[ Tech stack ]
Pinecone
The fully managed serverless vector database, with zero infrastructure to run.
Pinecone is a fully managed, serverless vector database: you send it embeddings, query by similarity, and the service takes care of indexing and scaling. Namespaces isolate tenants, metadata filtering combines semantics with business criteria, and hybrid sparse-dense search sharpens relevance. It's our choice when a team wants a production RAG pipeline fast, without operating a vector cluster.
[ Why Pinecone at Dexon ]
What this technology does well, and why we use it.
Typical usage: Ops-free production RAG, multi-tenant SaaS semantic search, recommendation.
- 01
Managed serverless: no cluster to size, usage-based billing.
- 02
Namespaces and metadata filtering: multi-tenant and business-aware queries.
- 03
Hybrid sparse-dense search to blend keywords with semantics.
- 04
Integrated inference: embeddings and reranking without a separate pipeline.
[ Complementary technologies ]
The building blocks we often mobilise alongside
A stack rarely exists alone. Here are the technologies Dexon most often pairs with this one, through pipeline habits, usage similarity or internal mastery. Click on a building block to see its scope.
[ Reassurance ]
- 0+
- custom projects delivered
- 30
- engineers, designers, project managers
- 80 %
- from top French schools
- 24 h
- average reply time
[ They trust us ]
More than 100 French and European companies trust us
[ Press ]
They talk about us
Discover what the business and tech press say about us. An outside reading of our work and our innovations.
