Sumarizace a rozšiřování textu

Prompt Engineering s OpenAI API

Fouad Trad

Machine Learning Engineer

Sumarizace textu

  • Zkracuje text do stručnější podoby
  • Zjednodušuje obchodní procesy
    • Finance -> sumarizuje rozsáhlé zprávy
    • Marketing -> převádí zpětnou vazbu zákazníků na praktické poznatky
  • LLM dokáží sumarizovat texty pomocí efektivních promptů

Obrázek znázorňující, jak sumarizace převádí hromadu knih na dokument se shrnutím.

Prompt Engineering s OpenAI API

Neefektivní prompt

  • Určuje pouze text k sumarizaci
text = "I recently purchased your XYZ Smart Watch and wanted to provide some feedback
based on my experience with the product. I must say that I'm impressed with the sleek design 
and build quality of the watch. It feels comfortable on the wrist and looks great with any 
outfit. The touchscreen is responsive and easy to navigate through the various features."

prompt = f"""Summarize the text delimited by triple backticks: ```{text}```""" print(get_response(prompt))
The author purchased the XYZ Smart Watch and is impressed with its sleek design, build 
quality, and comfortable fit on the wrist. They find the touchscreen responsive and 
user-friendly for navigating the watch's features.
Prompt Engineering s OpenAI API

Vylepšení promptu

  • Limity výstupu
  • Struktura výstupu
  • Zaměření sumarizace

Obrázek znázorňující osobu stoupající o stupeň výš jako znak zlepšení.

Prompt Engineering s OpenAI API

Efektivní prompt: limity výstupu

  • Určete počet vět, slov nebo znaků
text = "I recently purchased your XYZ Smart Watch and wanted to provide some feedback
based on my experience with the product. I must say that I'm impressed with the sleek design 
and build quality of the watch. It feels comfortable on the wrist and looks great with any 
outfit. The touchscreen is responsive and easy to navigate through the various features."

prompt = f"""Summarize the text delimited by triple backticks in one sentence: ```{text}```""" print(get_response(prompt))
The customer is impressed with the sleek design, build quality, comfort, and responsiveness 
of the XYZ Smart Watch's touch screen.
Prompt Engineering s OpenAI API

Efektivní prompt: struktura výstupu

  • Určete strukturu výstupu
text = "I recently purchased your XYZ Smart Watch and wanted to provide some feedback
based on my experience with the product. I must say that I'm impressed with the sleek design 
and build quality of the watch. It feels comfortable on the wrist and looks great with any 
outfit. The touchscreen is responsive and easy to navigate through the various features."

prompt = f"""Summarize the text delimited by triple backticks, in at most three bullet points. ```{text}```""" print(get_response(prompt))
- The XYZ Smart Watch has a sleek and impressive design with  excellent build quality.
- It feels comfortable on the wrist and complements any outfit.
- The touch screen is responsive and user-friendly for easy navigation through the features.
Prompt Engineering s OpenAI API

Efektivní prompt: zaměření sumarizace

  • Požádejte model, aby se zaměřil na konkrétní části textu
text = "I recently purchased your XYZ Smart Watch and wanted to provide some feedback
based on my experience with the product. I must say that I'm impressed with the sleek design 
and build quality of the watch. It feels comfortable on the wrist and looks great with any 
outfit. The touchscreen is responsive and easy to navigate through the various features."

prompt = f"""Summarize the review delimited by triple backticks, in three sentences, focusing on the key features and user experience: ```{text}```""" print(get_response(prompt))
Prompt Engineering s OpenAI API

Efektivní prompt: zaměření sumarizace

The customer purchased the XYZ Smart Watch and was impressed with its sleek design 
and build quality. 
They found it comfortable to wear and versatile enough to match any outfit. 
The touch screen was responsive and user-friendly, making it easy to navigate 
through the watch's features.
Prompt Engineering s OpenAI API

Rozšiřování textu

  • Generuje text z nápadů nebo odrážek
  • Zvyšuje efektivitu a produktivitu
  • LLM dokáží text rozšiřovat pomocí vhodných promptů

Obrázek vysvětlující, že rozšiřování textu spočívá v generování úplného textu na základě několika nápadů nebo požadavků.

Prompt Engineering s OpenAI API

Prompty pro rozšiřování textu

  • Požádejte model o rozšíření ohraničeného textu
  • Zdůrazněte aspekty, na které se zaměřit
  • Určete požadavky na výstup (tón, délka, struktura, cílová skupina)

Ikona znázorňující tužku píšící do zápisníku.

Prompt Engineering s OpenAI API

Rozšíření popisu služby

service_description = """Service: Social XYZ
- Social Media Strategy Development
- Content Creation and Posting 
- Audience Engagement and Community Building
- Increased Brand Visibility
- Enhanced Customer Engagement
- Data-Driven Marketing Decisions"""
prompt = f"""Expand the description for the Social XYZ service delimited by triple 
backticks to provide an overview of its features and benefits, without bypassing 
the limit of two sentences. Use a professional tone.
```{service_description}```"""
print(get_response(prompt))
Prompt Engineering s OpenAI API

Rozšíření popisu služby

Social XYZ is a comprehensive social media service that offers strategic 
development, content creation, and posting to help businesses effectively engage 
with their target audience and build a strong online community. 

With a focus on increasing brand visibility and enhancing customer engagement, 
Social XYZ enables businesses to make data-driven marketing decisions for optimal 
results.
Prompt Engineering s OpenAI API

Pojďme procvičovat!

Prompt Engineering s OpenAI API

Preparing Video For Download...