ChatGPTRecommender Class Reference

A class that interacts with OpenAI's ChatGPT API for recommendation tasks, inheriting from MLFunction. More...

#include <ChatGPT.h>

Inheritance diagram for ChatGPTRecommender:

Public Member Functions
	ChatGPTRecommender ()
	Default constructor.
	ChatGPTRecommender (std::string url, std::string model)
	Constructor with custom URL and model.
	~ChatGPTRecommender ()
	Destructor.
void	apply (const SelectivityVector &rows, std::vector< VectorPtr > &args, const TypePtr &type, exec::EvalCtx &context, VectorPtr &output) const override
	Applies the ChatGPTRecommender function to the input array.
float *	getTensor () const override
	Returns the tensor associated with this function.
CostEstimate	getCost (std::vector< int > inputDims)
	Estimates the computational cost of applying the ChatGPTRecommender function.
Public Member Functions inherited from MLFunction
virtual	~MLFunction ()=default
	Virtual destructor.
virtual std::vector< int >	getDims ()
	Returns the dimensions of the function.
virtual std::string	getFuncName ()
	Returns the name of the function.
virtual int	getNumDims ()
	Returns the number of dimensions of the function.

Static Public Member Functions
static std::vector< std::shared_ptr< exec::FunctionSignature > >	signatures ()
	Returns the function signatures supported by this class.
static std::string	getName ()
	Returns the name of the function.

Additional Inherited Members
Protected Member Functions inherited from MLFunction
double	getWeightedCost (std::string name, float cost)
	Calculates the weighted cost of the function.
std::vector< double >	getCoefficientVector (std::string name)
	Retrieves the cost coefficients for the function.
Protected Attributes inherited from MLFunction
std::vector< int >	dims
	Dimensions of the function.

Detailed Description

A class that interacts with OpenAI's ChatGPT API for recommendation tasks, inheriting from MLFunction.

This class provides functionality to send user statistics and movie metadata to the ChatGPT API and retrieve personalized recommendations. It supports multi-threaded requests for improved performance.

Constructor & Destructor Documentation

ChatGPTRecommender() [1/2]

ChatGPTRecommender::ChatGPTRecommender ( )

inline

Default constructor.

Initializes the ChatGPT API with the default URL and model ("gpt-3.5-turbo"). Requires the OPENAI_API_KEY environment variable to be set.

ChatGPTRecommender() [2/2]

ChatGPTRecommender::ChatGPTRecommender ( std::string url, std::string model )

inline

Constructor with custom URL and model.

Initializes the ChatGPT API with a custom URL and model. Requires the OPENAI_API_KEY environment variable to be set.

Parameters

url	The URL of the OpenAI API endpoint.
model	The model to use for text generation (e.g., "gpt-3.5-turbo").

~ChatGPTRecommender()

ChatGPTRecommender::~ChatGPTRecommender ( )

inline

Destructor.

Logs the total number of input tokens, output tokens, and API failures to a file.

Member Function Documentation

apply()

void ChatGPTRecommender::apply ( const SelectivityVector & rows, std::vector< VectorPtr > & args, const TypePtr & type, exec::EvalCtx & context, VectorPtr & output ) const

inlineoverride

Applies the ChatGPTRecommender function to the input array.

This method processes the input array, sends user statistics and movie metadata to the ChatGPT API, and stores the personalized recommendations in the output vector.

Parameters

rows	A SelectivityVector specifying the rows to process.
args	A vector of input arguments (e.g., user statistics and movie metadata).
type	The type of the output vector.
context	The execution context.
output	The output vector where the recommendations will be stored.

getCost()

CostEstimate ChatGPTRecommender::getCost ( std::vector< int > inputDims )

inlinevirtual

Estimates the computational cost of applying the ChatGPTRecommender function.

Parameters

inputDims

A vector containing the dimensions of the input.

Returns

A CostEstimate object representing the estimated cost.

Reimplemented from MLFunction.

getName()

static std::string ChatGPTRecommender::getName ( )

inlinestatic

Returns the name of the function.

Returns

The name of the function as a string ("chatgpt_recommender").

getTensor()

float * ChatGPTRecommender::getTensor ( ) const

inlineoverridevirtual

Returns the tensor associated with this function.

Returns

A null pointer (no tensor is associated with this function).

Implements MLFunction.

signatures()

static std::vector< std::shared_ptr< exec::FunctionSignature > > ChatGPTRecommender::signatures ( )

inlinestatic

Returns the function signatures supported by this class.

Returns

A vector of shared pointers to FunctionSignature objects.

---

The documentation for this class was generated from the following file:

• ChatGPT.h