Using trained data

[danielmeloalencar]

Feature Area

Documentation

Is your feature request related to a an existing bug? Please link it here.

N/A

Describe the solution you'd like

N/A

Describe alternatives you've considered

I created this training script according to the documentation, but I don't know how to use the trained data after training. I think it's important to add something about this in the documentation.

Additional context

How to use trained data???

from crewai import Agent, Task, Crew, Process, LLM


olllama = LLM(
  model="ollama/qwen2.5-coder:latest",
  base_url="http://localhost:11434",
)

agente_escritor = Agent(
  role='Escritor de Cartas de Amor',
  goal='Escreva uma carta de amor para {nome_destinatario}, expressando os seguintes sentimentos: {sentimentos}. Assine como {meu_nome}',
  verbose=True,
  memory=True,
  llm=olllama,
  backstory='Você é um poeta experiente, '
            'conhecido por sua habilidade de expressar sentimentos '
            'profundos em palavras'
)

tarefa_escrita_carta = Task(
  description='Escrever uma carta de amor',
  expected_output='Carta de amor escrita com palavras sinceras e sentimentos profundos em português do Brasil', 
  agent=agente_escritor,
  output_file='carta_de_amor.txt'
)

equipe = Crew(
  agents=[agente_escritor],
  tasks=[tarefa_escrita_carta],
  process = Process.sequential
)

nome_destinatario = "Maria"
meu_nome = "João"
sentimentos = "amor, paixão, admiração"

inputs={'nome_destinatario':nome_destinatario, 'sentimentos':sentimentos, 'meu_nome':meu_nome}

n_iterations = 1
filename = "your_model.pkl"

try:
    equipe.train(
      n_iterations=n_iterations, 
      inputs=inputs, 
      filename=filename
    )

except Exception as e:
    raise Exception(f"An error occurred while training the crew: {e}")

Willingness to Contribute

No, I'm just suggesting the idea

[theCyberTech]

It's automatically use it on the next run

[danielmeloalencar]

So it didn't work for me.
Training programmatically doesn't work.