Hello everyone, my name is Luis Enrique, today we are going to discuss the topic of generative AI on AWS, and why not talk a little about the AWS star service Amazon Bedrock in which you can use different frameworks such as the Lang Chain Lama index or also multiple
different Foundation models whenever a new Foundation model is likely to emerge.
Amazon Bedrock you can use to create end-to-end applications, you know, and with respect to all these types of Foundation models, how they can also be fine-tuned with your own custom data set
Deploying applications or generative AI applications In the cloud, the cloud platform basically means AWS another service that you can work with is with AWS Sage Maker how you can create a GenAI application from start to finish.
Within these services you can take it to the implementation part up to the production phase, how you can do all the deployments, how you can create all these amazing LLM techniques, LLM Ops. Well, before it was MLOPS, now LLM Ops specifically, where you can work with these kinds of LLM models in Bedrock where most of the best LLMs on the market are concentrated and which are specifically available with respect to AWS, if I talk about that there are different Foundation models, both open source and open source. Paid source, all those kinds of models are there as well, right?
For the most part, they charge with respect to inference and with respect to paid models, they can charge based on the number of requests, right?
These models obviously so far have shown everything with respect to development how we can deploy their potential to develop them in a coding environment itself, but again, the main objective is to take it to production whether in RAG right that is very important because in companies today they need it.