The use case: how Allspice deploys Pinecone
Allspice uses Pinecone as a semantic vector layer to match messy ingredient text to its structured ingredient database, which makes its recipe importing work. It also uses Pinecone for recipe similarity, fuzzy recipe search, and normalizing free-form chatbot inputs.
More reported results
Figures published in Pinecone’s case study. They are not independently measured by usedby.
the platform now manages a growing library of 110,000 total embeddings
The platform now indexes approximately 100,000 recipe embeddings.
In the customer’s words
Now more than ever, it is crucial to iterate quickly. I would have never tried Pinecone without a cloud-hosted, serverless option. I needed something that I could set up in an afternoon and get working in a basic pipeline to evaluate the effectiveness of my solution to my problems.Pinecone users in DevTools & Infrastructure
Companies in the same sector, with public evidence.
See all Pinecone customersGo straight to the source
Based on Pinecone’s published case study. We check the public evidence; the results are reported by the vendor.
pinecone.io- Last checked
- Nov 11, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 20% → 97%Checked
The figure is on the page; its label is our wording.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Allspice.
- Allspice uses PineconeChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Before Pinecone, ingredient matching accuracy sat at roughly 20% — far too low to support a production feature. After implementation, accuracy jumped to 97%, with Pinecone serving as the core enabling piece of the matching system.



