Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Mapping the French Culinary Network

Mar 03, 2025 - theophilec.github.io
The article discusses a project that uses LeFooding.com restaurant reviews to map the French culinary network by extracting structured data about restaurant staff and their previous workplaces. This data is visualized as a graph with nodes representing people and restaurants, and edges representing their relationships. The project employs OpenAI's gpt4o-mini model for structured data extraction, despite challenges with hallucinations and errors, and uses gephi-lite for visualization. The project aims to provide insights into the French restaurant scene by analyzing connections between staff and establishments.

The process involves scraping data from LeFooding.com, extracting structured information using large language models, and visualizing the data with WebGL. The project highlights the potential of LLMs for extracting information from text sources and discusses the tools and techniques used, including the `outlines` library for structured generation and a web app for data editing. The author plans to improve the process by using open models and addressing remaining data duplicates.

Key takeaways:

  • The project involves creating a network visualization of the French restaurant scene using data from LeFooding.com reviews, highlighting relationships between staff and restaurants.
  • Structured generation techniques are used to extract information from reviews, with OpenAI's gpt4o-mini model proving most effective for this task.
  • The visualization is created using gephi-lite and WebGL, with a focus on spatial layout to represent connections and node prominence.
  • Future improvements include refining the model's accuracy and potentially using open models like Mistral or Llama for similar tasks.
View Full Article

Comments (0)

Be the first to comment!