Analýza textu

Prompt Engineering s OpenAI API

Fouad Trad

Machine Learning Engineer

Analýza textu

Zkoumání textu za účelem extrakce informací
- Klasifikace textu
- Extrakce entit
Společnosti by měly při práci se zákaznickými daty konzultovat právní aspekty

Obrázek znázorňující, jak analýza textu extrahuje informace – sentiment, emoce, tón, entity apod.

Klasifikace textu

Přiřazení kategorií textu
Příklad: analýza sentimentu

Obrázek znázorňující třídy analýzy sentimentu: pozitivní, negativní nebo neutrální.

Zadané kategorie

Určete klasifikační kategorie, jsou-li známy
Uveďte požadavky na výstup

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

Nezadané kategorie

Pokud kategorie nejsou zadány, model využije vlastní znalosti

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.

Pro některé otevřené problémy to nemusí fungovat dobře

Více tříd

Text může patřit do více tříd
Definujte maximální počet tříd, pokud nejsou předem známy

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

Extrakce entit

Extrakce konkrétních entit z textu
Příklady: jména, místa, organizace, data

Ikona znázorňující, jak extrakce entit funguje – z daného textu jsou extrahovány konkrétní entity

Extrakce entit: určení entit

Určete entity k extrakci
Uveďte formát výstupu

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))

Extrakce entit: určení entit

Určete entity k extrakci
Uveďte formát výstupu

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))

Extrakce entit: určení entit

Určete entity k extrakci
Uveďte formát výstupu

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))

Extrakce entit: určení entit

Určete entity k extrakci
Uveďte formát výstupu

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))

Extrakce entit: určení entit

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

Extrakce entit s few-shot prompty

Pro složité struktury

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"""

Extrakce entit s few-shot prompty

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

Lass uns üben!

Prompt Engineering s OpenAI API