AWS

Situation A custom Typee deployment generates app configuration by a AWS Lambda. But there are some drawbacks: AWS Lambda has high delay when code start is required. Each refresh of a custom Typee deployment costs a AWS Lambda call and DynamoDB call. But the configuration actually changes less frequently. Solution I told myself as MVP I shouldn’t keep it simple and brutal, but I failed to convinced myself. First version I firstly put the Lambda behind Cloudfront(CDN)....

Overview This article describes how to implement a AI Chat API, in AWS. It will discuss use cases, requirements, architectures and detail designs. Use Case In SaaS version of Typee, An authorized user can use a preset model without setting up any configuration. Admin first needs to setup an model which include a model name, a backing model, API Key for the backing model, and if use training data. Once Admin finish setup and published the model, Authorized users can see the new model in front end and are ready to use....