Visualizing How Books Reference Each Other Across 3k Years
There are two parts for this project: 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…
What it does
In the maker’s words, at launch
There are two parts for this project: 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
Does the same job
all alternatives →- GDGoodreads Data Pipeline2020 · github.com · ▲213
- TAThrow a Whole Book into an LLM to Extract Characters and Relationships2025 · github.com · ▲9
Let's try a small experiment with LLMs that have a large context length: feed an entire book into the context window and ask it to generate a list of characters, their relationships, and physical descriptions—data that can later be used for image generation. In this repository, you can find two tools: a script that extracts data from book text using an LLM (Gemini or OpenRouter API) and an HTML/JS (D3) visualization of the character graph. An external text-to-image model can be used to generate character illustrations (a Google Colab example is provided). Explore the visualizations,…
- KAKooba, an interactive graph for finding new books2017 · koob.jake.run · ▲145
- SPSelf-Published Book – “Data Science in Production”2020 · ▲172
Hi HN, Over the past 6 months I've been working on a technical book focused on helping aspiring data scientists to get hands-on experience with cloud computing environments using the Python ecosystem. The book is targeted at readers already familiar with libraries such as Pandas and scikit-learn that are looking to build out a portfolio of applied projects. To author the book, I used the Leanpub platform to provide drafts of the text as I completed each chapter. To typeset the book, I used the R bookdown package by Yihui Xie to translate my markdown into a PDF format. I also used Google docs…
- GOGraph of wikipedia articles semantic similarity (LSI, Python, d3.js)2012 · similarityapi.appspot.com · ▲54
Small experiment of visualization of wikipedia articles as a graph using d3.js.<p>Articles with more traffic are bigger. I computed the semantic similarity using LSI with python (gensim) You have to scroll down/right a bit!<p>http://similarityapi.appspot.com/graph/?title=blade%20runner<p>There is also a JSON api: http://similarityapi.appspot.com/api/v1/?limit=100&title=blade%20runner<p>All feedback is appreciated:<p>@lucamartinetti [email protected]
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
