Integrated development environments for generating machine learning models

1 . A computer-implemented method executed by data processing hardware that causes the data processing hardware to perform operations comprising:

receiving, from a user device, a request indication indicating a graphical user interface (GUI) interaction by a user within a GUI presented on the user device;

in response to the request indication, providing, to the user device, a structured prompt response configured to cause the user device to display, within the GUI, a structured prompt comprising one or more user input fields, each of the user input fields representing a corresponding training sample and comprising:

a first corresponding text input field for capturing text representative of corresponding input text to be provided to a machine learning (ML) model; and

a second corresponding text input field for capturing text representative of corresponding ground-truth output text for the corresponding input text;

receiving, from the user device, one or more training samples, each of the one or more training samples comprising captured text from the first corresponding text input field and the second corresponding text input field;

in response to receiving the one or more training samples, adjusting the ML model using the one or more training samples;

receiving, from the user device, test input text representative of captured text from one of the one or more user input fields;

generating, using the ML model, test output text based on the test input text; and

providing, to the user device, the test output text to cause the user device to display, within the GUI, the test output text.

2 . The method of claim 1 , wherein the structured prompt further comprises a model selection input element allowing selection of one of a plurality of different ML models.

3 . The method of claim 1 , wherein the structured prompt further comprises a preamble text input field for identifying the ML model.

4 . The method of claim 1 , wherein adjusting the ML model comprises using one-shot learning or few-shot learning based on the corresponding training samples.

5 . The method of claim 1 , wherein the operations further comprise:

generating computer code for calling an application programming interface (API), the API configured to provide access to the ML model; and

providing the computer code to the user device.

6 . The method of claim 5 , wherein the operations further comprise:

receiving, via the API, second test input text;

generating, using the ML model, second test output text based on the second test input text; and

returning, via the API, the second test output text.

7 . The method of claim 1 , wherein each training sample of the one or more training samples comprises a row of a table of the structured prompt.

8 . The method of claim 7 , wherein the structured prompt further comprises a row addition user input element for indicating a request to add an additional row to the table.

9 . The method of claim 1 , wherein the structured prompt further comprises:

an input-prefix text input field for capturing text describing the first corresponding text input field; and

an output-prefix text input field for capturing text describing the second corresponding text input field.

10 . The method of claim 1 , wherein, after providing the test output text, the operations further comprise:

receiving, from the user device, one or more additional or refined training samples;

in response to receiving the one or more additional or refined training samples, further adjusting the ML model using the one or more additional or refined training samples;

receiving, from the user device, second test input text representative of captured text from one of the one or more user input fields;

generating, using the ML model, second test output text based on the second test input text; and

providing, to the user device, the second test output text configured to cause the user device to display, within the GUI, the second test output text.

11 . A system comprising:

data processing hardware; and

memory hardware in communication with the data processing hardware, the memory hardware storing instructions that, when executed on the data processing hardware, cause the data processing hardware to perform operations comprising:

receiving, from a user device, a request indication indicating a graphical user interface (GUI) interaction by a user within a GUI presented on the user device;

in response to the request indication, providing, to the user device, a structured prompt response configured to cause the user device to display, within the GUI, a structured prompt comprising one or more user input fields, each of the user input fields representing a corresponding training sample and comprising:

a first corresponding text input field for capturing text representative of corresponding input text to be provided to a machine learning (ML) model; and

a second corresponding text input field for capturing text representative of corresponding ground-truth output text for the corresponding input text;

receiving, from the user device, one or more training samples, each of the one or more training samples comprising captured text from the first corresponding text input field and the second corresponding text input field;

in response to receiving the one or more training samples, adjusting the ML model using the one or more training samples;

receiving, from the user device, test input text representative of captured text from one of the one or more user input fields;

generating, using the ML model, test output text based on the test input text; and

providing, to the user device, the test output text to cause the user device to display, within the GUI, the test output text.

12 . The system of claim 11 , wherein the structured prompt further comprises a model selection input element allowing selection of one of a plurality of different ML models.

13 . The system of claim 11 , wherein the structured prompt further comprises a preamble text input field for identifying the ML model.

14 . The system of claim 11 , wherein adjusting the ML model comprises using one-shot learning or few-shot learning based on the corresponding training samples.

15 . The system of claim 11 , wherein the operations further comprise:

generating computer code for calling an application programming interface (API), the API configured to provide access to the ML model; and

providing the computer code to the user device.

16 . The system of claim 15 , wherein the operations further comprise:

receiving, via the API, second test input text;

generating, using the ML model, second test output text based on the second test input text; and

returning, via the API, the second test output text.

17 . The system of claim 11 , wherein each training sample of the one or more training samples comprises a corresponding row of a table of the structured prompt.

18 . The system of claim 17 , wherein the structured prompt further comprises a row addition user input element for indicating a request to add an additional row to the table.

19 . The system of claim 11 , wherein the structured prompt further comprises:

an input-prefix text input field for capturing text describing the first corresponding text input field; and

an output-prefix text input field for capturing text describing the second corresponding text input field.

20 . The system of claim 11 , wherein, after providing the test output text, the operations further comprise:

receiving, from the user device, one or more additional or refined training samples;

in response to receiving the one or more additional or refined training samples, further adjusting the ML model using the one or more additional or refined training samples;

receiving, from the user device, second test input text representative of captured text from one of the one or more user input fields;

generating, using the ML model, second test output text based on the second test input text; and

providing, to the user device, the second test output text configured to cause the user device to display, within the GUI, the second test output text.