sgcWebSockets · Technical Document

OpenAI Component

High-level OpenAI HTTP API client — chat completions, responses, embeddings, images, audio, files, fine-tuning, batches and assistants.

Overview

OpenAI REST API client covering Chat Completions, Images, Audio (TTS/STT), Embeddings, Files, Fine-tuning, Moderation, Assistants, Threads, Runs, Messages and Vector Stores.

At a glance

Component class

TsgcHTTP_API_OpenAI

Standards / spec

OpenAI API reference

Transports

TCP, TLS

Platforms

Windows, macOS, Linux, iOS, Android

Frameworks

VCL, FireMonkey, Lazarus / FPC, .NET

Edition

Standard / Professional / Enterprise

Features

Native Delphi implementation with full ANSI/Unicode support.

Technical specification

Standards & specs	OpenAI API reference · OpenAI Chat Completions
Component class	`TsgcHTTP_API_OpenAI` (unit `sgcHTTP_API_OpenAI`)
Frameworks	VCL, FireMonkey, Lazarus / FPC, .NET
Platforms	Windows, macOS, Linux, iOS, Android

Main properties

The principal published / public properties used to configure and drive the component. Consult the online help for the full list.

`TLSOptions`	TLS/SSL configuration used for HTTPS connections to the OpenAI API
`OpenAIOptions`	Container for all OpenAI REST client settings including credentials, organization, HTTP, logging and retry options
`ReadTimeout`	HTTP read timeout in milliseconds applied to every OpenAI REST request
`CircuitBreaker`	Retry and rate-limit handling policy used when OpenAI endpoints fail transiently
`Version`	Read-only sgcWebSockets library version string

Main methods

The principal public methods exposed by the component.

`ListInputItems()`	Lists the input items that were provided when a response was created
`CreateThread()`	Creates a new Thread optionally seeded with initial messages and tool resources
`ModifyThread()`	Updates the tool resources and metadata of an existing Thread
`SubmitToolOutputsToRun()`	Returns tool function outputs to a Run that is waiting in requires_action state
`DeleteResponse()`	Deletes a stored response from the OpenAI Responses API
`DeleteFile()`	Permanently deletes a file previously uploaded to OpenAI
`DeleteFineTuneModel()`	Deletes a fine-tuned model so it is no longer available for inference
`DeleteAssistant()`	Permanently deletes an Assistant by its identifier
`RetrieveThread()`	Retrieves a Thread definition by its identifier
`DeleteThread()`	Permanently deletes a Thread and all of its messages

Public events

The component exposes the following published events; consult the online help for full event-handler signatures.

`OnHTTPAPIException`	Fires when an uncaught exception is raised during an OpenAI REST call
`OnHTTPAPISSE`	Fires for each Server-Sent Events chunk received during a streaming OpenAI call

Quick Start

Drop the component on a form, configure the properties below and activate it. The snippet that follows shows the typical OpenAI Chat — Simple Example configuration sourced from the online help.

About this scenario. Interact with ChatGPT by sending a Hello message.

Delphi (VCL / FireMonkey)

OpenAI := TsgcHTTP_API_OpenAI.Create(nil);
OpenAI.OpenAIOptions.ApiKey := 'API_KEY';
WriteLn(OpenAI._CreateChatCompletion('gpt-3.5-turbo', 'Hello!'));

C++ Builder

TsgcHTTP_API_OpenAI *OpenAI = new TsgcHTTP_API_OpenAI(NULL);
OpenAI->OpenAIOptions->ApiKey = "API_KEY";
ShowMessage(OpenAI->_CreateChatCompletion("gpt-3.5-turbo", "Hello!"));

.NET (C#)

TsgcHTTP_API_OpenAI OpenAI = new TsgcHTTP_API_OpenAI();
OpenAI.OpenAIOptions.ApiKey = "API_KEY";
MessageBox.Show(OpenAI._CreateChatCompletion("gpt-3.5-turbo", "Hello!"));

Common scenarios

The following scenarios are lifted verbatim from the online help. Each shows the configuration and method calls needed to drive the component through a specific real-world flow.

1 · OpenAI Batch — Simple Example

Create a batch job and retrieve its status.

Delphi (VCL / FireMonkey)

OpenAI := TsgcHTTP_API_OpenAI.Create(nil);
OpenAI.OpenAIOptions.ApiKey := 'API_KEY';

// Create a batch
WriteLn(OpenAI._CreateBatch('file-abc123', '/v1/chat/completions'));

// List batches
WriteLn(OpenAI._ListBatches());

C++ Builder

TsgcHTTP_API_OpenAI *OpenAI = new TsgcHTTP_API_OpenAI(NULL);
OpenAI->OpenAIOptions->ApiKey = "API_KEY";

// Create a batch
ShowMessage(OpenAI->_CreateBatch("file-abc123", "/v1/chat/completions"));

// List batches
ShowMessage(OpenAI->_ListBatches());

.NET (C#)

TsgcHTTP_API_OpenAI OpenAI = new TsgcHTTP_API_OpenAI();
OpenAI.OpenAIOptions.ApiKey = "API_KEY";

// Create a batch
MessageBox.Show(OpenAI._CreateBatch("file-abc123", "/v1/chat/completions"));

// List batches
MessageBox.Show(OpenAI._ListBatches());

2 · OpenAI Completion — Simple Example

Use the text-davinci-003 model to get a predicted completion.

Delphi (VCL / FireMonkey)

OpenAI := TsgcHTTP_API_OpenAI.Create(nil);
OpenAI.OpenAIOptions.ApiKey := 'API_KEY';
WriteLn(OpenAI._CreateCompletion('text-davinci-003', 'Say this is a test'));

C++ Builder

TsgcHTTP_API_OpenAI *OpenAI = new TsgcHTTP_API_OpenAI(NULL);
OpenAI->OpenAIOptions->ApiKey = "API_KEY";
ShowMessage(OpenAI->_CreateCompletion("text-davinci-003", "Say this is a test"));

.NET (C#)

TsgcHTTP_API_OpenAI OpenAI = new TsgcHTTP_API_OpenAI();
OpenAI.OpenAIOptions.ApiKey = "API_KEY";
MessageBox.Show(OpenAI._CreateCompletion("text-davinci-003", "Say this is a test"));

3 · OpenAI Edit — Simple Example

Tell OpenAI to fix the spelling mistakes of a prompt.

Delphi (VCL / FireMonkey)

OpenAI := TsgcHTTP_API_OpenAI.Create(nil);
OpenAI.OpenAIOptions.ApiKey := 'API_KEY';
WriteLn(OpenAI._CreateEdit('text-davinci-edit-001', 'Fix the spelling mistakes', 'What day of the wek is it?'));

C++ Builder

TsgcHTTP_API_OpenAI *OpenAI = new TsgcHTTP_API_OpenAI(NULL);
OpenAI->OpenAIOptions->ApiKey = "API_KEY";
ShowMessage(OpenAI->_CreateEdit("text-davinci-edit-001", "Fix the spelling mistakes", "What day of the wek is it?"));

.NET (C#)

TsgcHTTP_API_OpenAI OpenAI = new TsgcHTTP_API_OpenAI();
OpenAI.OpenAIOptions.ApiKey = "API_KEY";
MessageBox.Show(OpenAI._CreateEdit("text-davinci-edit-001", "Fix the spelling mistakes", "What day of the wek is it?"));

4 · OpenAI Fine-Tuning — Simple Example

Create a fine-tuning job and list existing jobs.

Delphi (VCL / FireMonkey)

OpenAI := TsgcHTTP_API_OpenAI.Create(nil);
OpenAI.OpenAIOptions.ApiKey := 'API_KEY';

// Create a fine-tuning job
WriteLn(OpenAI._CreateFineTuningJob('gpt-4o-mini-2024-07-18', 'file-abc123'));

// List fine-tuning jobs
WriteLn(OpenAI._ListFineTuningJobs());

C++ Builder

TsgcHTTP_API_OpenAI *OpenAI = new TsgcHTTP_API_OpenAI(NULL);
OpenAI->OpenAIOptions->ApiKey = "API_KEY";

// Create a fine-tuning job
ShowMessage(OpenAI->_CreateFineTuningJob("gpt-4o-mini-2024-07-18", "file-abc123"));

// List fine-tuning jobs
ShowMessage(OpenAI->_ListFineTuningJobs());

.NET (C#)

TsgcHTTP_API_OpenAI OpenAI = new TsgcHTTP_API_OpenAI();
OpenAI.OpenAIOptions.ApiKey = "API_KEY";

// Create a fine-tuning job
MessageBox.Show(OpenAI._CreateFineTuningJob("gpt-4o-mini-2024-07-18", "file-abc123"));

// List fine-tuning jobs
MessageBox.Show(OpenAI._ListFineTuningJobs());

5 · OpenAI Moderation — Simple Example

Moderate the following text

Delphi (VCL / FireMonkey)

OpenAI := TsgcHTTP_API_OpenAI.Create(nil);
OpenAI.OpenAIOptions.ApiKey := 'API_KEY';

WriteLn(OpenAI._CreateModeration('I want to kill them.'));

C++ Builder

TsgcHTTP_API_OpenAI *OpenAI = new TsgcHTTP_API_OpenAI(NULL);
OpenAI->OpenAIOptions->ApiKey = "API_KEY";

ShowMessage(OpenAI->_CreateModeration("I want to kill them."));

.NET (C#)

TsgcHTTP_API_OpenAI OpenAI = new TsgcHTTP_API_OpenAI();
OpenAI.OpenAIOptions.ApiKey = "API_KEY";

MessageBox.Show(OpenAI._CreateModeration("I want to kill them."));

6 · OpenAI Responses — Simple Example

Create a response using the Responses API.

Delphi (VCL / FireMonkey)

OpenAI := TsgcHTTP_API_OpenAI.Create(nil);
OpenAI.OpenAIOptions.ApiKey := 'API_KEY';
WriteLn(OpenAI._CreateResponse('gpt-4o', 'What is the capital of France?'));

C++ Builder

TsgcHTTP_API_OpenAI *OpenAI = new TsgcHTTP_API_OpenAI(NULL);
OpenAI->OpenAIOptions->ApiKey = "API_KEY";
ShowMessage(OpenAI->_CreateResponse("gpt-4o", "What is the capital of France?"));

.NET (C#)

TsgcHTTP_API_OpenAI OpenAI = new TsgcHTTP_API_OpenAI();
OpenAI.OpenAIOptions.ApiKey = "API_KEY";
MessageBox.Show(OpenAI._CreateResponse("gpt-4o", "What is the capital of France?"));

Sources used to build this document

Every external claim links back to a primary source. The online-help references decode the canonical deep-link the company maintains for this component.

Primary standard / spec — OpenAI API reference platform.openai.com/docs/api-reference
Primary standard / spec — OpenAI Chat Completions platform.openai.com/docs/api-reference/chat
Online help — component page www.esegece.com/help/sgcWebSockets/Components/AI/OpenAI/TsgcHTTP_API_OpenAI.htm
Delphi demo project (in the sgcWebSockets package) Demos\15.AI\01.QuickStart\01.OpenAI
.NET demo project (in the sgcWebSockets package) .net\demos\15.AI\01.QuickStart\01.OpenAI
Component page www.esegece.com/products/websockets/ai/openai/
Product page www.esegece.com/products/websockets/

Document scope. This document covers the publicly-documented surface of the OpenAI Component component shipped with sgcWebSockets. For full property, method and event reference consult the online help linked above.