System and method for deploying and versioning machine learning models

1. A method comprising:

receiving a request from a remote computer for a pre-trained machine learning model;

receiving one or more parameters for the pre-trained machine learning model via a first application programming interface (API), the API being accessible by the remote computer via an application executing on the remote computer and wherein the one or more parameters comprises a machine learning model type for the pre-trained machine learning model and data to be analyzed by the pre-trained machine learning model;

retrieving from a library of a plurality of machine learning models the pre-trained machine learning model corresponding to a type of model specified in the one or more parameters;

generating a container image comprising the pre-trained machine learning model and the data to be analyzed by the pre-trained machine learning model; and

provisioning a container based on the container image, wherein the pre-trained machine learning model analyzes the data following provisioning.

2. The method of claim 1 , further comprising:

analyzing the data using the pre-trained machine learning model; and

providing results of the analyzing via a second API accessible to the remote computer.

3. The method of claim 1 , wherein each of the one or more parameters are directed to a dependency in a plugin.

4. The method of claim 3 , wherein generating the container image comprising the pre-trained machine learning model and the data, comprises:

injecting the pre-trained machine learning model as a dependency into the plugin.

5. The method of claim 1 , further comprising:

identifying an increase in requests for the pre-trained machine learning model; and

increasing a number of containers comprising the container image.

6. The method of claim 1 , wherein the data is associated with an address corresponding to a storage location where the data is located.

7. The method of claim 1 , further comprising:

identifying a decrease in requests for the pre-trained machine learning model; and

decreasing a number of containers comprising the container image.

8. A non-transitory computer readable medium having one or more instructions that, when executed by a computing system, causes the computing system to perform one or more operations comprising:

receiving a request from a remote computer for a pre-trained machine learning model for analyzing an image file, the request comprising one or more parameters that include a machine learning model type for the pre-trained machine learning model and the image file to be analyzed by the pre-trained machine learning model;

retrieving from a library of a plurality of machine learning models the pre-trained machine learning model corresponding to the machine learning model type specified in the one or more parameters;

generating a container image comprising the pre-trained machine learning model and the image file to be analyzed by the pre-trained machine learning model; and

provisioning a container based on the container image, wherein the pre-trained machine learning model analyzes the image file following provisioning.

9. The non-transitory computer readable medium of claim 8 , further comprising:

analyzing the image file using the pre-trained machine learning model; and

providing results of the analyzing to the remote computer.

10. The non-transitory computer readable medium of claim 8 , wherein each of the one or more parameters are directed to a dependency in a plugin.

11. The non-transitory computer readable medium of claim 10 , wherein generating the container image comprising the pre-trained machine learning model and the image file, comprises:

injecting the pre-trained machine learning model as a dependency into the plugin.

12. The non-transitory computer readable medium of claim 11 , further comprising:

identifying an increase in requests for the pre-trained machine learning model; and

increasing a number of containers comprising the container image.

13. The non-transitory computer readable medium of claim 8 , wherein the image file is associated with an address corresponding to a storage location where the image file is located.

14. The non-transitory computer readable medium of claim 8 , further comprising:

identifying a decrease in requests for the pre-trained machine learning model; and

decreasing a number of containers comprising the container image.

15. A system, comprising:

a processor; and

a memory having programming instructions stored thereon which, when executed by the processor, performs an operation comprising:

receiving one or more parameters via a first application programming interface (API) for a pre-trained machine learning model, wherein the one or more parameters comprises a machine learning model type and data to be analyzed by the pre-trained machine learning model;

retrieving the pre-trained machine learning model corresponding to the machine learning model type specified in the one or more parameters;

generating a container image comprising the pre-trained machine learning model and the data to be analyzed by the pre-trained machine learning model;

provisioning a container based on the container image;

following the provisioning, analyzing the data using the pre-trained machine learning model; and

providing results of the analyzing via a second API.

16. The system of claim 15 , the operation further comprises:

identifying an increase in requests for the pre-trained machine learning model; and

increasing a number of containers comprising the container image.

17. The system of claim 15 , wherein the second API is configured to allow input of one or more files to be analyzed using the pre-trained machine learning model.

18. The system of claim 15 , wherein each of the one or more parameters are directed to a dependency in a plugin.

19. The system of claim 18 , wherein generating the container image comprising the pre-trained machine learning model and the data comprises:

injecting the pre-trained machine learning model as a dependency into the plugin.

20. The system of claim 15 , wherein the data is associated with an address corresponding to a storage location where the data is located.