Not an expert, but here are my 2 cents until there will be a better answer:
Winds are not directly responsibly for the evaporation. Rather can they consist of evaporated material.
The cause for the evaporation of gas out of the accretion disk is primarily heating from the much hotter corona. Or as Liu & Taam put it:
The ions in the corona are directly heated by viscous
dissipation, partially transferring their energy to the electrons by
means of Coulomb collisions. The energy gained by electrons
cannot be effectively radiated away and is conducted to the
lower, cooler, and denser coronal layers by electron–electron
collisions. In the transition layer, the conductive heat flux
is radiated away through bremsstrahlung only if the number
density in this layer reaches a critical value. If the density
is too low to efficiently radiate the energy (lower than the
critical value), a certain amount of lower, cooler gas is heated
up, whereby the bremsstrahlung cooling rate is raised, until
an energy equilibrium is established between the conduction,
radiation, and heating of the cool gas. The transfer of gas
from the disk to the corona, to establish the equilibrium, is
So, all you need for evaporation is a hot corona above the accretion disk and more heat transfer as you can radiate away. Then gas will "boil off" and the corona will "dig into" the disk until a critical density and equilibrium is reached.
For all this you do not need any winds. A wind will originate from the disk or the corona when gas is further accelerated outwards. This acceleration can be primarily radiation or line-driven when the intense radiation from the central regions illuminates the outer parts of the disk (see here). This also works for AGN. See e.g. these simulations.
Alternatively, these winds can also be (partly) magnetically or thermally driven. Which of these mechanisms dominates depends on the type of source (e.g., AGN/XRB), state and position on the disk. (Someone else might be able to give details here.)
And because images are always nice, here is a graphic how one can imagine the geometry for an AGN (from this paper):