Hi, community,
after long experiments and bug fixing, I finally launched this project. https://enumhq.com
The idea is to provide a simple way to load multiple data sources, extract text and be able to ask questions on them. I started with plain text (copy-paste), PDF files, and websites.
Free indexing up to 200 pages.
Useful for students, explorers, and businesses that would like to provide great support when they are OOO (not implemented yet
)
Iām eager to hear your opinion. Do you find it useful? What to improve in the first place?
NB You can use your own OpenAI key and ask unlimited questions. All keys are stored in our database encrypted.
Thanks!
My only question (and itās the same question I have for all of these types of services):
How do you handle parsing PDFs which contain typeset equations (both inline and blocks) and use LaTeX packages like algorithm2e
to typeset algorithms?
Because, for people (like me) who are only interested in highly technical journal articles where all of the important bits are locked in equations and algorithms every single āchat with your documentsā service Iāve seen badly bungles this.
If you can demonstrate high-quality/high-reliability parsing of these elements, you might have something I (and countless others like me) would be interested in.
1 Like
Hi!
Thanks a lot for your question. Actually, Iām very interested in implementing such functionality. Iād love to look at the example PDF filled with equations and formulas printed in any format to see how I can recognize and index them. If you wouldnāt mind, can you please send me them at info@enumhq.com ?
Can you please also give me an example question youād ask on such documents?
Thanks again.
Tonight or tomorrow Iāll be able to gather a couple of example documents and Iāll sent them your way.
1 Like
Hi, I am still waiting for the file examples. Maybe you can point me to where I can find them and how to distinguish when a file contains LaTeX blocks?
Meanwhile, we implemented the rendering normal formulas and equations that can be part of the answer: