Análise de texto

Engenharia rápida com a API OpenAI

Fouad Trad

Machine Learning Engineer

Análise de texto

Analisar texto para extrair informações
- Classificação de texto
- Extração de entidades
Empresas devem buscar aconselhamento jurídico ao usar dados de clientes

Imagem mostrando como a análise de texto extrai informações como sentimento, emoção, tom, entidades etc. de um texto.

Classificação de texto

Atribuir categorias a um texto
Exemplo: análise de sentimento

Imagem mostrando as classes de análise de sentimento: positivo, negativo ou neutro.

Categorias especificadas

Especifique as categorias quando conhecidas
Informe os requisitos de saída

text = "I bought your XYZ Smart Watch and wanted to share my positive experience. 
Impressed with its sleek design, comfort, and touchscreen usability."


prompt = f"""Classify the sentiment of the text delimited by triple backticks as 
positive, negative, or neutral. Give your answer as a single word:
           ```{text}```"""

print(get_response(prompt))

positive

Categorias não especificadas

O modelo usa seu conhecimento quando as categorias não são especificadas

text = "I bought your XYZ Smart Watch and wanted to share my positive experience. 
Impressed with its sleek design, comfort, and touchscreen usability."

prompt = f"""Classify the sentiment of the text delimited by triple backticks. 
             Give your answer as a single word.
           ```{text}```"""
print(get_response(response))

positive.

Para alguns problemas em aberto, isso pode não funcionar bem

Múltiplas classes

Um texto pode se encaixar em várias classes
Defina um número máximo de classes se não souber

text = "I bought your XYZ Smart Watch and wanted to share my positive experience. 
Impressed with its sleek design, comfort, and touchscreen usability."

prompt = f"""Identify emotions used in this text. Don't use more than 3 emotions. 
             Format your answer as a list of words separated by commas:
           ```{text}```"""

print(get_response(prompt))

impressed, positive, comfortable

Extração de entidades

Extração de entidades específicas do texto
Exemplos: nomes, lugares, organizações, datas

Ícone mostrando que extração de entidades é extrair entidades específicas de um texto

Extração de entidades: especifique entidades

Especifique as entidades a extrair
Informe o formato de saída

text = "The XYZ Mobile X200: a sleek 6.5-inch Super AMOLED smartphone with a 48MP 
triple-camera, octa-core processor, 5000mAh battery, 5G connectivity, and Android 
11 OS. Secure with fingerprint and facial recognition. 128GB storage, expandable up 
to 512GB."

prompt = f"""Identify the following entities from the text delimited by triple backticks:
             - Product Name



           ```{text}```"""
print(get_response(prompt))

Extração de entidades: especifique entidades

Especifique as entidades a extrair
Informe o formato de saída

text = "The XYZ Mobile X200: a sleek 6.5-inch Super AMOLED smartphone with a 48MP 
triple-camera, octa-core processor, 5000mAh battery, 5G connectivity, and Android 
11 OS. Secure with fingerprint and facial recognition. 128GB storage, expandable up 
to 512GB."

prompt = f"""Identify the following entities from the text delimited by triple backticks:
             - Product Name
             - Display Size


           ```{text}```"""
print(get_response(prompt))

Extração de entidades: especifique entidades

Especifique as entidades a extrair
Informe o formato de saída

text = "The XYZ Mobile X200: a sleek 6.5-inch Super AMOLED smartphone with a 48MP 
triple-camera, octa-core processor, 5000mAh battery, 5G connectivity, and Android 
11 OS. Secure with fingerprint and facial recognition. 128GB storage, expandable up 
to 512GB."

prompt = f"""Identify the following entities from the text delimited by triple backticks:
             - Product Name
             - Display Size
             - Camera Resolution

           ```{text}```"""
print(get_response(prompt))

Extração de entidades: especifique entidades

Especifique as entidades a extrair
Informe o formato de saída

text = "The XYZ Mobile X200: a sleek 6.5-inch Super AMOLED smartphone with a 48MP 
triple-camera, octa-core processor, 5000mAh battery, 5G connectivity, and Android 
11 OS. Secure with fingerprint and facial recognition. 128GB storage, expandable up 
to 512GB."

prompt = f"""Identify the following entities from the text delimited by triple backticks:
             - Product Name
             - Display Size
             - Camera Resolution
             Format the answer as an unordered list.
           ```{text}```"""
print(get_response(prompt))

Extração de entidades: especifique entidades

Product Name: XYZ Mobile X200
Display Size: 6.5-inch
Camera Resolution: 48MP triple-camera

Extração de entidades com few-shot

Para estruturas complexas

ticket_1 = "Hello, I'm Emma Adams. I'd 
like to ask about my reservation with 
the code CAR123. 
You can reach me at +123456 if needed."

ticket_2 = "This is Sarah Williams. 
I would like to request some information
regarding my upcoming flight with 
reservation code FLIGHT987. Thank you."

entities_1 = """
* Customer Details:
  - Name: Emma Adams
  - Phone: +123456
* Reservation Details:
  - Reservation Code: CAR123"""
entities_2 = """
* Customer Details:
  - Name: Sarah Williams
* Reservation Details:
  - Reservation Code: FLIGHT987"""

Extração de entidades com few-shot

ticket_3 = "Hello, I'm David Brown (CUST123). I need assistance with my reservation under 
the code HOTEL456. There are some questions and issues related to my upcoming stay that 
require your attention."


prompt = f"""Text: {ticket_1} -> Entities: {entities_1}
             Text: {ticket_2} -> Entities: {entities_2}
             Text: {ticket_3} -> Entities: """
print(get_response(prompt))

* Customer Details:
  - Name: David Brown
  - Customer ID: CUST123
* Reservation Details:
  - Reservation Code: HOTEL456

Vamos praticar!

Engenharia rápida com a API OpenAI