How our recipe extraction pipeline works
March 15, 2026 · Recipe Manager Team
Every time you import a recipe, we run it through four extraction
stages, each faster and more reliable than the last.
1. **Page-by-page**: we use font-based title detection to find recipes
without calling any AI.
2. **Cluster-based**: if that fails, we look for dense ingredient
groupings anywhere in the document.
3. **Font-based**: a simpler heuristic fallback.
4. **Vision AI**: as a last resort, we render each page as an image and
let a vision model read it directly.
The whole pipeline runs in parallel, caches aggressively, and falls
back gracefully. Next time you import a popular cookbook, chances are
we've seen it before and return results in a few hundred milliseconds.
#engineering#ai