Currently this one handles excel files. But docling is capable of parsing complex docs that include tables, charts, figures etc. It has dedicated models for layout detection and extracting tabular data.
@akshay_pachaar
-
Llama 3.2 Vision Model for Invoice Processing Tasks
By
–
Since you're processing individual invoices, I would recommend trying with Llama 3.2 vision model directly. If there the accuracy is not great, then you can try other methods.
-
Python and ML/AI Engineering Tutorials Daily
By
–
That's a wrap, if you're interested in: – Python – ML/AI Engineering Find me →
@akshay_pachaar
Everyday, I share tutorials on above topics! -
Getting Started with RAG for Complex Document Processing
By
–
This is a good place to get started with RAG over complex docs! We'll cover more advanced techniques very soon! Find all the code here: https://
github.com/patchy631/ai-e
ngineering-hub/tree/main/rag-with-dockling
… -
Create Query Engine to Ask Questions About Excel Data
By
–
Finally, create a query_engine and start asking question about your excel data! Check this out
-
Embedding Data and Creating Index for Next Steps
By
–
Next step is to embed the data and create an index. Check this out
-
Setting Up LLM and Embedding Model After Knowledge Base
By
–
Once our knowledge base is ready it's time to setup the LLM and embedding model! Check this out
-
LaTeX OCR with Llama: AI Engineering Hub Repository
By
–
Find code here: https://
github.com/patchy631/ai-e
ngineering-hub/tree/main/LaTeX-OCR-with-Llama
…
_____
Interested in ML/AI Engineering? Sign up for our newsletter for in-depth lessons and get a FREE eBook with 150+ core DS/ML lessons: -
Image to LaTeX Converter Using Llama 3.2 Vision Model
By
–
Image to LaTeX powered by multimodal Llama 3.2!
— Akshay 🚀 (@akshay_pachaar) 8 décembre 2024
.
.
Upload image of an equation, and it gives you the corresponding LaTeX code.
Here's what you need:
– Ollama for serving Llama 3.2 vision locally
– Streamlit for the UI
Everything is just 50 lines of code!
Link to the code in… pic.twitter.com/tMCt93sjgGImage to LaTeX powered by multimodal Llama 3.2!
.
.
Upload image of an equation, and it gives you the corresponding LaTeX code. Here's what you need: – Ollama for serving Llama 3.2 vision locally
– Streamlit for the UI Everything is just 50 lines of code! Link to the code in -
Python, Machine Learning, and AI Engineering Tutorials Daily
By
–
If you interested in: – Python – Machine Learning – AI Engineering Find me → @akshay_pachaar Everyday, I share tutorials on above topics! Cheers!