This speak by Harrison Chase of Langchain will concentrate on how “reminiscence” within the context of LLM functions. Reminiscence is most frequently mentioned within the context of chatbots so it can begin with an outline of conversational reminiscence. This will fluctuate from easy (buffer of latest messages) to complicated (extracting and dynamically producing a data graph). It then covers latest advances in reminiscence, together with the “Generative Brokers” paper (see hyperlink beneath). It can end with an outline of the place the area is now and the place it might go sooner or later (it’s nonetheless early days!)
Generative Brokers Paper (8:19) https://arxiv.org/pdf/2304.03442.pdf
Subscribe and activate notifications for upcoming Absolutely Linked content material!
Watch full playlist right here:https://www.youtube.com/playlist?list=PLD80i8An1OEHbWdBlST26cbOB_3lQu_cu
#LLMs #DeepLearning #AI #Modeling #ml #langchain
