RAD Studio - Recent changes [en]

Go to Related (C++)

L10nBot — Wed, 12 Aug 2026 14:03:52 GMT

Interlanguage links

← Older revision		Revision as of 14:03, 12 August 2026
(One intermediate revision by the same user not shown)
Line 77:		Line 77:

	[[de:Definition suchen (C++)]]		[[de:Definition suchen (C++)]]
	[[fr:~~Chercher la définition~~ (C++)]]		[[fr:Aller aux éléments associés (C++)]]
	[[ja:~~［定義の検索］（C~~++）]]		[[ja:［関連項目に移動］（C++）]]

Find Symbol (C++)

L10nBot — Wed, 12 Aug 2026 13:59:07 GMT

Interlanguage links

← Older revision		Revision as of 13:59, 12 August 2026
Line 26:		Line 26:

	[[de:Navigieren zu (C++)]]		[[de:Navigieren zu (C++)]]
	[[fr:~~Naviguer vers~~ (C++)]]		[[fr:Rechercher le symbole (C++)]]
	[[ja:［シンボルを検索］（C++）]]		[[ja:［シンボルを検索］（C++）]]

Category:Formatting Templates

L10nBot — Wed, 12 Aug 2026 13:53:03 GMT

Interlanguage links

← Older revision		Revision as of 13:53, 12 August 2026
Line 4:		Line 4:
	[[de:Category:Formatierungsvorlagen]]		[[de:Category:Formatierungsvorlagen]]
	[[fr:Category:Modèles de formatage]]		[[fr:Category:Modèles de formatage]]
			[[ja:Category:書式設定テンプレート]]

Create and implement your AI plugin

L10nBot — Wed, 12 Aug 2026 13:51:58 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 88:		Line 88:
	* [[Smart CodeInsight Options]]		* [[Smart CodeInsight Options]]

	~~[[de:KI-Plugin erstellen und implementieren]]~~
	[[ja:AI プラグインの作成と実装]]		[[ja:AI プラグインの作成と実装]]

Go to Definition and Go to Implementation (Delphi)

L10nBot — Wed, 12 Aug 2026 13:51:54 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 31:		Line 31:

	[[de:"Zu Definition wechseln" und "Zu Implementierung wechseln" (Delphi)]]		[[de:"Zu Definition wechseln" und "Zu Implementierung wechseln" (Delphi)]]
	~~[[fr:Aller à la définition et Aller à l'implémentation (Delphi)]]~~
	[[ja:［定義へ移動］と［実装へ移動］（Delphi）]]		[[ja:［定義へ移動］と［実装へ移動］（Delphi）]]

Go to Definition and Go to Implementation (C++)

L10nBot — Wed, 12 Aug 2026 13:51:53 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 34:		Line 34:

	[[de:"Zu Definition wechseln" und "Zu Implementierung wechseln" (C++)]]		[[de:"Zu Definition wechseln" und "Zu Implementierung wechseln" (C++)]]
	~~[[fr:Aller à la définition et Aller à l'implémentation (C++)]]~~
	[[ja:［定義へ移動］と［実装へ移動］]]		[[ja:［定義へ移動］と［実装へ移動］]]

Tanh

L10nBot — Wed, 12 Aug 2026 13:51:49 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 80:		Line 80:
	[[de:Tanh, tanhl]]		[[de:Tanh, tanhl]]
	[[fr:Tanh, tanhl]]		[[fr:Tanh, tanhl]]
			[[ja:Tanh，tanhl]]

Tan

L10nBot — Wed, 12 Aug 2026 13:51:49 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 80:		Line 80:
	[[de:Tan, tanl]]		[[de:Tan, tanl]]
	[[fr:Tan, tanl]]		[[fr:Tan, tanl]]
			[[ja:Tan，tanl]]

Sqrt

L10nBot — Wed, 12 Aug 2026 13:51:48 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 90:		Line 90:
	[[de:Sqrt, sqrtl]]		[[de:Sqrt, sqrtl]]
	[[fr:Sqrt, sqrtl]]		[[fr:Sqrt, sqrtl]]
			[[ja:Sqrt，sqrtl]]

Sinh

L10nBot — Wed, 12 Aug 2026 13:51:47 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 81:		Line 81:
	[[de:Sinh, sinhl]]		[[de:Sinh, sinhl]]
	[[fr:Sinh, sinhl]]		[[fr:Sinh, sinhl]]
			[[ja:Sinh，sinhl]]

Sin

L10nBot — Wed, 12 Aug 2026 13:51:47 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 79:		Line 79:
	[[de:Sin, sinl]]		[[de:Sin, sinl]]
	[[fr:Sin, sinl]]		[[fr:Sin, sinl]]
			[[ja:Sin，sinl]]

Debugger Tips and Workarounds

L10nBot — Wed, 12 Aug 2026 13:51:40 GMT

Interlanguage links

← Older revision		Revision as of 13:51, 12 August 2026
Line 34:		Line 34:
	* [[Environment Variables]]		* [[Environment Variables]]

	~~[[de:Debugger-Tipps und -Workarounds]]~~
	[[ja:デバッガのヒントと回避策]]		[[ja:デバッガのヒントと回避策]]

Creating International Applications Index

L10nBot — Wed, 12 Aug 2026 13:50:16 GMT

Interlanguage links

← Older revision		Revision as of 13:50, 12 August 2026
Line 32:		Line 32:
	[[Category:{{Delphi}}]]		[[Category:{{Delphi}}]]
	[[Category:C++]]		[[Category:C++]]

			[[de:Anwendungen für den internationalen Markt - Index]]
			[[fr:Création d'applications internationales - Index]]
			[[ja:国際化対応アプリケーションの作成：インデックス]]

Pi

L10nBot — Wed, 12 Aug 2026 13:49:08 GMT

Interlanguage links

← Older revision		Revision as of 13:49, 12 August 2026
Line 13:		Line 13:
	[[de:Pi]]		[[de:Pi]]
	[[fr:Pi]]		[[fr:Pi]]
			[[ja:パイ]]

Main Page

L10nBot — Wed, 12 Aug 2026 13:49:04 GMT

Interlanguage links

← Older revision		Revision as of 13:49, 12 August 2026
Line 73:		Line 73:
	[[de:Hauptseite]]		[[de:Hauptseite]]
	[[fr:Accueil]]		[[fr:Accueil]]
	[[ja:~~Main Page~~]]		[[ja:メインページ]]

Evaluate/Modify

L10nBot — Wed, 12 Aug 2026 13:48:27 GMT

Interlanguage links

← Older revision		Revision as of 13:48, 12 August 2026
Line 141:		Line 141:
	[[Category:C++]]		[[Category:C++]]
	[[Category:AMMigrate]]		[[Category:AMMigrate]]

			[[de:Auswerten/Ändern]]
			[[fr:Evaluer/Modifier]]
			[[ja:［評価/変更］]]

Transactions

L10nBot — Wed, 12 Aug 2026 13:48:15 GMT

Interlanguage links

← Older revision		Revision as of 13:48, 12 August 2026
Line 35:		Line 35:
	[[de:Transaktionen]]		[[de:Transaktionen]]
	[[fr:Transactions]]		[[fr:Transactions]]
			[[ja:トランザクション]]

File Menu

L10nBot — Wed, 12 Aug 2026 13:46:18 GMT

Interlanguage links

← Older revision		Revision as of 13:46, 12 August 2026
Line 112:		Line 112:
	[[de:Menü Datei]]		[[de:Menü Datei]]
	[[fr:Menu Fichier]]		[[fr:Menu Fichier]]
			[[ja:［ファイル］メニュー]]

Find Symbol (C++)

L10nBot — Wed, 12 Aug 2026 13:45:16 GMT

Interlanguage links

← Older revision		Revision as of 13:45, 12 August 2026
Line 26:		Line 26:

	[[de:Navigieren zu (C++)]]		[[de:Navigieren zu (C++)]]
	[[fr:~~Rechercher le symbole~~ (C++)]]		[[fr:Naviguer vers (C++)]]
	[[ja:［シンボルを検索］（C++）]]		[[ja:［シンボルを検索］（C++）]]

Go to Related (C++)

L10nBot — Wed, 12 Aug 2026 13:44:15 GMT

Interlanguage links

← Older revision		Revision as of 13:44, 12 August 2026
Line 77:		Line 77:

	[[de:Definition suchen (C++)]]		[[de:Definition suchen (C++)]]
	[[fr:~~Aller aux éléments associés~~ (C++)]]		[[fr:Chercher la définition (C++)]]
	[[ja:~~［関連項目に移動］（C~~++）]]		[[ja:［定義の検索］（C++）]]

TestPage3

Yukikoi — Wed, 12 Aug 2026 12:31:19 GMT

← Older revision		Revision as of 12:31, 12 August 2026
Line 1:		Line 1:
	== This is TestPage 3 ~~FLORENCE TEST ==~~		This is TestPage 3.
	The new section is below.		The new section is below.

Line 22:		Line 22:
	* another link		* another link

	[[fr:~~LeTestPage~~]]		[[ja:TestPage3]]

TestPage3

Yukikoi — Wed, 12 Aug 2026 12:09:15 GMT

Created page with "== This is TestPage 3 FLORENCE TEST == The new section is below. ==Section one== Testing if localization works This has changed. More text has been added. ==Subtitle1== Extra text up here This text is going to be translated. ==Subtitle 2== Added content ==See:== * example[dot]com * another link fr:LeTestPage"

New page

== This is TestPage 3 FLORENCE TEST ==
The new section is below.

==Section one==

Testing if localization works

This has changed.

More text has been added.

==Subtitle1==
Extra text up here
This text is going to be translated.

==Subtitle 2==
Added content

==See:==
* example[dot]com
* another link

[[fr:LeTestPage]]

User:Fabiola.Arias

Eric.revollo — Mon, 10 Aug 2026 12:58:05 GMT

Eric.revollo changed group membership for Fabiola.Arias from automoderated and moderator to automoderated, moderator, bureaucrat, writer and Employee

User:Fabiola.Arias

Eric.revollo — Mon, 10 Aug 2026 12:57:52 GMT

Eric.revollo changed group membership for Fabiola.Arias from Employee, automoderated, bureaucrat, moderator and writer to automoderated and moderator

Main Page

L10nBot — Mon, 10 Aug 2026 02:06:45 GMT

Interlanguage links

← Older revision		Revision as of 02:06, 10 August 2026
Line 73:		Line 73:
	[[de:Hauptseite]]		[[de:Hauptseite]]
	[[fr:Accueil]]		[[fr:Accueil]]
	[[ja:~~メインページ~~]]		[[ja:Main Page]]

BCC64X

Nicolas.rios — Wed, 05 Aug 2026 12:56:04 GMT

CPU Saturation

← Older revision		Revision as of 12:56, 5 August 2026
Line 277:		Line 277:
	You can also set it to any positive integer. Depending on how many are available, it will use up to this number of cores. If you set it to use more cores than you have, it will simply use as many cores as it can.		You can also set it to any positive integer. Depending on how many are available, it will use up to this number of cores. If you set it to use more cores than you have, it will simply use as many cores as it can.

	You can set the same value by invoking the compiler directly when using the {{code\|'--jobs=n'}} command line parameter.		You can set the same value by invoking the compiler directly when using the {{code\|'--jobs<nowiki>=</nowiki>n'}} command line parameter.

	Our recommended value is {{code\|0}} (the default). This saturates the CPU and builds as fast as possible.		Our recommended value is {{code\|0}} (the default). This saturates the CPU and builds as fast as possible.

Main Page

Nicolas.rios — Fri, 31 Jul 2026 16:00:29 GMT

← Older revision		Revision as of 16:00, 31 July 2026
Line 55:		Line 55:
	* [[Kai Features]]		* [[Kai Features]]
	* [[Kai Options]]		* [[Kai Options]]
			* [[Using Local AI Models with Kai]]
	* [[Kai Licensing]]		* [[Kai Licensing]]
	== Reference ==		== Reference ==

TLIB64.EXE, the Library Manager for 64-bit Windows

Nicolas.rios — Thu, 30 Jul 2026 13:55:24 GMT

RS-132863

← Older revision		Revision as of 13:55, 30 July 2026
Line 19:		Line 19:
	== Command Line Help ==		== Command Line Help ==
	Here is the command line help for TLIB64.EXE:		Here is the command line help for TLIB64.EXE:
	<~~code~~>		<source>
	~~C:\ > tlib64~~		TLIB64 7.3 Copyright (c) 1987-2026 Embarcadero Technologies, Inc.
	TLIB64 6.3 Copyright (c) 1987-~~2012 {{Company}}~~ Technologies, Inc.		Syntax: TLIB [options] libname [ operands ] [, listfile]
	Syntax: ~~TLIB64~~ libname ~~options commands~~, listfile		options switches beginning with '/' (see below); optional
	libname library file pathname		libname library file pathname (required)
	~~commands~~ ~~sequence of operations~~ to ~~be performed~~ (~~optional~~)		operands modules/files to act on (see below); zero or more
	listfile ~~file name for~~ listing file (~~optional~~)		, listfile optional listing file, introduced by a comma

	A command ~~is of~~ the ~~form~~: <symbol>module, ~~where <symbol> is:~~		New syntax (simpler for scripts and tooling):
	+ add module ~~to the library~~		With /N the old +/- operators are disabled, so '+' and '-' may
			appear in file names. Set a default action, then list plain
			file/module names; the action holds for every following operand
			until you set a different one, so one command can mix actions.
			/N select new syntax
			/a add module to the library
			/d delete module from the library
			/e extract module without removal
			/r replace module in the library
			/u update module: replace it, or add it if not present
			/x extract module and remove it from the library
			Example: TLIB mylib /N /a add1.obj add2.obj /d drop.obj

			Old syntax (command operators; the default): each operand is
			[<symbol>]module; a symbol sets that operand's action, overriding
			any default.
			/O select old syntax (the default)
			+ add module (does NOT replace an existing member; use -+)
	- delete module from the library		- delete module from the library
	* extract module without removing it		* extract module without removing it
	-+ or +- ~~update~~ module in library		-+ or +- replace module in the library
	-* or *- extract module and remove it		-* or *- extract module and remove it

	~~Set the default action for modules without a specified command~~:		General switches:
	/a ~~add module to the~~ library		/8 output encoding is utf-8
	/d ~~delete module from~~ library		/F force new library
	/e ~~extract module without removal~~		/Q quiet: reduce output messages
	/u ~~update module in library~~
	/x ~~extract module and remove it from~~ library		OMF library switches:
			/0 purge comment records
			/1 purge like /0 but keep the compiler-version comment
			/C case-sensitive library
			/E build the extended dictionary
	/L write listfile to stdout		/L write listfile to stdout
	/~~N disable support of command syntax~~		/Pnn set the library page size to nn
	/~~O enable support of command syntax~~
			GNU ar / ELF archive switches:
	/A write GNU AR format archive with ELF objs		/A write GNU AR format archive with ELF objs
	/C ~~case-sensitive library~~		/Z zero AR member timestamps for reproducible builds
	~~/PSIZE set the library page size to SIZE~~
	~~/0 purge comment records~~		Response files (read further arguments from a file or stdin):
	/8 ~~output encoding is utf~~-8		@filepath read further arguments from filepath
			/B response-file lines are newline-terminated, so no
	~~Use @filepath to continue from~~ file ~~"filepath".~~		trailing '&' is needed (recommended)
	~~Use~~ '&' at end ~~of a~~ line ~~to continue onto~~ the ~~next~~ line.		& otherwise, end each continued line with '&'
	</~~code~~>		(the final line takes none)
			</source>

	== See Also ==		== See Also ==

13 Florence - Release 1

Nicolas.rios — Wed, 29 Jul 2026 14:30:46 GMT

← Older revision		Revision as of 14:30, 29 July 2026
(One intermediate revision by the same user not shown)
Line 6:		Line 6:
	* See what is included in version '''[[What%27s New \|13 Florence]]'''}}		* See what is included in version '''[[What%27s New \|13 Florence]]'''}}

			=Key Enhancements by product area in 13.1=
	RAD Studio 13 Florence - Release 1 (also known as 13.1) is available for installation. RAD 13.1 builds on the feature set of RAD Studio 13, enhancing existing features throughout the product and adding new capabilities.		RAD Studio 13 Florence - Release 1 (also known as 13.1) is available for installation. RAD 13.1 builds on the feature set of RAD Studio 13, enhancing existing features throughout the product and adding new capabilities.

	RAD Studio 13.1 focuses on quality improvements and includes significant enhancements to the C++ toolchain and the IDE. Key features and quality focus areas include:		RAD Studio 13.1 focuses on quality improvements and includes significant enhancements to the C++ toolchain and the IDE. Key features and quality focus areas include:
			* IDE and IDE Tools
	~~=Key Enhancements by product area in 13.1=~~		* Native Delphi ARM64EC Toolchain
	~~The following sections show key 13.1 improvements by area.~~		* Delphi LSP
			* Debugger
			* Delphi Compilers
			* C++ Win64 Modern Platform
			* Android API Level 36
			* Libraries: VCL, FireMonkey, Delphi RTL
			* WebBroker and WebStencils
			* RAD Server

	== IDE and IDE Tools ==		== IDE and IDE Tools ==

Kai

Nicolas.rios — Wed, 29 Jul 2026 01:42:57 GMT

KAI-178

← Older revision		Revision as of 01:42, 29 July 2026
Line 9:		Line 9:
	* [[Kai Features]]		* [[Kai Features]]
	* [[Kai Licensing]]		* [[Kai Licensing]]
			* [[Using Local AI Models with Kai]]
	* [[Kai Options]]		* [[Kai Options]]
	** [[Kai Options: Chat]]		** [[Kai Options: Chat]]

Using Local AI Models with Kai

Nicolas.rios — Wed, 29 Jul 2026 01:42:20 GMT

KAI-178

New page

{{Parent|Kai}}

Kai can connect to locally hosted Large Language Models (LLMs), allowing you to use AI-assisted development while keeping prompts and source code within an environment you control.

Using local models can help you with the following:
* Keeping prompts and source code within your local network.
* Avoiding model subscriptions and token-usage.
* Selecting a model that fits your hardware and development needs.
* Running the model on the same computer as {{Product}} or another computer on your network.
* Using separate models for [[Kai Options: Chat|Kai Chat]] and code completions.

The performance and capabilities of a local model depend on the model, the local model runtime, and the available hardware.
Kai version 1.0.2 expands local model support for [[Kai Features#Ghost Text|Ghost Text]], [[Kai Features#CodeInsight Completions|Code Completions]], and [[Kai Features#Suggestions|Code Suggestions]] by adding additional local backends and configurable Fill-In-the-Middle support.

==Topics==
* [[#Local Model Hardware Requirements|Local Model Hardware Requirements]]
* [[#Choosing a Local Model Runtime|Choosing a Local Model Runtime]]
* [[#Choosing a Local Model|Choosing a Local Model]]
* [[#Setting Up LM Studio|Setting Up LM Studio]]
* [[#Connecting Kai Chat to a Local Model|Connecting Kai Chat to a Local Model]]
* [[#Connecting to a Model on Another Computer|Connecting to a Model on Another Computer]]
* [[#Using a Local Model in Kai Chat|Using a Local Model in Kai Chat]]
* [[#Configuring Local Code Completions|Configuring Local Code Completions]]
* [[#Improving Local Model Results|Improving Local Model Results]]
* [[#Troubleshooting|Troubleshooting]]
* [[#Security Considerations|Security Considerations]]

== Local Model Hardware Requirements ==
Kai does not impose a fixed hardware requirement for local models. The required resources depend on the following:
* The model size.
* The selected quantization.
* The configured context-window size.
* The local model runtime.
* Whether the model uses CPU or GPU acceleration.
* Whether {{Product}} and the model runtime run on the same computer.

The following recommendations apply to the computer hosting the local model, not only to the computer running {{Product}}.

==Choosing a Local Model Runtime==
A local model runtime downloads, loads, and runs the model. It also provides the API endpoint that Kai uses to connect.

Common options include LM Studio, Ollama, llama.cpp, and oMLX.

===LM Studio===
[https://lmstudio.ai LM Studio] provides a graphical interface for:
* Finding and downloading models.
* Loading and unloading models.
* Starting a local API server.
* Viewing the server URL.
* Allowing access from other computers on the local network.

LM Studio is a practical choice when you prefer a graphical interface.

===Ollama===
[https://ollama.com Ollama] provides command-line tools and a local API for downloading and running supported models.

Follow these steps to prepare Ollama for Kai:
# Install Ollama.
# Download a supported coding model.
# Start the Ollama service.
# Identify the API URL and port.
# Enter the URL in Kai.
# Test the connection.
# Select the model.

LM Studio and Ollama use different ports. Always use the URL displayed or documented by the runtime.

===llama.cpp===
The [https://llama-cpp.com llama.cpp] model provides greater control over model loading and resource use, but it usually requires more manual configuration.

It is best suited to advanced users who need a customized local model environment.

===oMLX===
[https://omlx.ai oMLX] provides a native macOS interface for:

* Finding and downloading models optimized for Apple Silicon.
* Loading and managing models in MLX format.
* Starting an OpenAI-compatible local API server.
* Viewing the server URL and port.
* Using the Mac’s unified memory and MLX hardware acceleration.
* Allowing RAD Studio in a Windows virtual machine or another computer on the local network to connect to the model.

oMLX is a practical choice when you use an Apple Silicon Mac and want models specifically optimized for Apple’s MLX framework.

==Choosing a Local Model==
Not every model is suitable for software development or for use with Kai.

Consider the following when selecting a model:
* Whether it is designed for coding.
* Whether it supports tool use for Kai Chat.
* Whether it supports Fill-In-the-Middle for code completions.
* Whether it fits within the available memory.
* Whether it is compatible with your selected runtime.
* Whether its response speed is appropriate for your workflow.

A model that works well for Kai Chat might not be suitable for inline code completion.

===Choosing a Model for Kai Chat===
For Kai Chat and agentic development tasks, select a coding model that:
* Supports tool use.
* Has a context window suitable for the project.
* Fits comfortably within the available memory.
* Is compatible with the selected runtime.

Common coding model families available through local runtimes include:
* Qwen Coder.
* Gemma coding-capable models.
* DeepSeek coding models.
* Smaller coding models for systems with limited memory.

Test the model with tasks representative of your own projects, such as:
* Creating a Delphi class.
* Explaining an existing unit.
* Refactoring a method.
* Generating a DUnitX test.
* Correcting a compiler error.

===Choosing a Model for Code Completions===
For Ghost Text, Code Completions, and Code Suggestions, select a coding model that explicitly supports Fill-In-the-Middle, or FIM.

FIM allows the model to generate code at the cursor using both the code before and after the insertion point

Common [[Kai Options: Completions|FIM-capable]] model families include:
* StarCoder.
* Code Llama.
* DeepSeek-Coder.
* Qwen2.5-Coder.
* Codestral.
* Replit Code models.

Verify FIM support for the exact model version you download.

===Using LLM Fit===
[https://github.com/AlexsJones/llmfit LLM Fit] evaluates your computer and identifies models that are likely to run within the available resources.

Follow these steps to use LLM Fit:
# Install LLM Fit from its project repository.
# Open a terminal or command prompt.
# Run:
# Review the detected hardware and available memory.
# Filter the results by the coding use case.
# Review the estimated model memory use and speed.
# Select a model that fits comfortably within the available resources.
# Download the corresponding model through LM Studio, Ollama, or another supported source.

Avoid models identified as marginal or borderline unless you are prepared for reduced performance or memory errors.

==Setting Up LM Studio==
Follow these steps to prepare LM Studio for use with Kai.
# Download LM Studio from [https://lmstudio.ai/ https://lmstudio.ai/]
# Install and open LM Studio.
# Search for a coding model.
# Select a model size and format appropriate for your hardware.
# Download the model.
# Load the downloaded model.
# Open the local server area.
# Start the local API server.
# Record the server URL displayed by LM Studio.

A typical local URL is:
<nowiki>http://localhost:1234/v1/</nowiki>

The exact URL may vary.

===Enable Network Access===
Enable network access when {{Product}} and the model runtime are running on different computers or when RAD Studio is running in a virtual machine.
To enable access:
# Open the LM Studio server settings.
# Enable access from the local network.
# Record the host computer’s IP address or network name.
# Confirm that the operating-system firewall allows access to the server port.

{{Note|Use this option only on a trusted network.}}

==Connecting Kai Chat to a Local Model==
Follow these steps to connect Kai Chat to LM Studio, Ollama, or another compatible local server:
# Start the local model runtime and load or activate the coding model.
# Start the runtime’s API server.
# Open {{Product}} and select {{Menu| Tools > Options}}.
# In the Options window, select {{Menu| Kai > Chat}} to open the Chat settings.
# Select the '''Local Model''' tab.
# Enter the server URL.
# Test the connection with the'''Test Connection''' button to confirm that the connection succeeds.
# Select the model.
# Save the settings.

When the connection succeeds, Kai displays the models exposed by the local runtime.

{{Note|A model configured for Kai Chat is not automatically used for code completions.}}

==Connecting to a Model on Another Computer==
It is possible to run the model on another computer on the same trusted network. You can also run a model on a cloud-hosted machine; in that case, {{Product}} recommends using an API key for additional security.

This configuration is useful in the following situations:
When the {{Product}} computer has limited system or GPU memory.
Another computer has a more capable GPU.
{{Product}} runs in a virtual machine.
To prevent the model runtime from competing with {{Product}} for resources.

To connect to another computer, follow these steps:
# Start the model runtime on the host computer and load the required model.
# Start the API server.
# Enable network access in the runtime.
# Determine the host computer’s IP address or network name.
# Confirm that the firewall permits access to the API port.
# Open {{Product}} and navigate to the appropriate Kai settings.
# Enter the network URL and test the connection.
# Select the model and save the settings.

{{Note|Do not use {{code|localhost}} when the model runs on another computer. {{code|localhost}} refers to the computer running {{Product}}.}}

When {{Product}} runs in a virtual machine, use a host address that is reachable from the virtual machine. It is strongly recommended to enable an API key if your chosen inference engine supports it. For example, LM Studio has an entry for this. Then, in Kai, enter the API key. This helps prevent unauthorized use of your LLM.

==Using a Local Model in Kai Chat==
Once the model configurations are completed, follow these steps to use the local model in the Kai Chat:
# Open a project in RAD Studio.
# Open the Kai Chat window.
# Create a new local session.
# Select one of the available models from the model combobox (in the bottom panel).
# Enter a clear development request.
# Approve or reject requested operations, if requested.
# Review the files created or modified by Kai.
# Compile and test the changes.

Additionally, local models can also help you:
* Explain existing code.
* Create classes and units.
* Refactor methods.
* Generate tests.
* Diagnose compiler errors.
* Add validation and error handling.
* Generate documentation.

{{Note|Ensure to always review and test generated code before using it in a production project.}}

===Manage Permissions===
Kai may request permissions before any of the following actions:
* Reading project files.
* Searching the project.
* Creating or modifying files.
* Accessing a directory.
* Using an MCP tool.

Use restricted permissions when evaluating a new model. Keep the project under source control and review all generated changes.

==Configuring Local Code Completions==
In version 1.0.2, Kai expands local support for [[Kai Features#Ghost Text|Ghost Text]], [[Kai Features#CodeInsight Completions|Code Completions]], and [[Kai Features#Suggestions|Code Suggestions]].

For local completions, Kai allows users to perform the following configurations:
* The local server URL.
* The backend engine.
* The model.
* The FIM token format.

===Before Configuring Completions===
Before configuring a local completion model, ensure to complete this set of steps:
* Install Kai version 1.0.2 or later.
* Install a compatible local model runtime.
* Download a FIM-capable coding model.
* Load the model.
* Start the local API server.
* Record the server URL.

===Configure the Completion Model===
Follow these simple steps to configure a local completion model.
* Open {{Product}} and navihgate to {{Menu|Tools > Options > Kai}}.
* In the Kai window, select the '''Completions''' settings.
* Select the '''Local Models''' tab.
* Enter the local server URL.
* Select the backend engine.
* Select the model.
* Select the FIM configuration that matches the model.
* Save the settings.
* Open a Delphi or C++ source file.
* Begin coding and verify that a completion appears.

Different backends can expose and process models differently. Select the backend that corresponds to the runtime used to serve the model.

===Configure FIM Tokens===
Kai provides predefined FIM configurations for supported model families.

Use a predefined option when it matches the selected model.

When no matching preset is available:
* Review the documentation for the exact model version.
* Identify the model’s prefix, suffix, and middle tokens.
* Open {{Menu|Tools > Options > Kai > Completions}}.
* Select '''Local Models'''.
* Select the server, backend, and model.
* Select the manual FIM option.
* Enter the required tokens.
* Save and test the configuration.

Incorrect FIM tokens can cause the model to repeat existing code, continue from the wrong location, or return unusable suggestions.

===Test Code Completions===
Follow these steps to test the configuration:
# Open a Delphi or C++ source file.
# Place the cursor inside a method or function.
# Begin typing a statement or code block.
# Pause briefly for a suggestion.
# Review the Ghost Text or completion.
# Accept or dismiss the suggestion.
# Repeat the test in several code contexts.

For inline completion, response speed is especially important. A smaller FIM-capable model may provide a better editing experience than a larger chat-oriented model.

===Use Different Models for Chat and Completions===
You can configure a larger, tool-capable model for Kai Chat, or a smaller, faster FIM-capable model for code completions.

When system memory is limited, avoid loading two large models simultaneously.

==Improving Local Model Results==
This section explains how to improve local model results.

'''Provide Specific Instructions'''

Ensure to provide specific instructions that include the following information:
* The language and framework.
* The required file or unit name.
* The classes and methods to create.
* Validation and error-handling requirements.
* Files that must not be modified.
* Required tests.
* The targeted {{Product}} version.

'''Break large tasks into Stages'''

Try breaking large tasks into smaller stages for a complex change:
# Ask Kai to inspect and summarize the existing code.
# Request a proposed plan.
# Review the plan.
# Apply one stage at a time.
# Compile and test after each stage.

'''Start a New Session when necessary'''

Start a new session when:
* The conversation becomes very long.
* The model stops following earlier instructions.
* You move to an unrelated task.
* You want to provide a clean set of requirements.

==Troubleshooting==
This section explains the most common issues and how to troubleshoot them.

===Test Connection Fails===
If the test connection fails, verify the following to troubleshoot the issue.
* The model runtime is running.
* The API server has started.
* The model is loaded.
* The URL and port are connected.
* The firewall allows access.
* Enable Network access for remote connections.
* You are not using {{code|localhost}} for a remote model.

===Kai does not display any Models===
If Kai is not displaying any models, verify that:
* A model has been downloaded.
* The model is available to the API server.
* The correct backend is selected.
* The connection test succeeds.

Restart the API server if the model list does not refresh.

===The Model is Slow or Runs Out of Memory===
If the model is runnig slow of runs out of memory, try the following troubleshooting:
# Selecting a smaller model.
# Using a more efficient quantization.
# Reducing the context-window size.
# Closing memory-intensive applications.
# Confirming that GPU acceleration is active.
# Running the model on another computer.
# Using LLM Fit to identify a better model.

===Chat Works, but Code Completions Does Not===
If the chat is working but the code completion feature is not, verify the following to troubleshoot the issue.
* The completion model supports FIM.
* The correct backend is selected.
* The correct FIM preset is selected.
* Manually entered FIM tokens match the exact model version.
* The '''Local Models''' option is selected in the Kai Completions settings.

{{Note|Chat support does not guarantee FIM support.}}

===Suggestions Repeat Existing Code or Appear Misplaced===
The Suggestions feature may be repeating existing code or appearing in incorrect places.

Check if the FIM is configured correctly and verify the selected preset or the manually entered prefix, suffix, and middle tokens.

===The Model Produces Incorrect Code===
# If the model is returning incorrect, try the following:
# Specify the exact RAD Studio version.
# Identify Delphi or C++Builder.
# Identify VCL or FireMonkey.
# Provide the relevant existing declarations.
# Compile the code.
# Return the exact compiler error to Kai.
# Ask Kai to correct only the reported issue.

==Security Considerations==
A local model can keep prompts and code within the infrastructure under your control, but the complete configuration may include other tools and services. For better security measurements, review the following:
* Whether the runtime sends optional telemetry.
* Whether MCP servers connect to external systems.
* Whether the API server is accessible outside the intended network.
* Whether downloaded models come from trusted sources.
* Whether project files contain credentials or regulated data.

Do not expose an unauthenticated local-model server directly to the public internet. Instead, use the following:
* A trusted private network.
* Appropriate firewall rules.
* Authentication, when supported.
* Source control to review and reverse generated changes.
* Least-privilege permissions for project and file access.

== See Also ==
* [[Kai Installation]]
* [[Kai Options]]
* [[Kai Options: Chat]]
* [[Kai Options: Completions]]
* [[Kai Options: MCP Servers]]
* [[GetIt Package Manager]]

Kai Installation

Nicolas.rios — Mon, 27 Jul 2026 13:40:19 GMT

← Older revision		Revision as of 13:40, 27 July 2026
Line 17:		Line 17:

	==Kai Installation==		==Kai Installation==
			Once downloaded from the GetIt package manager, the installation window displays. Follow the steps to complete the installation.
			# Ensure to read the License Agreement information, select the '''I accept the agreement''' option, and click '''Next'''.
			# Ensure to read the Information screen and click '''Next'''.
			# Select the destination location folder.
			# On the components screen, you can select components manually or choose one of the drop-down options: '''Full installation''', '''Compact installation''', '''Custom installation''', '''Local models only''', '''Chat only''', or '''Completions only'''.[[File:Kai install selectComponents.png\|=link\|border]]
			# Select any additional task you wish to perform.
			# On the Ready to Install screen, review all selected settings, then click '''Install''' to begin installation.

	Once the installation is complete, the {{Product}} splash screen displays a specific entry for the Kai package, along with its [[Kai Licensing\|licensing status]].		Once the installation is complete, the {{Product}} splash screen displays a specific entry for the Kai package, along with its [[Kai Licensing\|licensing status]].
Line 38:		Line 44:

	=== Claude Integration ===		=== Claude Integration ===
	If you wish to integrate Claude Code as an LLM interface, you first need to have npm installed to install the Claude Agent ACP. The next step would be to install Claude Code.		If you wish to integrate Claude Code as an LLM interface, you first need to have npm installed to install the Claude Agent ACP. The next step would be to install Claude Code. Note that the Claude Agent is not the same as the Claude desktop app. You need to install the Claude Agent even if you have previously installed Claude Desktop.

	{{Note\| Claude Code cannot be legally distributed ~~within~~ a third-party installer.}}		{{Note\| Claude Code cannot be legally distributed by a third-party installer.}}

	Follow the steps below to integrate Claude Code:		Follow the steps below to integrate Claude Code:

	1. ~~Download the [https://nodejs.org/ Node.js LTS] installer~~.		1. Close {{Product}} if it is open.

	2. ~~Install~~ Node.js		2. Download the [https://nodejs.org/ Node.js LTS] installer.

	3. Open a terminal to use npm, and run:		3. Install Node.js; this also installs npm.

			4. Open a terminal to use npm, and run:
	Npm install -g @agentclientprotocol/claude-agent-acp		Npm install -g @agentclientprotocol/claude-agent-acp

	4. Install Claude Code from PowerShell and add it to the path as needed, for example:		5. Install Claude Code from PowerShell and add it to the path as needed, for example:
	Irm http://claude.ai/install.ps1 \| iex		Irm http://claude.ai/install.ps1 \| iex

			6. Now, from the terminal window, run the following Claude command:
			claude

			7. A prompt pops up asking users to log in to Claude. Follow the instructions and, in the browser window, log in to your Claude account. Once logged in, return to the terminal window.

			{{Note\| At this point, the installation is complete, but it is necessary to ensure that Claude tools are visible in {{Product}}. This can be done by checking the path environment variable.}}

			8. Click the Windows key and search for "'''envir'''". Select the '''Edit the system environment variables''' option.

			[[File:Env variables search.png\|=link\|border]]

			9. When the System Properties window opens, ensure you are in the '''Advanced''' tab and click the '''Environment Variables''' option.

			[[File:Env variables sysprop.png\|=link\|border]]

			10. In the Environment Variables window, select the '''Path''' variable and click the '''Edit button'''.

			[[File:Env variables path.png\|=link\|border]]

			11. In the dialog box that appears, click on the '''New''' button.

			[[File:Env variables.png\|=link\|border]]

			12. Next, edit the new blank entry by typing:
			%USERPROFILE%\.local\bin

			13. Click '''Ok''' and close the Environment variable window.

			14. Now, when you go into {{Product}}, you will be able to select Claude as one of the options in the Kai Chat window.

			{{Note\| When navigating in the {{Menu\|Tools > Options > [[Kai Options\|Kai]]}} settings, Claude Code cannot detect if you are logged in; thus, the Kai settings configuration window displays a message requesting users to log in. This is static and does not reflect the real status.}}

	==See Also==		==See Also==

File:Env variables.png

Nicolas.rios — Mon, 27 Jul 2026 13:40:12 GMT

Nicolas.rios uploaded File:Env variables.png

New page

Env variables

File:Env variables path.png

Nicolas.rios — Mon, 27 Jul 2026 13:39:40 GMT

Nicolas.rios uploaded File:Env variables path.png

New page

Env variables path

File:Env variables sysprop.png

Nicolas.rios — Mon, 27 Jul 2026 13:39:08 GMT

Nicolas.rios uploaded File:Env variables sysprop.png

New page

Env variables sysprop

File:Env variables search.png

Nicolas.rios — Mon, 27 Jul 2026 13:31:25 GMT

Nicolas.rios uploaded File:Env variables search.png

New page

Env variables search

X1033 Unit '%s' implicitly imported into package '%s' (Delphi)

Yukikoi — Fri, 24 Jul 2026 01:28:58 GMT

F1027 Unit not found '%s' or binary equivalents (%s) (Delphi)

Yukikoi — Fri, 24 Jul 2026 01:26:34 GMT

remove [[

← Older revision		Revision as of 01:26, 24 July 2026
Line 13:		Line 13:
	== See Also ==		== See Also ==
	* [https://docwiki.embarcadero.com/Support/en/Getting_%22F1027_Unit_not_found%22_compiling_release_mode_for_iosDevice Support Article: F1027 when Compiling for iOS Device]		* [https://docwiki.embarcadero.com/Support/en/Getting_%22F1027_Unit_not_found%22_compiling_release_mode_for_iosDevice Support Article: F1027 when Compiling for iOS Device]
	* [[[[Warning messages (Delphi)]]		* [[Warning messages (Delphi)]]

	[[Category:{{Product}} Reference]]		[[Category:{{Product}} Reference]]

Kai Options: Completions

Nicolas.rios — Thu, 23 Jul 2026 21:07:29 GMT

← Older revision		Revision as of 21:07, 23 July 2026
(One intermediate revision by the same user not shown)
Line 3:		Line 3:
	{{Menu\|Tools > Options > Kai > Completions}}		{{Menu\|Tools > Options > Kai > Completions}}

	Here you can configure AI code completion providers for Kai.		Here, you can configure AI code-completion providers for Kai.

	Kai supports multiple completion engines, including cloud-based providers and local models. You must sign in or configure the selected provider before using AI completions.		Kai supports multiple completion engines, including cloud-based providers and local models. You must sign in or configure the selected provider before using AI completions.

	[[File:~~Settings-~~Completions~~-Light~~.png\|900px\|border]]		[[File:Completions local models.png\|900px\|border]]

	== Completions Options ==		== Completions Options ==
Line 151:		Line 151:

	Kai uses a Bring Your Own Key (BYOK) model. Depending on the selected provider, you may need a valid account or API key.		Kai uses a Bring Your Own Key (BYOK) model. Depending on the selected provider, you may need a valid account or API key.

			==FIM Tokens Tab==
			FIM (Fill-In-the-Middle) tokens are special control tokens that tell a language model to complete text between a given prefix and suffix, rather than simply continuing from the end of a prompt. They are particularly important for code completion in IDEs, where the model needs to insert code at the cursor while preserving the code that follows. Configuring these token parameters allows user integration with additional local AI engines.

			Since different model families use different special tokens, Kai now lets you choose predefined options or manually customize the FIM tokens.

			[[File:Kai completions fim.png\|800px\|border]]

			{{Note\|To determine if a local LLM supports FIM, check the model information on the backend model, such as Hugging Face or the vendor’s documentation. It often explicitly states “Supports Fill-in-the-Middle (FIM).”}}

			Most popular local coding models with FIM support include:
			* StarCoder
			* CodeLlama
			* DeepSeek-Coder
			* Qwen2.5-Coder
			* Codestral
			* Replit Code models

	==See Also==		==See Also==

File:Completions local models.png

Nicolas.rios — Thu, 23 Jul 2026 21:06:15 GMT

Nicolas.rios uploaded File:Completions local models.png

New page

Completions local models

File:Kai completions fim.png

Nicolas.rios — Thu, 23 Jul 2026 20:19:50 GMT

Nicolas.rios uploaded File:Kai completions fim.png

New page

Kai completions fim

Kai Release Notes

Nicolas.rios — Thu, 23 Jul 2026 20:16:46 GMT

KAI-176

@@ Line 3: / Line 3: @@
 These Release Notes contain important Kai information based on each {{Product}} version.
-=={{Product}} Florence 13.1==
+== Kai version 1.0.2 ==
 '''Stability Issues with Gemini version''':
-The {{code|0.42.0-preview.0}} release of Google Gemini CLI is included as part of the Kai 1.0 release. There have been reports of stability issues in some environments with this version of the Google Gemini CLI.
+The {{code| 0.42.0-preview.0}} release of Google Gemini CLI is included as part of the Kai 1.0 release. There have been reports of stability issues in some environments with this version of the Google Gemini CLI.
 Customers experiencing stability-related behavior can manually downgrade to version {{code|0.35.3}} to mitigate the issue in affected environments. However, downgrading may reintroduce security vulnerabilities or dependency issues that were addressed in later releases, such as the {{code|0.42.0-preview.0}} release.
 ==See Also==
 * [[Kai Overview]]
 * [[Kai Features]]

Kai Installation

Nicolas.rios — Thu, 23 Jul 2026 20:15:50 GMT

← Older revision		Revision as of 20:15, 23 July 2026
Line 10:		Line 10:
	Using the GetIt package manager, search for '''Kai''' and click '''Install'''.		Using the GetIt package manager, search for '''Kai''' and click '''Install'''.

	[[File:Kai ~~install~~.png\|~~600px~~\|border]]		[[File:Kai getit package.png\|650px\|border\|=link]]

	Another option is to download Kai from the [http://my.embarcadero.com/ Embarcadero customer portal] with an active EDN account.		Another option is to download Kai from the [http://my.embarcadero.com/ Embarcadero customer portal] with an active EDN account.

File:Kai getit package.png

Nicolas.rios — Thu, 23 Jul 2026 20:15:12 GMT

Nicolas.rios uploaded File:Kai getit package.png

New page

Kai getit package

Kai Installation

Nicolas.rios — Thu, 23 Jul 2026 20:13:47 GMT

Download Kai

← Older revision		Revision as of 20:13, 23 July 2026
(2 intermediate revisions by the same user not shown)
Line 13:		Line 13:

	Another option is to download Kai from the [http://my.embarcadero.com/ Embarcadero customer portal] with an active EDN account.		Another option is to download Kai from the [http://my.embarcadero.com/ Embarcadero customer portal] with an active EDN account.

			{{Note\|The latest Kai version 1.0.2, is available in GetIt. You can find it in the [[GetIt Package Manager]] dialog or from the Kai Welcome Page. The installer automatically removes the previous version and installs Kai 1.0.2. A restart of RAD Studio is required to complete the update.}}

	==Kai Installation==		==Kai Installation==

← Older revision		Revision as of 01:28, 24 July 2026
Line 56:		Line 56:
	* [[Add dialog box, Add Unit tab]]		* [[Add dialog box, Add Unit tab]]
	* [[Add dialog box, Requires tab]]		* [[Add dialog box, Requires tab]]
	* [[[[Warning messages (Delphi)]]		* [[Warning messages (Delphi)]]