Add Kai documentation: setup guides, LLM configuration, and analysis procedures

content/docs/Konveyor/Kai/GettingStarted/_index.md

@@ -0,0 +1,59 @@
+---
+title: "Getting started with Konveyor AI"
+date: 2025-12-13T14:58:52-06:00
+draft: false
+---
+The Getting started section contains information to walk you through the
+prerequisites, persistent volume requirements, installation, and
+workflows that help you to decide how you want to use the Konveyor AI.
+
+## Prerequisites
+
+This section lists the prerequisites required to successfully use the
+generative AI features in the Konveyor AI Visual Studio (VS) Code
+extension.
+
+Before you install Konveyor AI, you must:
+
+- Install Java v17 and later
+
+- Install Maven v3.9.9 or later
+
+- Install Git and add it to the $PATH variable
+
+- Install the Konveyor Operator 8.0.0
+
+  The Konveyor Operator is mandatory if you plan to enable the Solution
+  Server. Solution Server provides context for the large language model (LLM) for generating code changes. It enables you to log in to the `konveyor-ai` project where you must enable the Solution Server in the Tackle custom resources (CR).
+
+- Create an API key for an LLM.
+
+  You must enter the provider value and model name in Tackle CR to
+  enable generative AI configuration in the Konveyor VS Code plugin.
+
+
+| LLM Provider (Tackle CR value) | Large language model examples for Tackle CR configuration|
+|--------------------------------|--------------------------------|
+| OpenShift AI platform          | Models deployed in OpenShift AI                                               |
+| Open AI (openai)               | `gpt-4`, `gpt-4o`,`gpt-4o-mini`                                           |
+| Azure OpenAI (azure_openai)    | `gpt-4`,`gpt-35-turbo`                                                        |
+| Amazon Bedrock (bedrock)       | `anthropic.claude-3-5-sonnet-20241022-v2:0`,   `meta.llama3-1-70b-instruct-v1:0` |
+| Google Gemini (google)         | `gemini-2.0-flash-exp`, `gemini-1.5-pro`                                       |
+| Ollama (ollama)                | `llama3.1`, `codellama`,`mistral`|
+
+
+**Note:** The availability of public LLM models is maintained by the respective LLM provider.
+
+## Persistent Volume
+
+The Solution Server component requires a backend database to store code changes from previous analyses.
+
+If you plan to enable Solution Server, you must create a `5Gi` `RWO` persistent volume used by the Konveyor AI database.
+
+
+## Installation
+
+You can install the Konveyor AI extension from the [Konveyor AI release page in GitHub](https://github.com/konveyor/editor-extensions/releases/tag/v0.2.0).
+
+You can use the Konveyor VS Code plug-in to perform analysis and
+optionally enable KAI to use generative AI capabilities. Use KAI to fix code issues before migrating the application to target technologies by using the generative AI capabilities.

content/docs/Konveyor/Kai/GettingStarted/con_developer-lightspeed-pathways.md

@@ -0,0 +1,52 @@
+---
+title: "How to use Konveyor AI"
+date: 2025-12-15T14:58:52-06:00
+draft: false
+---
+You can opt to use Konveyor AI features to request a code fix suggestion after running a static code analysis of an application. Konveyor AI augments the manual changes made to code throughout your organization in different migration waves and creates a context that is shared with a large language model (LLM). 
+
+The LLM suggests code resolutions based on the issue description, context, and previous examples of code changes to resolve issues.
+
+To make code changes by using the LLM, you must enable the generative AI option. 
+
+You can use Konveyor in one of the three ways after enabling generative AI in VS Code:
+
+* Use LLM to generate code fix suggestion. 
+
+* Use LLM along with the Solution Server 
+
+* Use the LLM with the Agent AI. 
+
+The configurations that you complete before you request code fixes depend on how you prefer to request code resolutions.
+
+**NOTE:** If you make any configuration change after enabling the generative AI settings in the extension, you must restart the extension for the change to take effect.
+
+To use the LLM for code fix suggestions:
+
+- Enable the generative AI option in the Konveyor plugin extension
+  settings.
+
+- Activate the LLM provider in the `provider-settings.yaml` file.
+
+- `Start` the RPC server to run the analysis and get code fix suggestions for the identified issues.
+
+To use the Solution Server to provide an additional context for the LLM:
+
+- Create a secret for your LLM key in the Kubernetes cluster.
+
+- Enable the Solution Server in the Tackle custom resource (CR).
+
+- Configure the LLM base URL and model in the Tackle CR.
+
+- Enable the generative AI option in the Konveyor plugin extension
+  settings.
+
+- Add the Solution Server configuration in the `settings.json` file.
+
+- Configure the profile settings and activate the LLM provider in the `provider-settings.yaml` file.
+
+To use the agent mode for code fix suggestions:
+
+- Enable the generative AI and the agent mode in the Konveyor plugin extension settings.
+
+- Configure the profile settings and activate the LLM provider in the `provider-settings.yaml` file.

content/docs/Konveyor/Kai/GettingStarted/ref_example-code-suggestion.md

@@ -0,0 +1,91 @@
+---
+title: "Generating code fix suggestion example"
+date: 2025-12-14T14:58:52-06:00
+draft: false
+---
+This example will walk you through generating code fixes for a `Java` application that must be migrated to the target technology `quarkus`. To generate resolutions for issues in the code, we use the Agentic AI mode and the `my-model` as the large language model (LLM) that you deployed in OpenShift AI.
+
+## Procedure
+
+1.  Open the `my-Java` project in Visual Studio (VS) Code.
+
+2.  Download the Konveyor AI extension from the [Konveyor AI release page in GitHub](https://github.com/konveyor/editor-extensions/releases/tag/v0.2.0).
+
+3.  Open Command Palette:
+
+    1.  Type `Ctrl+Shift+P` in Windows and Linux systems.
+
+    2.  Type `Cmd+Shift+P` in Mac systems.
+
+4.  Type `Preferences: Open Settings (UI)` in the Command Palette to
+    open the VS Code settings and select `Extensions > Konveyor AI`.
+
+5.  Select `Gen AI:Agent Mode`.
+
+6.  In the Konveyor AI extension, click `Open Analysis View`.
+
+7.  Type `Konveyor: Manage Analysis Profile` in the Command Palette to open
+    the analysis profile page.
+
+8.  Configure the following fields:
+
+    1.  **Profile Name**: Type a profile name
+
+    2.  **Target Technologies**: `quarkus`
+
+    3.  **Custom Rules**: Select custom rules if you want to include
+        them while running the analysis. By default, Konveyor AI enables
+        **Use Default Rules** for `quarkus`.
+
+9.  Close the profile manager.
+
+10. Type `Konveyor: Open the Gen AI model provider configuration file` in the
+    Command Palette.
+
+11. Configure the following in the `provider-settings` file and close
+    it:
+    ```yaml
+        models:
+          openshift-example-model: &active
+            environment:
+              OPENAI_API_KEY: "<Server's OPENAI_API_KEY>"
+              CA_BUNDLE: "<Servers CA Bundle path>"
+            provider: "ChatOpenAI"
+            args:
+              model: "my-model"
+              configuration:
+                baseURL: "https://<serving-name>-<data-science-project-name>.apps.konveyor-ai.example.com/v1"
+    ```
+    You must change the `provider-setting` configuration if you plan to
+    use a different LLM provider.
+
+12. Type `Konveyor AI: Open Analysis View` in the Command Palette.
+
+13. Click **Start** to start the Konveyor AI RPC server.
+
+14. Select the profile you configured.
+
+15. Click **Run Analysis** to scan the Java application.
+
+    Konveyor AI identifies the issues in the code.
+
+16. Click the solutions icon in an issue
+    to request suggestions to resolve the issue.
+
+    Konveyor AI streams the issue description, a preview of the code
+    changes that resolve the issue, and the file(s) in which the changes
+    are to be made.
+
+    You can review the code changes in the editor and accept or reject
+    the changes. If you accept the changes, Konveyor AI creates a new
+    file with the accepted code changes.
+
+17. Click **Continue** to allow Konveyor AI to run a follow-up analysis.
+
+    This round of analysis detects lint issues, compilation issues, or
+    diagnostic issues that may have occurred when you accepted the
+    suggested code change.
+
+    Repeat the review and accept or reject the resolutions. Konveyor AI
+    continues to run repeated iterations of scan if you allow until all
+    issues are resolved.

content/docs/Konveyor/Kai/IDESettings/_index.md

@@ -0,0 +1,12 @@
+---
+title: "Using Konveyor AI in IDE"
+date: 2025-12-06T14:58:52-06:00
+draft: false
+---
+You must configure the following settings in the Konveyor extension:
+
+- Visual Studio Code IDE settings.
+
+- Profile settings that provide context before you request a code fix for a particular application.
+
+

content/docs/Konveyor/Kai/IDESettings/proc_configuring-developer-lightspeed-ide-settings.md

@@ -0,0 +1,57 @@
+---
+title: "Configuring the LLM provider settings"
+date: 2025-12-05T14:58:52-06:00
+draft: false
+---
+After you install the Konveyor extension in Visual Studio (VS) Code, you must provide your large language model (LLM) credentials to activate Konveyor AI settings in Visual Studio (VS) Code.
+
+Konveyor AI settings are applied to all AI-assisted analysis that you perform by using the Konveyor extension. The extension settings can be broadly categorized into debugging and logging, Konveyor AI settings, analysis settings, and Solution Server settings.
+
+## Prerequisites
+
+In addition to the overall prerequisites, you have configured the
+following:
+
+- You completed the Solution Server configurations in Tackle custom
+  resource if you opt to use the Solution Server.
+
+## Procedure
+
+1.  Go to the Konveyor AI settings in one of the following ways:
+
+    1.  Click `Extensions > Konveyor Extension for VSCode > Settings`
+
+    2.  Type `Ctrl + Shift + P` or `Cmd + Shift + P` on the search bar
+        to open the Command Palette and enter
+        `Preferences: Open Settings (UI)`. Go to `Extensions > Konveyor` to
+        open the settings page.
+
+2.  Configure the settings described in the following table:
+
+| Settings       | Description                                        |
+|----------------|----------------------------------------------------|
+| Log level | Set the log level for the Konveyor binary. The default log level is `debug`.The log level increases or decreases the verbosity of logs. |
+| Analyzer path| Specify an Konveyor custom binary path. If you do not provide a path, Konveyor extension uses the default path to the binary.|
+| Auto Accept on Save | This option is enabled by default. When you accept the changes suggested by the LLM, the updated code is saved automatically in a new file. Disable this option if you want to manually save the new file after accepting the suggested code changes.|
+| Gen AI:Enabled | This option is enabled by default. It enables you to get code fixes by using Konveyor AI with a large language model.|
+| Gen AI: Agent mode | Enable the experimental Agentic AI flow for analysis. Konveyor runs an automated analysis of a file to identify issues and suggest resolutions. After you accept the solutions, Konveyor AI makes the changes in the code and re-analyzes the file. |
+| Gen AI: Excluded diagnostic sources 	| Add diagnostic sources in the `settings.json` file. The issues generated by such diagnostic sources are excluded from the automated Agentic AI analysis.|
+| Cache directory| Specify the path to a directory in your filesystem to store cached responses from the LLM. 	|
+| Trace directory| Configure the absolute path to the directory that contains the saved LLM interaction.|
+| Trace enabled| Enable to trace Konveyor communication with the LLM model. Traces are stored in the `trace` directory that you configured.	|
+| Demo mode | Enable to run Konveyor AI in demo mode that uses the LLM responses saved in the `cache` directory for analysis. |
+| Solution Server:URL | Edit Solution Server configurion.                      
+| Debug:Webview | Enable debug level logging for Webview message handling in VS Code.|
+
+Solution server configuration:
+* “enabled”: Enter a boolean value. Set `true` for connecting the Solution Server client (Konveyor extension) to the Solution Server. <br>
+
+* “url”: Configure the URL of the Solution Server end point.  <br>
+
+* “auth”: The authentication settings allows you to configure a list of options to authenticate to the Solution Server.  <br>
+
+    * "enabled": Set to `true` to enable authentication. If you enable authentication, then you must configure the Solution Server realm. <br> 
+
+    * "insecure": Set to `true` to skip SSL certificate verification when clients connect to the Solution Server. Set to `false` to allow secure connections to the Solution Server. <br>       
+
+    * "realm": Enter the name of the Keycloak realm for Solution Server. If you enabled authentication for the Solution Server, you must configure a Keycloak realm to allow clients to connect to the Solution Server. An administrator can configure SSL for the realm.|

content/docs/Konveyor/Kai/IDESettings/proc_configuring-developer-profile-settings.md

@@ -0,0 +1,46 @@
+---
+title: "Configuring the Konveyor AI profile settings"
+date: 2025-12-03T14:58:52-06:00
+draft: false
+---
+You can use the Visual Studio (VS) Code plugin to run an analysis to discover issues in the code. You can optionally enable Konveyor AI to get AI-assisted code suggestions.
+
+To generate code changes using the Konveyor extension, you must
+configure a profile that contains all the necessary configurations, such as source and target technologies and the API key to connect to your chosen large language model (LLM).
+
+## Prerequisites
+
+- You completed the Solution Server configurations in Tackle custom
+  resource if you opt to use the Solution Server.
+
+- You opened a Java project in your VS Code workspace.
+
+## Procedure
+
+1.  Open the `Konveyor View Analysis` page in either of the following
+    ways:
+
+    1.  Click the book icon on the `Konveyor: Issues` pane of the
+        Konveyor extension.
+
+    2.  Type `Ctrl + Shift + P` or `Cmd + Shift + P` on the search bar
+        to open the Command Palette and enter
+        `Konveyor:Open Analysis View`.
+
+2.  Click the settings button on the `Konveyor View Analysis` page to
+    configure a profile for your project. The `Get Ready to Analyze`
+    pane lists the following basic configurations required for an
+    analysis:
+
+| Profile settings         | Description  |
+|--------------------------|--------------|
+| Select profile           | Create a profile that you can reuse for<br>multiple analyses. The profile name is part of the context provided to<br>the LLM for analysis. |
+| Configure label selector | A label selector filters rules for<br>analysis based on the source or target technology.<br>Specify one or more target or source technologies (for example,<br>cloud-readiness). The Konveyor extension uses this configuration to<br>determine the rules that are applied to a project during analysis.<br>If you mentioned a new target or a source technology in your custom<br>rule, you can type that name to create and add the new item to the<br>list.<br><br><br>&#10;<br>You must configure either target or source technologies before<br>running an analysis.<br> |
+| Set rules                | Enable default rules and select your<br>custom rule that you want Konveyor to use for an analysis. You can use<br>the custom rules in addition to the default rules.  |
+| Configure generative AI  | This option opens the<br>provider-settings.yaml file that contains API keys and<br>other parameters for all supported LLMs. By default, Konveyor AI is<br>configured to use OpenAI LLM. To change the model, update the anchor<br>&amp;active to the desired block. Modify this file with the<br>required arguments, such as the model and API key, to complete the<br>setup.  See [Configuring the LLM provider settings](../LLMSettings/ref_llm-provider-configurations.md). |
+
+
+## Verification
+
+After you complete the profile configuration, close the `Get Ready to Analyze` pane. You can verify that your configuration works by running an analysis.
+

content/docs/Konveyor/Kai/IDESettings/proc_configuring-solution-server-settings-file.md

@@ -0,0 +1,46 @@
+---
+title: "Configuring the Solution Server settings"
+date: 2025-12-04T14:58:52-06:00
+draft: false
+---
+You need a Keycloak realm and the Solution Server URL to connect
+Konveyor extension with the Solution Server.
+
+## Prerequisites
+
+- The Solution Server URL is available.
+
+- An administrator configured the Keycloak realm for the Solution
+  Server.
+
+## Procedure
+
+1.  Type `Ctrl + Shift + P` or `Cmd + Shift + P` on the search bar and
+    enter `Preferences:Open User Settings (JSON)`.
+
+2.  In the `settings.json` file, enter `Ctrl + SPACE` to enable the
+    auto-complete for the Solution Server configurable fields.
+
+3.  Modify the following configuration as necessary:
+
+     ```json
+        {
+            "konveyor.solutionServer": {
+
+                "url": "https://konveyor.apps.konveyor-ai.example.com/hub/services/kai/api",
+
+                "enabled": true,
+                "auth": {
+
+                   "enabled": true, 
+                   "insecure": true,
+                   "realm": "tackle"
+                },
+
+            }
+        }
+     ```
+
+    **NOTE:** When you enable Solution Server authentication for the first time, you must enter the `username` and `password` in the VS >Code search bar.
+
+    **TIP:** Enter `Konveyor: Restart Solution Server` in the Command Palette >to restart the Solution Server.