Joris de Jong Profile picture
Jun 22 11 tweets 4 min read Twitter logo Read on Twitter
ChatGPT is great for studying.

But did you know you can use it to make mindmaps based on your study material?

Through the combined power of @LangChainAI and @XmindHQ you can.

Let's dive into the workflow and code 🧵

#AI
Before we dive in, this is day 3 of my '7 days of LangChain'.

Every day, I'll introduce you to a simple project that will guide you through the basics of LangChain.

Follow @JorisTechTalk to stay up-to-date.

Let me know what you'd like to see

Let's dive in:
High-level overview:

1️⃣ Load study material
2️⃣ Split into smaller chunks
3️⃣ Generate mindmap in Markdown with @LangChainAI
4️⃣ Import markdown file in @XmindHQ
1. Load study material

Load your data with a Pdf Reader.

Since it splits this into multiple pages, add all text to a single text variable for further use.
2. Split text into chunks

The new OpenAI 16k model is amazing. It lets you have 4 times the input compared to the earlier model.

Larger context window = better understanding and fewer API calls.
3. Create your prompts.

Prompting is key. I specifically instructed the model to only output the text in markdown, with the correct format.

Try it yourself and see what works best.

4. Initialize and run the summary chain

With the use of your custom prompts, the summary chain will create the mindmap based on your study material.

Setting verbose to True will show the model's 'thought process'.

Always play around with structuring your prompts.
5. Save the mindmap to a markdown file

Nothing fancy happening here.

Just saving it to import it to Xmind later.
6. Import the markdown file into @XmindHQ.

Voila. You've just created a mindmap to help you study!

This is still a manual step. Will look into automating this as well.
That's day 3 out of '7 days of Langchain' done.

Follow @JorisTechTalk to stay up to date.

Still looking for a project for tomorrow. What do you want me to cover?
Day 3 of '7 days of @LangChainAI' ✅

Nearly crossing the half-way point.

What else do you want to see?

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Joris de Jong

Joris de Jong Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @JorisTechTalk

Jun 25
I love podcasts and the value they contain.

But ChatGPT doesn't have access to them.

With the power of @LangChainAI, it does! Let me show you how you can easily create a Podcast Chatbot & Summarizer.

Explanation and code 🧵

#AI
Before we dive in, this is day 5 of my '7 days of LangChain'.

Every day, I'll introduce you to a simple project that will guide you through the basics of LangChain.

Follow @JorisTechTalk to stay up-to-date.

If there's anything you'd like to see, let me know!

Let's dive in:
High-level overview of what's happening:

1️⃣ Load YouTube Transcript
2️⃣ Split text into chunks
3️⃣ Summarize Podcast
4️⃣ Create vector database for Q&A on the content

Let's dive into the code ⬇️
Read 15 tweets
Jun 21
Did you know you can use ChatGPT to summarize your (online) meetings?

With @LangChainAI, and a couple of lines of code, you can!

Let me show you how in 6 simple steps🧵

#AI Image
Before we dive in, this is day 2 of my '7 days of LangChain'.

Every day, I'll introduce you to a simple project that will guide you through the basics of LangChain.

Follow @JorisTechTalk to stay up-to-date.

If there's anything you'd like to see, let me know!

Let's dive in:
High level overview of what's happening:

1️⃣ Load your audio file
2️⃣ Speech-to-text with Whisper
3️⃣ Split the transcript into chunks
4️⃣ Summarize the transcript

Let's dive into the code ⬇️ Image
Read 12 tweets
Jun 21
Meta entered the chat...

Meta AI has unveiled Voicebox, a groundbreaking generative model for voice synthesis tasks.

This model can generate speech from text and perform tasks like editing, noise removal, and style transfer.

Let's dive into the details! 🧵
Voicebox is a generative model that can synthesize speech in six languages.

It has been trained on a general task of mapping voice audio samples to their transcripts, enabling it to perform various text-guided speech generation tasks seamlessly.
🔬 The researchers at Meta developed a unique training method called "Flow Matching" for Voicebox.

This technique allows the model to learn from diverse speech data without the need for careful labeling.

Trained on 50,000 hours of speech and transcripts from audiobooks. Image
Read 10 tweets
Jun 20
ChatGPT is great for creating plans.

But it can't use YouTube videos as a knowledge base.

With @LangChainAI, you can!

I've used the @thedankoe's YouTube video on '4-hour workdays' and let AI create a detailed plan.

Let me show you how you can do it too, in just 8 steps.

#AI Image
Before we dive in, this is day 1 of my '7 days of LangChain'.

Every day, I'll introduce you to a simple project that will guide you through the basics of LangChain.

Follow @JorisTechTalk to stay up-to-date.

If there's anything you'd like to see, let me know!

Let's dive in:
A high-level overview:

1️⃣ Load the YouTube transcript
2️⃣ Split the transcript into chunks
3️⃣ Use a summarization chain to create a strategy based on the content of the video
4️⃣ Use a simple LLM Chain to create a detailed plan based on the strategy.

And now for the code ⬇️ Image
Read 16 tweets
Jun 20
Finance 🤝 AI

Language models have transformed natural language processing across industries, and now they're making waves in finance.

Enter FinGPT: An open-source Financial Large Language Model

Let's dive in 🧵 Image
Extracting financial data can be daunting, spanning web platforms to PDFs.

While proprietary models like BloombergGPT have specialized data, the need for an open and inclusive alternative is clear.

Introducing FinGPT:
Developed by researchers from Columbia University and NYU Shanghai, FinGPT is an end-to-end open-source framework for economical large language models (FinLLMs).

Its mission: democratize financial data access and foster open finance. 📈
Read 8 tweets
Jun 19
One step closer to human-level intelligence in AI:

A year ago, Meta's Chief AI Scientist, Yann LeCun, proposed a groundbreaking architecture that could revolutionize AI systems as we know them.

Today, the first implementation is here: I-JEPA.

A deeper dive 🧵 Image
1/13 The goal?

To create machines that can learn internal models of how the world works, enabling them to learn faster, plan complex tasks, and adapt to new situations.

Let's dive into the details! 👇
2/13 📚 Introducing the Image Joint Embedding Predictive Architecture (I-JEPA).

The first AI model based on LeCun's vision. I-JEPA learns by creating an internal model of the world, comparing abstract representations of images instead of pixels themselves. 🖼️
Read 14 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(