Netflix Inc.

Naveen Mareddy

Francisco J San Miguel

Anush Moorthy

Megha Manohara

Ameya Ramesh Vasani

Chih Hao Lin

Dmitry Vasilyev

Guanhua Ye

Xiaomei Liu

Rick Wong

In various embodiments, a serverless function agent determines that a client stub function has been invoked with a first set of arguments in a first execution environment. The serverless function agent then performs one or more operations on a media item that is associated with a first argument included in the first set of arguments to generate a second argument included in a second set of arguments. Notably, the first argument has a first data type and the second argument has a second data type. Subsequently, the serverless function agent invokes a function with the second set of arguments in a second execution environment. Advantageously, because the serverless function agent automatically performs operations on the media item, the overall amount of technical know-how and manual effort required to enable the function to successfully execute on a wide range of media items can be reduced.

Techniques for executing serverless functions on media items

In various embodiments, a function build application compiles source code to generate an executable version of a function that has a first function signature. The function build application then replaces a first data type of a first parameter included in the first function signature with a second data type to generate a second function signature for a client stub function. Subsequently, the function build application generates a remote procedure call (RPC) client that includes the client stub function. Notably, the RPC client causes the function to execute when the client stub function is invoked. Advantageously, unlike conventional techniques that require manual generation of strongly typed functions, the function build application automatically customizes the RPC client for the function.

Techniques for interfacing between media processing workflows and serverless functions

In various embodiments, a workflow engine executes a custom algorithm on a media item. In operation, the workflow engine generates split specifications based on a split function included in a container image. Each split specification is associated with a different portion of the media item. Subsequently, the workflow engine generates map output files based on the split specifications and a map function included in the container image. The workflow engine then generates one or more final output file(s) based on the map output files and a collect function included in the container image. The final output file(s) are subsequently used to perform at least one of an evaluation operation on, a modification operation on, and a representation operation with respect to the media item.

Scalable techniques for executing custom algorithms on media items

Growing community of inventors

San Ramon, CA, United States of America

Naveen Mareddy