Textanalys

Prompt Engineering med OpenAI API

Fouad Trad

Machine Learning Engineer

Textanalys

Undersöker text för att utvinna information
- Textklassificering
- Entitetsextraktion
Företag bör söka juridisk rådgivning vid användning av kunddata

Bild som visar hur textanalys utvinner information såsom sentiment, känslor, ton, entiteter m.m. från en given text.

Textklassificering

Tilldela kategorier till text
Exempel: sentimentanalys

Bild som visar sentimentanalysens klasser: positiv, negativ eller neutral.

Specificerade kategorier

Ange klassificeringskategorier när de är kända
Specificera krav på utdata

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

Ospecificerade kategorier

Modellen använder sin kunskap när kategorier inte anges

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.

För vissa öppna problem fungerar detta inte alltid bra

Flera klasser

Text kan passa in i flera klasser
Ange ett maxantal klasser om de inte är kända

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

Entitetsextraktion

Extrahera specifika entiteter från text
Exempel: namn, platser, organisationer, datum

Ikon som visar hur entitetsextraktion handlar om att hämta ut specifika entiteter från en given text

Entitetsextraktion: ange entiteter

Ange entiteter att extrahera
Specificera utdataformat

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))

Entitetsextraktion: ange entiteter

Ange entiteter att extrahera
Specificera utdataformat

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))

Entitetsextraktion: ange entiteter

Ange entiteter att extrahera
Specificera utdataformat

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))

Entitetsextraktion: ange entiteter

Ange entiteter att extrahera
Specificera utdataformat

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))

Entitetsextraktion: ange entiteter

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

Entitetsextraktion med few-shot-promptar

För komplexa strukturer

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"""

Entitetsextraktion med few-shot-promptar

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

Nu kör vi en övning!

Prompt Engineering med OpenAI API