.knowledge.sources)}")

Verificar Localizações de Armazenamento de Knowledge

import os
from crewai.utilities.paths import db_storage_path

# Check storage structure
storage_path = db_storage_path()
knowledge_path = os.path.join(storage_path, "knowledge")

if os.path.exists(knowledge_path):
    print("Knowledge collections found:")
    for collection in os.listdir(knowledge_path):
        collection_path = os.path.join(knowledge_path, collection)
        if os.path.isdir(collection_path):
            print(f"  - {collection}/")
            # Show collection contents
            for item in os.listdir(collection_path):
                print(f"    └── {item}")

Testar Recuperação de Knowledge

# Test agent knowledge retrieval
if hasattr(agent, 'knowledge') and agent.knowledge:
    test_query = ["test query"]
    results = agent.knowledge.query(test_query)
    print(f"Agent knowledge results: {len(results)} documents found")

    # Test crew knowledge retrieval (if exists)
    if hasattr(crew, 'knowledge') and crew.knowledge:
        crew_results = crew.query_knowledge(test_query)
        print(f"Crew knowledge results: {len(crew_results)} documents found")

Inspecionar Coleções de Knowledge

import chromadb
from crewai.utilities.paths import db_storage_path
import os

# Connect to CrewAI's knowledge ChromaDB
knowledge_path = os.path.join(db_storage_path(), "knowledge")

if os.path.exists(knowledge_path):
    client = chromadb.PersistentClient(path=knowledge_path)
    collections = client.list_collections()

    print("Knowledge Collections:")
    for collection in collections:
        print(f"  - {collection.name}: {collection.count()} documents")

        # Sample a few documents to verify content
        if collection.count() > 0:
            sample = collection.peek(limit=2)
            print(f"    Sample content: {sample['documents'][0][:100]}...")
else:
    print("No knowledge storage found")

Verificar Processamento de Knowledge

from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource

# Create a test knowledge source
test_source = StringKnowledgeSource(
    content="Test knowledge content for debugging",
    chunk_size=100,  # Small chunks for testing
    chunk_overlap=20
)

# Check chunking behavior
print(f"Original content length: {len(test_source.content)}")
print(f"Chunk size: {test_source.chunk_size}")
print(f"Chunk overlap: {test_source.chunk_overlap}")

# Process and inspect chunks
test_source.add()
print(f"Number of chunks created: {len(test_source.chunks)}")
for i, chunk in enumerate(test_source.chunks[:3]):  # Show first 3 chunks
    print(f"Chunk {i+1}: {chunk[:50]}...")

Problemas Comuns de Armazenamento de Knowledge

Erros “Arquivo não encontrado”:

# Ensure files are in the correct location
from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
import os

knowledge_dir = KNOWLEDGE_DIRECTORY  # Usually "knowledge"
file_path = os.path.join(knowledge_dir, "your_file.pdf")

if not os.path.exists(file_path):
    print(f"File not found: {file_path}")
    print(f"Current working directory: {os.getcwd()}")
    print(f"Expected knowledge directory: {os.path.abspath(knowledge_dir)}")

Erros “Incompatibilidade de dimensão de embedding”:

# This happens when switching embedding providers
# Reset knowledge storage to clear old embeddings
crew.reset_memories(command_type='knowledge')

# Or use consistent embedding providers
crew = Crew(
    agents=[...],
    tasks=[...],
    knowledge_sources=[...],
    embedder={"provider": "openai", "config": {"model": "text-embedding-3-small"}}
)

Erros “ChromaDB permissão negada”:

# Fix storage permissions
chmod -R 755 ~/.local/share/CrewAI/

Knowledge não persistindo entre execuções:

# Verify storage location consistency
import os
from crewai.utilities.paths import db_storage_path

print("CREWAI_STORAGE_DIR:", os.getenv("CREWAI_STORAGE_DIR"))
print("Computed storage path:", db_storage_path())
print("Knowledge path:", os.path.join(db_storage_path(), "knowledge"))

Comandos de Reset de Knowledge

# Reset only agent-specific knowledge
crew.reset_memories(command_type='agent_knowledge')

# Reset both crew and agent knowledge
crew.reset_memories(command_type='knowledge')

# CLI commands
# crewai reset-memories --agent-knowledge  # Agent knowledge only
# crewai reset-memories --knowledge        # All knowledge

Limpando Knowledge

Se você precisar limpar o knowledge armazenado no CrewAI, você pode usar o comando crewai reset-memories com a opção --knowledge.

crewai reset-memories --knowledge

Isso é útil quando você atualizou suas fontes de knowledge e quer garantir que os agentes estejam usando as informações mais recentes.

Melhores Práticas

Organização de Conteúdo

Mantenha tamanhos de chunk apropriados para seu tipo de conteúdo
Considere sobreposição de conteúdo para preservação de contexto
Organize informações relacionadas em fontes de knowledge separadas

Dicas de Performance

Ajuste tamanhos de chunk baseado na complexidade do conteúdo
Configure modelos de embedding apropriados
Considere usar provedores de embedding locais para processamento mais rápido

Knowledge de Uma Vez

Com a estrutura de arquivo típica fornecida pelo CrewAI, as fontes de knowledge são incorporadas toda vez que o kickoff é acionado.
Se as fontes de knowledge são grandes, isso leva à ineficiência e latência aumentada, pois os mesmos dados são incorporados cada vez.
Para resolver isso, inicialize diretamente o parâmetro knowledge em vez do parâmetro knowledge_sources.
Link para a issue para ter a ideia completa Github Issue

Gerenciamento de Knowledge

Use knowledge no nível do agente para informações específicas do papel
Use knowledge no nível da crew para informações compartilhadas que todos os agentes precisam
Configure embedders no nível do agente se você precisar de estratégias de embedding diferentes
Use nomenclatura consistente de coleção mantendo papéis de agente descritivos
Teste a inicialização de knowledge verificando agent.knowledge após o kickoff
Monitore localizações de armazenamento para entender onde o knowledge está armazenado
Reset knowledge apropriadamente usando os tipos de comando corretos

Melhores Práticas de Produção

Configure CREWAI_STORAGE_DIR para uma localização conhecida em produção
Escolha provedores de embedding explícitos para corresponder à sua configuração de LLM e evitar conflitos de chave de API
Monitore o tamanho do armazenamento de knowledge conforme ele cresce com adições de documentos
Organize fontes de knowledge por domínio ou propósito usando nomes de coleção
Inclua diretórios de knowledge em suas estratégias de backup e implantação
Configure permissões de arquivo apropriadas para arquivos de knowledge e diretórios de armazenamento
Use variáveis de ambiente para chaves de API e configuração sensível