Skip to content

Commit

Permalink
Update custom-ai-function.rst
Browse files Browse the repository at this point in the history
fixed indent issues
  • Loading branch information
IshSiva authored Oct 13, 2023
1 parent 6d3d44e commit ff35e87
Showing 1 changed file with 10 additions and 6 deletions.
16 changes: 10 additions & 6 deletions docs/source/reference/ai/custom-ai-function.rst
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,8 @@ The custom setup operations for the function can be written inside the function

**Forward**

The abstract method `forward` must be implemented in your function. The forward function receives the frames and runs the deep learning model on the data. The logic for transforming the frames and running the models must be provided by you.
The abstract method `forward` must be implemented in your function. The forward function receives the frames and runs the deep learning model on the data. The logic for transforming the frames and running the models must be provided by you. Using the forward decorator is optional.

The arguments that need to be passed are

- input_signatures: List[IOArgument]
Expand All @@ -74,13 +75,16 @@ Now that you have implemented your function, we need to register it as a functio

1. Register the function with a query that follows this template:

`CREATE FUNCTION [ IF NOT EXISTS ] <name>
IMPL <path_to_implementation>;`
.. code-block:: sql
CREATE FUNCTION [ IF NOT EXISTS ] <name>
IMPL <path_to_implementation>;
where,
where,

* <name> - specifies the unique identifier for the function.
* <path_to_implementation> - specifies the path to the implementation class for the function
* <name> - specifies the unique identifier for the function.
* <path_to_implementation> - specifies the path to the implementation class for the function


2. Execute your function on any data:
Expand Down

0 comments on commit ff35e87

Please sign in to comment.