🧞♂️Transform unstructured PDFs Job Offers into a dataset w. gemma4:2b
The article discusses a project that transforms unstructured PDF job offers into a structured dataset using Gemma 4. This initiative aims to facilitate the comparison and management of job offers by standardizing their format. By creating a well-structured database, the project enhances the efficiency of job searches and data analysis.
- ▪The project utilizes Open Data Public Sector Job offers as input to create a structured dataset.
- ▪Gemma 4 is employed to standardize the format of job offers, making them easier to compare.
- ▪The outcome includes well-structured markdowns, a clean database for SQL reporting, and organized ePub and PDF documents.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 446871) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } adriens Posted on May 17 🧞♂️Transform unstructured PDFs Job Offers into a dataset w. gemma4:2b #devchallenge #gemmachallenge #gemma #dataengineering Open Data (6 Part Series) 1 🎙️ Interview avec ChatGPT : Data Citizen, Developer Citizen, Kézako? 2 🤔 Rétrospective sur 6️⃣ années de (Data) Citizen Developer 🏙️ ... 2 more parts...
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
