Show HN: Visualizing How Books Reference Each Other Across 3k Years(thiagolira.github.io)
thiagolira.github.io
Show HN: Visualizing How Books Reference Each Other Across 3k Years
https://thiagolira.github.io/bookgraph-revisited/
3 comments
I love this, how much tokens/$ did you spend to be able to extract and link all of them?
I used DeepSeek V3.2 for everything at $0.25/M input tokens and $0.38/M output tokens.
I lost count of how many runs I had until I was satisfied with the results. I'd say for the final books I spent +- $10, so some millions of tokens!
I lost count of how many runs I had until I was satisfied with the results. I'd say for the final books I spent +- $10, so some millions of tokens!
this is so cool!
FYI "Tractatus de sphaera, John of Holywood" appears to be wrongly been put in BC
FYI "Tractatus de sphaera, John of Holywood" appears to be wrongly been put in BC
1) The LLM-powered pipeline to extract citations (books + authors) from books and resolve them using both Wikipedia and Goodreads with offline copies I have. The result is data associating Books/Authors to other Books/Authors with accurate bibliographical information spanning centuries.
2) A WebGPU + D3.js powered visualization tool written by Claude Code so I'm able to deal with all this data on the browser on a more or less comfortable experience for the viewer.
I spent some months on a off with this project, and definitely the most challenging part was dealing with accurate bibliographical information across centuries, with original publication dates and etc. For that I wrote what is now a very complex pipeline with LLMs (I used DeepSeek V3.2) wired on offline Goodreads and Wikipedia databases + a fallback that actually uses the internet.
Hope you enjoy it! Open to suggestions on how to improve the system :)
Code is here: https://github.com/ThiagoLira/bookgraph-revisited