Talk2Arxiv
Learning and science
research paper chat
SHOW HN2023
How HN took it
4 positive, 18 neutral or asking, 1 mixed, 6 critical, out of 29 comments about the project. Thread score -0.05.
Execution: 2 for, 1 againstPerformance: 0 for, 3 againstIdea: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
The URL-prefix trick is clever and useful
From 2 comments
Idk where this changing the url thing started but I really like it.
katella on HNIt works well with bookmarklets. This swizzles between arxiv.org <-> www.talk2arxiv.org. I've now added it to my Favorites bar, next to arxiv.org/abs <-> arxiv.org/pdf and…
osteele on HN
Works well and is a cool solution
From 2 comments
Very nice; appears to work well. Just an FYI that I did get a couple errors where the max context length was exceeded, one using the demo summarization task as the first query. I…
gorkish on HNThis is the first time I have seen someone use GROBID. It seems like an incredibly cool solution
skeptrune on HN
Objections
Struggles with math and symbolic text from PDF extraction
From 1 comment
Context length errors on long papers
From 2 comments
Very nice; appears to work well. Just an FYI that I did get a couple errors where the max context length was exceeded, one using the demo summarization task as the first query. I…
gorkish on HNThis is the paper that would reliably trigger context overflows. https://arxiv.org/abs/1811.03116 It otherwise did an admirable job on this brainbender.
gorkish on HN
Requests for OpenAI API key entry raises privacy concerns
From 2 comments
Will it become normal to paste your OpenAI keys into a website and will it become the new curl-sudo-bash or checking cloud credentials into github?
willvarfar on HNAll while calling the solution open source.
imjonse on HN
Requests
Move to LaTeX source or HTML instead of PDF parsing
From 2 comments
You might be able to drop the PDF backend since they're close to getting HTML running well: https://news.ycombinator.com/item?id=38713215 Using that might be easier than a…
pushfoo on HNYes, using the LaTeX source code (or HTML, once that becomes reliable and widely used) should be much more robust than PDF parsing.
Mandelmus on HN
Support for bioRxiv
From 2 comments
Any plans for bioRxiv?
aendruk on HNThis is great! We could also point it to https://biorxiv.org/ Awesome work!
gtsnexp on HN
Local LLM support such as Ollama
From 1 comment
What's the easiest way to adapt this to local LLMs like Ollama or Lama.cpp
killingtime74 on HN
Questions
Can it answer questions about references?
From 1 comment
Is it able to answer questions about references?
friend_and_foe on HN
Which vector dimension and metric were used in Pinecone?
From 1 comment
Awesome project. What metric and dimension size did you set on Pinecone?
soliax on HN
Alternatives named
Marker and Nougat for PDF to markdown conversion
From 2 comments
Maybe you could use: https://github.com/facebookresearch/nougat/tree/main or https://github.com/VikParuchuri/marker Both are tools to convert pdfs into Latex or Markup with latex…
Koaisu on HNI've spent the last couple weeks diving into various PDF parsing solutions for scientific documents. GROBID is pretty cool, but it made some mistakes when trying to parse (I…
pugio on HN
ar5iv HTML versions of arXiv papers
From 1 comment
I wonder if they knew that they could get html versions of the paper by just changing the link from ...arxiv.. to ar5iv..
arbitrandomuser on HN
Cheshire Cat and Ollama web UI for chatting with PDFs
From 1 comment
There are a bunch of little projects that do this. It's on the roadmap for ollama-webui (but not implemented yet), and Ollama published a guest blog post with a simple…
lolinder on HN