This talk will explore the mean-field limit of non-exchangeable particle models. Starting with a model that describes the trajectories of N particles in d-dimensional space, the goal is to derive a model that describes the evolution of the distributions of the positions and velocities of these particles. Mathematically, this amounts to proving that the solution to an ordinary differential equation in R^{2dN} converges, as N tends to infinity, to the weak solution of a partial differential equation in the set of probability measures on R^{2d}. The classical interpretation of this limit requires working with an exchangeable model, that is where the interaction between two particles depends only on their respective positions and velocities. However, this assumption is unlikely to be valid in many biological systems, such as herds of cattle or sheep, where other parameters, such as age or sex, can influence how two individuals interact. First, we will present a framework, based on the notions of graphons and fibered probability spaces, that allows us to interpret the mean-field limit of non-exchangeable particle models. We will then apply this framework to derive a non-exchangeable Vlasov-type equation from the Cucker-Dong model, which incorporates the three main interactions used to describe large groups of animals: alignment, long-range attraction, and short-range repulsion.