Doc2Vec is an unsupervised algorithm used to convert documents in vectors (dense embeddings). It is based on the Paragraph Vector paper and implemented in the Gensim Python library and elsewhere. The algorithm can work in either a Distributed Bag Of Words mode (PV-DBOW, which works somewhat analogously to skip-gram mode in Word2Vec) or a Distributed Memory mode (PV-DM, which is more analogous to CBOW mode in Word2Vec.)
