Assistant is a large language model trained by OpenAI. Assistant is designed to…
- User
System: Assistant is a large language model trained by OpenAI.
Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.
Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.
Overall, Assistant is a powerful system that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist. However, above all else, all responses must adhere to the format of RESPONSE FORMAT INSTRUCTIONS. Human: lembre de minha idade AI: Você não informou sua idade anteriormente, portanto não tenho essa informação memoriza para lembrar. Human: 40 AI: Anotei que sua idade é 40 anos. Sempre que precisar que eu lembre dessa informação, é só avisar! Human: olá, qual a minha idade? AI: Sua idade é 40 anos, conforme a informação que você forneceu anteriormente. Human: quais são as coisas que você é possivel de fazer? AI: Eu posso ajudar com uma variedade de tarefas, incluindo responder perguntas, explicar conceitos, ajudar com escrita e tradução, realizar cálculos, inverter textos, converter unidades, contar palavras ou caracteres, executar pequenos códigos em Node.js, fornecer a hora atual no Brasil, e muito mais. Também posso memorizar informações que você me fornecer para lembrar posteriormente. Se quiser experimentar alguma dessas funções, é só pedir! Human: qual a data AI: A data e hora atuais são 06/07/2025, 22:23:51. Human: me fala apenas o horario AI: O horário atual no Brasil é 06/07/2025, 22:24:02. Human: TOOLS
Assistant can ask the user to use tools to look up information that may be helpful in answering the users original question. The tools the human can use are:
calculadora: Faz cálculos matemáticos simples e resolve equações com uma ou várias variáveis. Exemplos:
- 2 + 2
- x + 2 = 10
- x + y = 10, 2*x - y = 4 inverter_texto: Inverte o texto dado, ex: 'amor' vira 'roma' contar_caracteres: Conta quantos caracteres tem no texto para_maiusculas: Transforma o texto todo em maiúsculas para_minusculas: Transforma o texto todo em minúsculas contar_palavras: Conta quantas palavras tem no texto dado executa_nodejs: Executa código Node.js de forma segura e isolada com suporte a todos os tipos de console. ✔️ Suporta: async/await, variáveis JS, console.log/warn/error/info/debug ❌ Bloqueia: require, eval, acesso a arquivos, travas infinitas (timeout 3s) hora_atual: Retorna a hora e data atual no Brasil. Entrada: nada. converter_unidades: Converte unidades básicas. Entrada: " " Exemplos: "30 km", "10 mi", "100 c", "32 f" memorizar: Armazena um fato simples em memória. Entrada: qualquer frase ou informação a ser lembrada depois. Exemplo: "meu nome é Lucas", não coloque coisa desnecessaria na memoria, exemplo: "idade do usuario não informada", coloque apenas informações que o usuario fornecer, caso não fornecer, salva "nulo lembrar: Lembra o que foi memorizado. Entrada: qualquer texto. Retorna lista de fatos armazenados anteriormente.
RESPONSE FORMAT INSTRUCTIONS
Output a JSON markdown code snippet containing a valid JSON object in one of two formats:
Option 1: Use this if you want the human to use a tool. Markdown code snippet formatted in the following schema:
{ "action": string, // The action to take. Must be one of [calculadora, inverter_texto, contar_caracteres, para_maiusculas, para_minusculas, contar_palavras, executa_nodejs, hora_atual, converter_unidades, memorizar, lembrar] "action_input": string // The input to the action. May be a stringified object. }Option #2: Use this if you want to respond directly and conversationally to the human. Markdown code snippet formatted in the following schema:
{ "action": "Final Answer", "action_input": string // You should put what you want to return to user here and make sure to use valid json newline characters. }For both options, remember to always include the surrounding markdown code snippet delimiters (begin with "
json" and end with "")!USER'S INPUT
Here is the user's input (remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else):
me fala todas lembranças armazenadas
- Assistant
{ "action": "lembrar", "action_input": "" }