Free AI web copilot to create summaries, insights and extended knowledge, download it at here

4588

Abstract

on't know, don't try to make up an answer. """

<span class="hljs-comment"># Prepend context if used</span>
<span class="hljs-keyword">if</span> context != <span class="hljs-string">""</span>:
    question = <span class="hljs-string">"Use the following context to answer the users question:\n```\n"</span> + context + <span class="hljs-string">"\n```\n\n"</span> + question

response = openai.ChatCompletion.create(
    engine=<span class="hljs-string">"gpt-35-turbo"</span>,
    messages = [{<span class="hljs-string">"role"</span>:<span class="hljs-string">"system"</span>,<span class="hljs-string">"content"</span>:system},{<span class="hljs-string">"role"</span>:<span class="hljs-string">"user"</span>,<span class="hljs-string">"content"</span>:question}],
    temperature=<span class="hljs-number">0.0</span>,
    max_tokens=<span class="hljs-number">500</span>,
    top_p=<span class="hljs-number">0.95</span>,
    frequency_penalty=<span class="hljs-number">0</span>,
    presence_penalty=<span class="hljs-number">0</span>,
    stop=<span class="hljs-literal">None</span>)
    
<span class="hljs-keyword">return</span> response[<span class="hljs-string">'choices'</span>][<span class="hljs-number">0</span>][<span class="hljs-string">'message'</span>][<span class="hljs-string">'content'</span>]</pre></div><p id="212c">This first one, <code>ask</code> is simply a wrapper to calling OpenAI GPT 3.5. Turbo, including a System Prompt about looking through research papers. It also accepts a <code>context</code>variable which is included in the prompt as necessary.</p><div id="6164"><pre><span class="hljs-keyword">def</span> <span class="hljs-title function_">extract_section</span>(<span class="hljs-params">documents, section_name, debug=<span class="hljs-literal">False</span></span>):
section_page = <span class="hljs-string">""</span>
section_text = <span class="hljs-string">""</span>

<span class="hljs-keyword">for</span> idx, page <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(documents):
    <span class="hljs-keyword">if</span> section_text == <span class="hljs-string">""</span> <span class="hljs-keyword">and</span> section_name <span class="hljs-keyword">in</span> page.text.lower():
        <span class="hljs-keyword">if</span> debug: <span class="hljs-built_in">print</span>(idx)

        context = page.text
        <span class="hljs-keyword">if</span> idx &lt; <span class="hljs-built_in">len</span>(documents)-<span class="hljs-number">2</span>:
            context += <span class="hljs-string">"\n"</span> + documents[idx+<span class="hljs-number">1</span>].text
            context += <span class="hljs-string">"\n"</span> + documents[idx+<span class="hljs-number">2</span>].text

        answer = ask(<span class="hljs-string">f"Does the above have the section called '<span class="hljs-subst">{section_name}</span>' or similar, and does it, in detail, explain the <span class="hljs-subst">{section_name}</span>?"</span>, context)
        <span class="hljs-keyword">if</span> answer.startswith(<span class="hljs-string">"Yes"</span>):
            answer = ask(<span class="hljs-string">f"\n-----\nWhat is the <span class="hljs-subst">{section_name}</span> in the document? Return everything in this section, up to the next heading. Do not interpret it, give me the verbatim text."</span>, context)
            <span class="hljs-keyword">if</span> debug: <span class="hljs-built_in">print</span>(answer + <span class="hljs-string">"\n----------"</span>)
            section_page = idx + <span class="hljs-number">1</span>
            section_text = answer
            <span class="hljs-keyword">if</span> debug: <span class="hljs-built_in">print</span>(section_page, section_text, validate)

<span class="hljs-keyword">return</span> section_text, section_page</pre></div><p id="f08f">In the <code>extract_section</code>function, we do a couple of things:</p><ol><li>We use the <code>section_name</code>we pass in to do a really simple check. We iterate through all pages in the document and see if the text in <code>section_name</code>exists in the lower case version of the page</li><li>If it does, it uses that page and the two subsequent pages and pass them into a couple of LLM prompts to see if it has a section named <code>section_name</code> and if so, it extracts the section verbatim</li><li>Returns a tuple of the the section text, and the page it which it was found</li></ol><p i

Options

d="5b9a">Of course, this is a one time activity. In reality this would be used and ran to extract the relevant sections and cache them for future use.So let’s first start to build up a <code>sections</code>variable. For the first section I am actually going to cheat a little and not use <code>extract_section</code>function because the section I want, <code>authors</code>does not have a section heading, so we just use the <code>ask</code>function and pass in the first page of the document.<div id="0aa4"><pre>sections = {}

sections["authors"] = (ask("Who are the authors mentioned before the abstract", documents[0].text), 1) sections["authors"]</pre></div><figure id="2fc0"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*iXz3LsCIKxj0qAHG2IV0bQ.png"><figcaption></figcaption></figure>OK that looks good. now let’s use the <code>extract_section</code>function to extract the <code>abstract</code>section.<div id="c468"><pre>sections["abstract"] = extract_section(documents, "abstract") sections["abstract"]</pre></div><figure id="4c09"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*AaGiiD9HRReA34Laz6ODCw.png"><figcaption></figcaption></figure>OK so lets see if what we’ve done is of any use.First let’s look at what license is applicable to this. We’ll start with the Llama Index search:<div id="601a"><pre>%%time

query = 'What licenses are mentioned?' print(query) answer = query_engine.query(query) print(answer.response)</pre></div><figure id="5b74"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*LjefM-QYa773vVlv_M9JVg.png"><figcaption></figcaption></figure>Oh that's a little disappointing. It couldn't find anything.What about if we use just the abstract section.<div id="c085"><pre>%%time

ask(query, sections["abstract"][0])</pre></div><figure id="3cee"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*QqBO27pBanGBmPf-89Sz-w.png"><figcaption></figcaption></figure>That looks good. Not only did it get the right answer, it was also quicker because we only use the section of interest in the prompt, and not the k chunks that the semantic search thought would be relevant.OK another quick check. Let’s ask a question about an author. This author was responsible for one of the papers in the References, but not actually an author of this paper. So asking if they are an author of this paper should say no, right?<div id="ae97"><pre>%%time

query = 'Is Jacob Austin an author of this paper?' print(query) answer = query_engine.query(query) print(answer.response)</pre></div><figure id="8ee4"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*2Bvv0A6CRjdrd-SbEVil9Q.png"><figcaption></figcaption></figure>OK well that’s a little odd. It thinks he was an author of this paper, And it thinks that because the semantic search found him as an author, but not distinguished it as being a paper in the reference and not the paper itself.What about using the sections specifically?<div id="2ffe"><pre>%%time

ask(query, sections["authors"][0])</pre></div><figure id="5d52"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*JdCeCo313dTBVHVmAL0HqQ.png"><figcaption></figcaption></figure>Well yes of course that it would work and recognise he is not an author of this paper. And of course it’s quicker because we only use the section of interest in the prompt, and not the k chunks that the semantic search thought would be relevant.I personally use this approach a fair bit. I’m not saying it’s better. I’m saying it’s simpler. More Balanced. An alternate approach and another tool in your arsenal.So, how about it? KISS and BRAG?Thanks for reading.</article></body>

What I Discovered When I Shared My Miscarriage Experience

Approximately 40% of women will encounter this profound loss, making it a statistic demanding our attention.

My journey involves a chemical miscarriage, a loss that transpires before the five-week embryo development mark.

I loved someone I never got to meet.

Many miscarriages can occur even after a heartbeat is detected or, sadly, even suddenly in seemingly healthy pregnancies.

Empty crib. Photo by Sidekix Media on Unsplash

As I opened up to close friends and medical specialists about my loss, three things became evident:

Many people in my circle had gone through a miscarriage. Roughly 5 out of 8 people I shared the news with had a similar experience.
There are many misconceptions about miscarriage.
Unlike news of someone’s passing, people struggle to know how to respond to the news of a miscarriage.

I was deeply moved by those who opened up to me about their loss as I opened up to them about mine. It helped me feel less alone.

However, I was equally resentful of people who tried to give me advice or their opinions.

If you’re not sure how to respond to someone who’s miscarried, I highly recommend taking note of what not to say. If you’re interested, we wrote about it in our first article:

I Had a Miscarriage — 40% of the Women You Meet Will Experience One: What Not to Say

Despite significant progress in addressing social issues, it remains surprising that miscarriage continues to be taboo.

medium.com

Anyone who has undergone a D&C procedure or sat on a toilet waiting for incomplete genetic tissue to pass will understand miscarriage is a physically demanding and isolating experience.

It can be a shock to see a forming embryo on an ultrasound one day and then see an empty sac the next day.

According to Johns Hopkins Medicine D&C, A dilation and curettage procedure is a surgical procedure in which the cervix (the lower, narrow part of the uterus) is dilated (expanded) so that the uterine lining (endometrium) can be scraped with a curette (spoon-shaped instrument) to remove abnormal tissues.

The Lack of Understanding Around Miscarriage: A Startling Reality

Photo by Ehimetalor Akhere Unuabona on Unsplash

It baffles me that in our modern society, where we have advanced treatments for conditions like HIV, diabetes, and cancer, something as uncontrollable and tragic as miscarriage is still often treated as a quiet disease or inconvenience.

Only once you’ve experienced it do you understand the strength needed to navigate through one or multiple pregnancy losses.

It underscores the intricate challenges that a considerable portion of society faces when planning for a family. Continuing to ignore the glaring problem will likely result in adverse effects.

People are having less kids these days, according to studies published in US News. Photo by Joseph Chan on Unsplash

On a global scale, the American population, like many other developed nations, including Japan, Korea, and significant regions like the European Union nations, is on the decline.

Overall, birth rates have plummeted for Americans over the past five decades: “Between 1976 and 2018, the mean number of children ever born per woman declined, from three children to two,” according to the report’s authors, Gladys Martinez and Kimberly Daniels.

Our country should pick a struggle.

We shouldn’t be ignorant about miscarriage AND lead our population into decline at the same time.

While there are lifestyle adjustments that may lower the risk of early pregnancy loss, the reality is that nothing is certain, and no one has complete control over such circumstances.

Miscarriage can happen for no apparent reason but is often due to a chromosomal defect or lack of genetic material, which means the mom has little control over when or if it happens.

Another misconception that persists today is linking the loss solely to infertility or female factors. In fact:

This loss can even happen to healthy couples. I met a young surgeon whose wife, also a young doctor, experienced a traumatic miscarriage at home even though they had healthy lifestyles and were in their early 30s.
Secondly, there are also male factors, such as limited motility and urologic disorders. It takes two sets of genes to make an embryo, after all.

People need to be aware of how common miscarriages are. Our generation has to lead the uncomfortable conversation so that the path to parenthood is less shrouded in mystery for the next generation.

Although in the US, teen pregnancy is higher than most developed countries, the reality is getting pregnant is not always as simple it is in the movies.

It can take up to a year or more for most couples to conceive, and fertility options are a mystery, sometimes causing much unnecessary confusion for young people later on in their parenthood journey.

We need to change the narrative and stop being silent about the reality of negative pregnancy outcomes and how fertility actually works.

Wrapping Up

Miscarriage is a tale as old as time, a silent challenge that demands understanding.

My journey through a chemical loss revealed shared pain — 5 in 8 people knew it, too. Despite progress, misconceptions persist, and responses vary — sometimes in a hurtful manner.

The physical toll is isolating, and the strength needed is beyond words. You’ll likely meet someone who will go through this tragedy at least once in your life.

In our so-called advanced society, miscarriage is still somehow swept under the rug.

Ignorance on the topic and declining birth rates point to more significant societal battles. It’s time to face reality, dispel myths, and give the narrative a good shake.

About Tiny Sesame

Tiny Sesame was started by two longtime friends who aim to foster support and empowerment on the journey to parenthood. We understand the challenges others may face when balancing life and family. We are leaders within our respective industries; one owns a six-figure government advisory firm, and the other works in finance, recently helping a billion-dollar fintech company go public.

Join our compassionate community of individuals navigating the complexities of fertility. Together, we share stories, insights, and expert guidance to inspire hope, resilience, and connection.

Whether you’re exploring fertility options, facing challenges, or celebrating success, this is the space to find understanding, resources, and a community that genuinely cares.