Skip to content

Forum in maintenance, we will back soon πŸ™‚

Summarization promp...
 
Notifications
Clear all

Summarization prompt not working correctly

6 Posts
3 Users
1 Reactions
23 Views
(@arslaniqbal)
Posts: 7
Active Member
Topic starter
 

I am practicing the summarization prompt, but OpenAI is returning some parts of the prompt script as the summary result.
I used the summarization prompt as given in the video, then passed my input text(blog post), it returned the result:
"Perplexity and burstiness are crucial factors when writing content for AI
- Perplexity measures the complexity of text
- Burstiness compares the variations of sentences
- AI can be used to automate repetitive tasks, accelerate writing, brainstorm ideas, augment skills, condense information, simplify complex text, expand perspectives, and improve existing content"

@admin can you please guide me to fix this issue?

 
Posted : 08/09/2023 2:12 pm
SSAdvisor
(@ssadvisor)
Posts: 1139
Noble Member
 

@arslaniqbal You'll need to share the code before anyone can help.Β 

Regards,
Earnie Boyd, CEO
Seasoned Solutions Advisor LLC
Schedule 1-on-1 help
Join me on Slack

 
Posted : 08/09/2023 8:34 pm
(@arslaniqbal)
Posts: 7
Active Member
Topic starter
 
selected_model = "gpt-3.5-turbo-0613"
input_text = """In simple words, How to talk to AI to get it to do what you want.
This skill will be one of the top skills needed in the future, and in this guide, we will see real-world examples and applications that help you see the power of this skill in action, and it may change how you work, learn, and think.
You can even start selling prompts on websites like PromptBase after your finish this guide.
Not only that! after mastering this skill, you will also be able to .....................
"""
Β 
prompt = blog_prompts.summarize_text_to_bullet_points.format(Minimum="4", Maximum="6", Text=input_text)

token_count = helpers.count_tokens(prompt,selected_model)
cost_estimated = helpers.estimate_input_cost(selected_model,token_count)
print(f"estimated cost : {cost_estimated}")

response = llm.llm_generate_text(prompt,"OpenAI",selected_model)
print(response)
Β 
__________________________________________
This is the response I am getting from Chatgpt:
Perplexity and burstiness are crucial factors when writing content for AI
- Perplexity measures the complexity of text
- Burstiness compares the variations of sentences
- AI can be used to automate repetitive tasks, accelerate writing, brainstorm ideas, augment skills, condense information, simplify complex text, expand perspectives, and improve existing content
 
Posted : 08/10/2023 6:38 am
Hasan Aboul Hasan
(@admin)
Posts: 1276
Member Admin
 

@arslaniqbal did you change the prompt?

please add this line: to print the full prompt being sent to OpenAI:

print(prompt)
 
Posted : 08/10/2023 11:37 am
(@arslaniqbal)
Posts: 7
Active Member
Topic starter
 

Here is my prompt
"Your task is to create a concise summary
of the provided text.

I want you to remember the following information: When it comes to writing content,
two factors are crucial, "perplexity" and "burstiness."
Perplexity measures the complexity of text. Separately,
burstiness compares the variations of sentences.

Your summary should adhere to the given bullet points number.

Please format your response as bullet points. and add emojies when relevant

Minimum Number of Bullet Points: [4]
Maximum Number of Bullet Points: [6]
Provided Text: [In simple words, How to talk to AI to get it to do what you want.
This skill will be one of the top skills needed in the future, and in this guide, we will see real-world examples and applications that help you see the power of this skill in action, and it may change how you work, learn, and think.
You can even start selling prompts on websites like PromptBase after your finish this guide.
Not only that! after mastering this skill, you will also be able to
Automate repetitive tasks: Produce outputs on a consistent basis with a certain format and quality. Example use cases: producing ad copy, creating product descriptions, extracting phone numbers from text.
Accelerate writing: Write down the first draft or even the final version of a piece of text. Example use cases: composing emails, writing blog posts, and providing customer chat responses.
Brainstorm ideas: Generating a skeleton of a bigger piece to be worked on instead of working off a blank canvas. Example use cases: generating article outlines, finding business ideas, and writing story plots.
Augment a skill: Augmenting the skill of a writer who might not have sufficient proficiency. Example use cases: writing poems, writing fiction stories, formulating product pitches.
Condense information: Getting a summarized version of a document that strips it to its essence. Example use cases: summarizing reports, articles, and podcast transcripts.
Simplify the complex: Rewriting a piece of text into a simpler, more accessible way. Example use cases: simplifying technical explanations, understanding the complex text, extracting key concepts from a passage.
Expand perspectives: Adding variety to the voice and idea beyond just the person writing. Example use cases: generating opinions in essays, constructing arguments in debating, adding variety in speech scripts.
Improve what’s available: Turning a piece of text into a better version. Example use cases: correcting spelling errors, making a passage more coherent, rewriting podcast transcripts.
]"

 
Posted : 08/10/2023 1:15 pm
Hasan Aboul Hasan
(@admin)
Posts: 1276
Member Admin
 

Try this:

Β 

Your task is to create a concise summary
of the [provided text].

I want you to remember the following information: When it comes to writing content,
two factors are crucial, "perplexity" and "burstiness."
Perplexity measures the complexity of text. Separately,
burstiness compares the variations of sentences.

Your summary should adhere to the given bullet points number.

Please format your response as bullet points. and add emojies when relevant

Minimum Number of Bullet Points: [4]
Maximum Number of Bullet Points: [6]
[provided text]: ...

 
Posted : 08/11/2023 11:50 am
SSAdvisor reacted
Share:
[the_ad_group id="312"]