TIL: 3️⃣ ways I use Large Language Models to increase learning efficiency
Table of Contents: To Do List Management System LLM with RAG system Online Courses Summary (In the future) Summary This semester, it's a bit odd that I registered for 5 courses for my master degree at HCMUT along with the job at the bank, so It makes me burn out a bit. I've only been taking the courses for a week and I'm already feeling miserable. It's not until now that I've tried applying LLMs in work and study, but really, my tight schedule recently forces me to optimize everything and only prioritize things that brings the most important value There is never enough time to do everything, but there is always enough time to do the most important thing. - Brian Tracy. To Do List Management System I often use Microsoft To Do because it is simple and convenient. Normally, just call "Hi Bixby" to create a task from my Samsung phone. Tasks will be synchronized into the Calendar app. However, it handles Vietnamese poorly, cannot add multiple tasks at the same time, does not automatically set the importance level... Although Google Assistant are better at handling speech to text problem, it has the same limitations as above. I decided to go big this time and build my own Telegram chat bot. Every time you send a voice, it will process it automatically: Breaking down the text into multiple tasks. Summary, fix tasks Set due date, reminder date, important level based on my personal information. Very convenient. But the biggest drawback is that I still need to send voice to the app manually, not "Hi Bixby" or "Hey Google", this makes it lose its practicality. I will find a way to fix this in the future To do list is integrated into this tele bot: mrzaizai2k / stock_price_4_fun Mrzaizai2k Stock Assistant Bot: Your all-in-one stock analysis companion. Calculate payback time, find support/resistance, and receive market warnings. Mrzaizai2k Stock Assistant Bot Table of Contents Introduction Available Commands How to Use How to Set Up the Bot Warning Price Database Open VScode tunnel Summarize Sound Summarize News LLM with RAG system Example Uses To-Do List Introduction Welcome to the Mrzaizai2k Stock Assistant bot! This bot is designed to assist you with various stock-related tasks and analyses. Whether you want to calculate the payback time for a stock, find support and resistance levels, or receive warnings about specific market conditions, this bot has you covered. Available Commands Available commands /start: Initializes the bot and provides a welcome message. /help: Displays a list of available commands and their descriptions. /pbt: Calculates the payback time for a specific stock. /snr: Finds the closest support and resistance levels for a stock. /findpbt: Identifies stocks with favorable payback times. /findmyfav: Recommends stocks based on specified criteria. /risk… View on GitHub LLM with RAG system I used Faiss as vector database and Langchain to get text from any sources I could think of (.pdf, .doc, .ppt, .txt, .md, .epub, link, ebook, youtube...). If you ask Chatgpt, it will sometime mislead you or create fake answer. Although the answer might be correct, it doesn't follow the lecturer's documents. This RAG system take the answer from our documents to produce results, so the results are more accurate and we can immediately check its correctness. I also tested on the Software Testing Quizz, the result was about 7/10. I also ask chatgpt, but the answer seems bad. But Questions with the answer "All the answers are correct" are often wrong. Perhaps it's because the model only finds the answer with the highest probability, so the aggregated answers are not fit to this case. Maybe I should rewriting the prompt. Additionally, a small part of the learning resources are images, and I'm actually still looking for ways to optimize the explanation for the images. My LLM + RAG system: mrzaizai2k / LLM-with-RAG I just wanna build my own LLM with RAG LLM-with-RAG I just wanna build my own LLM with RAG Table of Contents Introduction Features How to Set Up Example Uses To-Do List Introduction Welcome to the my LLM with RAG system! This system is designed for me the ease the learning as a master in HCMUT Features Update vector database curl -X POST http://localhost:8083/update Ask questions with vector data curl -X POST -H "Content-Type: application/json" -d '{"query": "who is karger"}' http://localhost:8083/query Nougat Link: https://github.com/facebookresearch/nougat nougat data/web_data/Growth_of_Functions.pdf --markdown --no-skipping -m 0.1.0-base -o data/nougat How to Set Up Prerequisites Before running the system, follow these steps to set up the environment: Clone the Repository: Close the Git r
Table of Contents:
- To Do List Management System
- LLM with RAG system
- Online Courses Summary (In the future)
- Summary
This semester, it's a bit odd that I registered for 5 courses for my master degree at HCMUT along with the job at the bank, so It makes me burn out a bit. I've only been taking the courses for a week and I'm already feeling miserable.
It's not until now that I've tried applying LLMs in work and study, but really, my tight schedule recently forces me to optimize everything and only prioritize things that brings the most important value
There is never enough time to do everything, but there is always enough time to do the most important thing. - Brian Tracy.
To Do List Management System
I often use Microsoft To Do because it is simple and convenient. Normally, just call "Hi Bixby" to create a task from my Samsung phone. Tasks will be synchronized into the Calendar app. However, it handles Vietnamese poorly, cannot add multiple tasks at the same time, does not automatically set the importance level... Although Google Assistant are better at handling speech to text problem, it has the same limitations as above.
I decided to go big this time and build my own Telegram chat bot. Every time you send a voice, it will process it automatically:
- Breaking down the text into multiple tasks.
- Summary, fix tasks
- Set due date, reminder date, important level based on my personal information.
Very convenient. But the biggest drawback is that I still need to send voice to the app manually, not "Hi Bixby" or "Hey Google", this makes it lose its practicality. I will find a way to fix this in the future
To do list is integrated into this tele bot:
mrzaizai2k
/
stock_price_4_fun
Mrzaizai2k Stock Assistant Bot: Your all-in-one stock analysis companion. Calculate payback time, find support/resistance, and receive market warnings.
Mrzaizai2k Stock Assistant Bot
Table of Contents
- Introduction
- Available Commands
- How to Use
- How to Set Up the Bot
- Warning Price
- Database
- Open VScode tunnel
- Summarize Sound
- Summarize News
- LLM with RAG system
- Example Uses
- To-Do List
Introduction
Welcome to the Mrzaizai2k Stock Assistant bot! This bot is designed to assist you with various stock-related tasks and analyses. Whether you want to calculate the payback time for a stock, find support and resistance levels, or receive warnings about specific market conditions, this bot has you covered.
Available Commands
Available commands
-
/start
: Initializes the bot and provides a welcome message. -
/help
: Displays a list of available commands and their descriptions. -
/pbt
: Calculates the payback time for a specific stock. -
/snr
: Finds the closest support and resistance levels for a stock. -
/findpbt
: Identifies stocks with favorable payback times. -
/findmyfav
: Recommends stocks based on specified criteria. -
/risk
…
LLM with RAG system
I used Faiss as vector database and Langchain to get text from any sources I could think of (.pdf, .doc, .ppt, .txt, .md, .epub, link, ebook, youtube...). If you ask Chatgpt, it will sometime mislead you or create fake answer. Although the answer might be correct, it doesn't follow the lecturer's documents.
This RAG system take the answer from our documents to produce results, so the results are more accurate and we can immediately check its correctness. I also tested on the Software Testing Quizz, the result was about 7/10. I also ask chatgpt, but the answer seems bad.
But Questions with the answer "All the answers are correct" are often wrong. Perhaps it's because the model only finds the answer with the highest probability, so the aggregated answers are not fit to this case. Maybe I should rewriting the prompt. Additionally, a small part of the learning resources are images, and I'm actually still looking for ways to optimize the explanation for the images.
My LLM + RAG system:
mrzaizai2k
/
LLM-with-RAG
I just wanna build my own LLM with RAG
LLM-with-RAG
I just wanna build my own LLM with RAG
Table of Contents
Introduction
Welcome to the my LLM with RAG system! This system is designed for me the ease the learning as a master in HCMUT
Features
-
Update vector database
curl -X POST http://localhost:8083/update
-
Ask questions with vector data
curl -X POST -H "Content-Type: application/json" -d '{"query": "who is karger"}' http://localhost:8083/query
Nougat
Link: https://github.com/facebookresearch/nougat
nougat data/web_data/Growth_of_Functions.pdf --markdown --no-skipping -m 0.1.0-base -o data/nougat
How to Set Up
Prerequisites
Before running the system, follow these steps to set up the environment:
-
Clone the Repository:
- Close the Git repository to your local machine:
git clone [repository_url]
- Close the Git repository to your local machine:
-
Install Dependencies:
-
Navigate to the project directory and install the required packages using the provided
setup.txt
file:pip install -r setup.txt
-
To read
.ppt
file we need to run this codeapt update apt install libreoffice
…
Online Courses Summary (In the future)
During the pandemic, I realized that I'm best at learning online courses. I usually watch the video 2 or 3 times, fast forwarding unimportant parts (focusing on the 20% of the time that brings 80% of the value). I plan to record all the lectures, then ask the model to synthesize and track which time period and what topic is being talked about... Or convert it to text format to save in the database for LLM + RAG system
Summary
I am convinced that individuals adept at utilizing LLMs can elevate their performance by up to 200%. To stand out among others, it requires a combination of diligent effort and the right tools. Even a marginal improvement of 1% can contribute significantly to your success.