Incorporar contexto externo

Ingeniería rápida con la API de OpenAI

Fouad Trad

Machine Learning Engineer

La necesidad de contexto externo

Los modelos de lenguaje preentrenados reconocen lo que vieron en su entrenamiento
Hay que aportar más contexto
Más precisión y eficacia

Icono que representa un chatbot en un móvil.

Falta de información en los LLM

Corte de conocimiento

system_prompt = "Act as a financial expert that knows about the latest trends."

user_prompt = "What are the top financial trends in 2023?"

print(get_response(system_prompt, user_prompt))

I apologize for any inconvenience, but as of my last knowledge update in 
September 2021, I don't have information about financial trends in 2023.

Falta de información en los LLM

Se pide información no pública

system_prompt = "Act as a study buddy that helps me with my studies to succeed 
in exams."


user_prompt = "What is the name of my favorite instructor?"

print(get_response(system_prompt, user_prompt))

I don't have personal information about you, including the name of your 
favorite instructor.

¿Cómo dar información extra?

Conversaciones previas de ejemplo
Prompt del sistema

Icono con dos globos de diálogo para reflejar una conversación.

Conversaciones de ejemplo

Guiar al modelo para responder preguntas concretas

response = client.chat.completions.create(
  model="gpt-3.5-turbo",
  messages=[{"role": "system",
             "content": "You are a customer service chatbot that responds to user queries in a gentle way"},

            {"role": "user",
             "content": "What services do you offer?"},

           {"role": "assistant",
             "content": "We provide services for web application development, mobile app development, and 
            custom software solutions."},

           {"role": "user",
             "content": "How many services do you have?"}])

print(response.choices[0].message.content)

We have 3 services including web application development, mobile app development, and custom software solutions.

Desventaja: puede requerir muchas muestras

Prompt del sistema

Incluye el contexto necesario para las respuestas del chatbot

services = "ABC Tech Solutions, a leading IT company, offers a range of services: 
application development, mobile app development, and custom software solutions."

system_prompt = f"""You are a customer service chatbot that responds to user 
queries in a gentle way. Some information about our services are delimited by 
triple backticks.
```{services}```"""

user_prompt = "How many services do you offer?"
print(get_response(system_prompt, user_prompt))

We have 3 services including web application development, mobile app development, 
and custom software solutions.

Nota final

Los métodos previos funcionan bien con contextos pequeños
Contextos más grandes requieren técnicas más avanzadas

Icono que representa una alerta.

¡Vamos a practicar!

Ingeniería rápida con la API de OpenAI