[ Tech stack ]
LangChain
The reference open source framework for building LLM applications.
LangChain is an open source framework (Python, JS/TS) for building LLM applications: prompt chains, tool calling, RAG components and integrations with model providers and vector stores. Its shared abstractions let you swap models or vector stores without rewriting business logic. It's our choice when an AI application needs to orchestrate LLMs, data and tools without locking into a single provider.
[ Why LangChain at Dexon ]
What this technology does well, and why we use it.
Typical usage: RAG assistants, structured extraction, tool-using agents, fast AI app prototyping.
- 01
Unified abstractions: swap LLMs or vector stores without rewriting the app.
- 02
Tool calling and structured outputs for agents and extraction.
- 03
Ready-made RAG components: loaders, splitters, retrievers, embeddings.
- 04
Python and JS/TS, with LangSmith for tracing and evaluation in production.
[ 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.
Nationwide coverage by BFM Business, Le Figaro, Challenges, La Tribune and CNews. An outside reading of our work and our innovations.
