Activity
Mon
Wed
Fri
Sun
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
What is this?
Less
More

Memberships

Data Alchemy

Public • 23.5k • Free

Data Freelancer

Private • 99 • Paid

You Probably Need a Robot

Private • 1.7k • Free

2 contributions to Data Alchemy
Improve Your RAG Systems with Azure Document Intelligence
Working with unstructured documents can be a challenge, but there's a way to make it more manageable and effective. Azure Document Intelligence offers a robust solution for extracting meaningful information from complex layouts and converting it to structured markdown format. In this week's video, I guide you through techniques for chunking documents and integrating OCR tools with vector databases to enhance your RAG systems.
26
10
New comment Jul 22
Improve Your RAG Systems with Azure Document Intelligence
3 likes • Jul 13
Awesome, thank you for sharing it! Another approach that I'm testing right now is using Google Document AI (OCR $1.50 per 1000 pages) + Gemini Flash to format to Markdown. I send the content from Document AI along with the page image, and then I instruct the model to format to Markdown. By sending the page image, the model has an idea about the layout. In the end, the average cost is $0.003 per page.
1 like • Jul 13
@Daniel Zivkovic Another service that I’ve used was Llama Parse the results is in markdown and is very good, the problem is that now I have to process PDFs that have scanned pages, obfuscated text, and bad quality, and in that case the results with the approach that I mentioned was better
Welcome to Data Alchemy - Start Here
The goal of this group is to help you navigate the complex and rapidly evolving world of data science and artificial intelligence. This is your hub to stay up-to-date on the latest trends, learn specialized skills to turn raw data into valuable insights, connect with a community of like-minded individuals, and ultimately, become a Data Alchemist. Together, let's decode the language of data and shape a future where knowledge and community illuminate our way. Rules - Don't sell anything here or use Data Alchemy as any kind of funnel - We delete low effort community posts, and posts with poor English. Proofread your post first. - Help us make the posts high quality. If you see a low quality post, then click on the 3 dots on the post and "Report To Admins". Start by checking out these links - Classroom - Introduction - Roadmap - Contribution Be Aware of Scammers - Please be aware that this is a public group. Unfortunately, some people abuse the Skool platform to send DMs or post comments to trick people. This is the internet, so always do your own due diligence. Never automatically trust someone here on the Skool platform other than @Dave Ebbelaar's official account. To kick things off, please comment below, introducing yourself. Let us know: 1. Your name and where you're from 2. What project(s) you're currently focused on See you in the comments!
Complete action
849
12k
New comment 4h ago
Welcome to Data Alchemy - Start Here
8 likes • Jul 5
Hi, I'm Thierry from Brazil. I recently joined an AI company and am very interested in learning more about the field.
2 likes • Jul 10
@Anaxareian Aia It's tela.com I'm working as software engineer building the product, from the front-end to backend. It's recent, the last entire month I were working in our parser service, more specific building a PDF parser that's used in our product.
1-2 of 2
Thierry Santos
2
6points to level up
@thierry-santos-1121
full-stack engineer with focus on backend and AI

Active 24d ago
Joined Jul 4, 2024
ISTJ
São Paulo, Brazil
powered by