gpt-graph. A simple, GPT-3 text to entity-relation graph generator
Hi HN! This is a simple text to entity-relation graph generator, powered by gpt-3 davinci model. The purpose is to feed it actual written data, to obtain a graph representation of entities and relationships mentioned in the text. Also, being able to identify entity attributes like gender, size, age ... My initial goal, was to make it able to process a large amount of text into a big single graph. The problem being the 4000 token limit the model has, I decided to take the approach of feeding the text in batches, and try to merge the incoming graph with the existing information each time. This…
In plain words
gpt-graph uses GPT-3 to convert written text into entity-relation graphs, extracting entities, their relationships, and attributes like gender, size, and age. It processes large texts by breaking them into batches and merging results into a single graph, overcoming token limits through incremental node comparison. The tool is designed for anyone needing to visualize and structure information from unstructured text data, though entity deduplication could be refined.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! This is a simple text to entity-relation graph generator, powered by gpt-3 davinci model. The purpose is to feed it actual written data, to obtain a graph representation of entities and relationships mentioned in the text. Also, being able to identify entity attributes like gender, size, age ... My initial goal, was to make it able to process a large amount of text into a big single graph. The problem being the 4000 token limit the model has, I decided to take the approach of feeding the text in batches, and try to merge the incoming graph with the existing information each time. This is done by comparing the incoming node labels with those already in the graph, adding the new information to the existing nodes. This works somewhat, but sometimes entities get duplicated if they are mentioned slightly differently in the text. The comparation method could use some improvement clearly. A nice feature, is that you get to decide what types you want to extract. So if, for example, you are interested only in people, and companies in the text, you can tell the model to stick to that. You can also leave the types to the model discretion. Also, the application allows for saving / loading graphs to json files. These files can be used with Cytoscape Desktop Application, which is a nice side effect of using cytoscape.js. in the UI. I think tools like this can really be of help when going through dense documentation. To have a visual representation of the concepts, entities or whatever, can be really helpful in education, investigation, legal ... Would love to hear your thoughts on how this could be improved.
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 · 27d ago · cactuscompute.com
Launched alongside, March 2023
the whole month →
- BI
I'm a big fan of the BBC podcast In Our Time -- and (like most people) I've been playing with the OpenAI APIs. In Our Time has almost 1,000 episodes on everything from Cleopatra to the evolution of teeth to plasma physics, all still available, so it's my starting point to learn about most topics. But it's not well organised. So here are the episodes sorted by library code. It's fun to explore. Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript definition. At the same time I…
AI · 2023 · genmon.github.io