https://github.com/devoxx/devoxxgenieideaplugin
DevoxxGenie is a plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code.
https://github.com/devoxx/devoxxgenieideaplugin
anthropic assistant azure-ai chatgpt chatgpt-api claude-3 claude-ai copilot copilot-chat gemini genai gpt4all groq intellij-plugin java llm lmstudio mistral ollama openai
Last synced: 18 days ago
JSON representation
DevoxxGenie is a plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code.
- Host: GitHub
- URL: https://github.com/devoxx/devoxxgenieideaplugin
- Owner: devoxx
- License: mit
- Created: 2024-04-14T21:08:14.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2025-04-10T16:37:08.000Z (11 months ago)
- Last Synced: 2025-04-13T00:41:52.176Z (11 months ago)
- Topics: anthropic, assistant, azure-ai, chatgpt, chatgpt-api, claude-3, claude-ai, copilot, copilot-chat, gemini, genai, gpt4all, groq, intellij-plugin, java, llm, lmstudio, mistral, ollama, openai
- Language: Java
- Homepage: https://devoxx.com
- Size: 15.3 MB
- Stars: 426
- Watchers: 10
- Forks: 48
- Open Issues: 47
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-ChatGPT-repositories - DevoxxGenieIDEAPlugin - DevoxxGenie is a plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Llama.cpp and Exo) and Cloud based LLMs to help review, test, explain your project code. (Browser-extensions)
README
## DevoxxGenie
[](https://x.com/devoxxgenie)
[](https://genie.devoxx.com)
Devoxx Genie is a fully Java-based LLM Code Assistant plugin for IntelliJ IDEA, designed to integrate with local LLM providers such as [Ollama](https://ollama.com/), [LMStudio](https://lmstudio.ai/), [GPT4All](https://gpt4all.io/index.html), [Llama.cpp](https://github.com/ggerganov/llama.cpp) and [Exo](https://github.com/exo-explore/exo) but also cloud based LLM's such as [OpenAI](https://openai.com), [Anthropic](https://www.anthropic.com/), [Mistral](https://mistral.ai/), [Groq](https://groq.com/), [Gemini](https://aistudio.google.com/app/apikey), [DeepInfra](https://deepinfra.com/dash/deployments), [DeepSeek](https://www.deepseek.com/), [Kimi](https://platform.moonshot.ai/), [GLM](https://open.bigmodel.cn/), [OpenRouter](https://www.openrouter.ai/), [Azure OpenAI](https://azure.microsoft.com/en-us/products/ai-services/openai-service) and [Amazon Bedrock](https://aws.amazon.com/bedrock)
**🆕 [Security Scanning](https://genie.devoxx.com/docs/features/security-scanning)** — Run **Gitleaks** (secret detection), **OpenGrep** (SAST) and **Trivy** (dependency CVEs) directly from the LLM agent. Findings are automatically created as prioritised tasks in the Spec Browser for tracking and remediation!
**🆕 [Spec Driven Development (SDD)](https://genie.devoxx.com/docs/features/spec-driven-development)** — Define tasks in `Backlog.md`, browse them in the Spec Browser with Task List and Kanban Board views, then let the Agent implement them autonomously! Use the **Agent Loop** to run multiple tasks in a single batch with dependency ordering and automatic advancement.
**🆕 [AI-powered Inline Code Completion](https://genie.devoxx.com/docs/features/inline-completion)** — Get context-aware code suggestions as you type using Fill-in-the-Middle (FIM) models via Ollama or LM Studio!
**🆕 [ACP Runners](https://genie.devoxx.com/docs/features/acp-runners)** — Communicate with external agents (Kimi, Gemini CLI, Kilocode, Claude Code, Copilot) via the Agent Communication Protocol (JSON-RPC 2.0 over stdin/stdout) with structured streaming, conversation history, and capability negotiation!
**🆕 [CLI Runners](https://genie.devoxx.com/docs/features/acp-runners)** — CLI Runners let you execute prompts and spec tasks directly from DevoxxGenie's chat interface or Spec Browser using external CLI tools like Claude Code, GitHub Copilot, Codex, Gemini CLI, and Kimi.
**🆕 [Plugin Integration API](https://genie.devoxx.com/blog/devoxxgenie-plugin-integrations)** — Other IntelliJ plugins can integrate with DevoxxGenie at runtime via a reflection-based `ExternalPromptService` — no compile-time dependency required. Two real-world POCs show it in action: a [SonarLint fork](https://github.com/stephanj/sonarlint-devoxxgenie-intellij) and a [SpotBugs fork](https://github.com/stephanj/spotbugs-devoxxgenie-plugin) that each send code-quality findings to DevoxxGenie with a single click, or defer them as Backlog tasks for the SDD workflow.
With [Agent Mode](https://genie.devoxx.com/docs/features/agent-mode), MCPs and frontier models like Claude Opus 4.6, Gemini Pro, DevoxxGenie isn't just another developer tool — it's a glimpse into the future of agentic programming. One thing's clear: we're in the midst of a paradigm shift in AI-Augmented Programming (AAP) 🐒
We also support RAG-based prompt context based on your vectorized project files, Git Diff viewer, and LLM-driven web search with [Google](https://developers.google.com/custom-search) and [Tavily](https://tavily.com/).
[
](https://plugins.jetbrains.com/plugin/24169-devoxxgenie)
45K+ Downloads
## 📚 Documentation
**[📖 Visit our comprehensive documentation at genie.devoxx.com](https://genie.devoxx.com)**
Quick links:
- [Getting Started](https://genie.devoxx.com/docs/intro) - Start using DevoxxGenie in minutes
- [Installation Guide](https://genie.devoxx.com/docs/category/installation) - Local and cloud LLM setup
- [Configuration](https://genie.devoxx.com/docs/category/configuration) - API keys, settings, and customization
- [Features](https://genie.devoxx.com/docs/category/features) - Explore all capabilities
- [Security Scanning](https://genie.devoxx.com/docs/features/security-scanning) - Gitleaks, OpenGrep and Trivy as LLM agent tools with auto-backlog task creation
- [Agent Mode](https://genie.devoxx.com/docs/features/agent-mode) - Autonomous code tools with parallel sub-agents
- [Spec Driven Development](https://genie.devoxx.com/docs/features/spec-driven-development) - Task management with Backlog.md, Kanban Board, and Agent implementation
- [Agent Loop](https://genie.devoxx.com/docs/features/sdd-agent-loop) - Batch task execution with dependency ordering and progress tracking
- [ACP Runners](https://genie.devoxx.com/docs/features/acp-runners) - Agent Communication Protocol integration with external agents
- [CLI Runners](https://genie.devoxx.com/docs/features/cli-runners) - Execute prompts and spec tasks via external CLI tools
- [Plugin Integration API](https://genie.devoxx.com/blog/devoxxgenie-plugin-integrations) - Integrate other IntelliJ plugins with DevoxxGenie at runtime
- [Inline Code Completion](https://genie.devoxx.com/docs/features/inline-completion) - AI-powered code suggestions as you type
- [MCP Support](https://genie.devoxx.com/docs/mcp-support) - Model Context Protocol integration
- [RAG Setup](https://genie.devoxx.com/docs/rag) - Retrieval-Augmented Generation guide
- [Troubleshooting](https://genie.devoxx.com/docs/troubleshooting) - Common issues and solutions
### 🔒 Security Scanning
**[📖 Full Security Scanning Documentation](https://genie.devoxx.com/docs/features/security-scanning)**
DevoxxGenie integrates three best-in-class open-source security scanners as **LLM agent tools**. When Agent Mode is active, the LLM can invoke them on demand, interpret the results in context, and automatically create prioritised backlog tasks for every finding.
| Scanner | What it detects | Install |
|---------|----------------|---------|
| **Gitleaks** | Hardcoded secrets, API keys, tokens | `brew install gitleaks` |
| **OpenGrep** | SAST issues — injection flaws, insecure patterns | `brew install opengrep` |
| **Trivy** | Dependency CVEs (SCA) | `brew install trivy` |
Ask the agent: *"Run a full security scan and create backlog tasks for everything you find."*
Enable in **Settings → DevoxxGenie → Security Scanning**. Each scanner has a path browser, a Test button, and install guidance. Findings are deduplicated — re-running a scan will not create duplicate tasks.
### Spec Driven Development (SDD)
**[📖 Full SDD Documentation](https://genie.devoxx.com/docs/features/spec-driven-development)**
Spec Driven Development brings structured task management directly into your IDE. Instead of ad-hoc prompts, define your tasks in `Backlog.md` files, browse them in the **Spec Browser**, and let the Agent implement them autonomously.
**How it works:**
1. **Create tasks** — Use natural language prompts or write Backlog.md task specs manually
2. **Browse in Specs** — View tasks in a Task List or visual Kanban Board with drag-and-drop
3. **Implement with Agent** — Click "Implement with Agent" and let the AI do the work
The Kanban Board gives you a visual overview of task status with drag-and-drop support:
17 built-in backlog tools provide full CRUD operations on tasks, documents, and milestones — all accessible to the LLM agent for autonomous project management.
#### Agent Loop — Batch Task Execution
Select multiple tasks (or click "Run All To Do") and the **Agent Loop** executes them sequentially in a single batch. Tasks are automatically sorted by dependencies using topological ordering, and each task gets a fresh conversation. The agent implements each task autonomously, and when it marks a task as Done the runner advances to the next one — with progress tracking and notifications throughout.
**[📖 Agent Loop Documentation](https://genie.devoxx.com/docs/features/sdd-agent-loop)**
### Agentic Programming with DevoxxGenie
#### Unlocking AI Coding Assistants: Real World Use Cases by Gunter Rotsaert
[](https://youtu.be/LtAe8EB72OI?si=wVfqa_2CUt5ZtQSO)
#### Building full-stack AI agents: From project generation to code execution by Stephan Janssen
[](https://www.youtube.com/watch?v=I4qPgRHCLBY)
### 🗂️ Video Tutorials:
- [Building full-stack AI agents: From project generation to code execution (Devoxx France 2025)](https://www.youtube.com/watch?v=I4qPgRHCLBY)
- [Agentic programming with DevoxxGenie (VoxxedDays Bucharest 2025)](https://www.youtube.com/watch?v=ZRNx9ZOoxsg)
- [DevoxxGenie in action (Devoxx Belgium 2024)](https://www.youtube.com/watch?v=c5EyVLAXaGQ)
- [How ChatMemory works](https://www.youtube.com/watch?v=NRAe4d7n6_4)
- [Hands-on with DevoxxGenie](https://youtu.be/Rs8S4rMTR9s?feature=shared)
- [The Era of AAP: Ai Augmented Programming using only Java](https://www.youtube.com/watch?v=yvgvALVs3xo)
- [DevoxxGenie Demo 2024](https://www.youtube.com/live/kgtctcbA6WE?feature=shared&t=124)
### Blog Posts:
- [DevoxxGenie: Your AI Assistant for IDEA](https://mydeveloperplanet.com/2024/10/08/devoxxgenie-your-ai-assistant-for-idea/)
- [The Devoxx Genie IntelliJ Plugin Provides Access to Local or Cloud Based LLM Models](https://www.infoq.com/news/2024/05/devoxx-genie-intellij-plugin/)
- [10K+ Downloads Milestone for DevoxxGenie!](https://www.linkedin.com/pulse/10k-downloads-milestone-devoxxgenie-stephan-janssen-hokce/)
### Key Features:
- **🔒 [Security Scanning](https://genie.devoxx.com/docs/features/security-scanning)** *(v0.9.17+)*: Run Gitleaks (secret detection), OpenGrep (SAST) and Trivy (SCA/CVEs) as LLM agent tools. Each finding is auto-created as a prioritised Backlog.md task. Enable in Settings → Security Scanning.
- **📋 [Spec Driven Development](https://genie.devoxx.com/docs/features/spec-driven-development)** *(v0.9.7+)*: Define tasks in Backlog.md, browse them in the Spec Browser (Task List + Kanban Board), and let the Agent implement them. 17 built-in backlog tools for full CRUD on tasks, documents, and milestones. Use the [Agent Loop](https://genie.devoxx.com/docs/features/sdd-agent-loop) to run multiple tasks in batch with dependency ordering *(v0.9.8+)*.
- **🆕 [ACP Runners](https://genie.devoxx.com/docs/features/acp-runners)** *(v0.9.10+)*: Communicate with external agents (Kimi, Gemini CLI, Kilocode, Claude Code, Copilot) via the Agent Communication Protocol with structured streaming, conversation history, and capability negotiation.
- **🔌 [Plugin Integration API](https://genie.devoxx.com/blog/devoxxgenie-plugin-integrations)** *(v0.9.12+)*: Let other IntelliJ plugins send prompts or create Backlog tasks via a reflection-based `ExternalPromptService` — no compile-time dependency required. Two POC integrations available: [SonarLint DevoxxGenie](https://github.com/stephanj/sonarlint-devoxxgenie-intellij) and [SpotBugs DevoxxGenie](https://github.com/stephanj/spotbugs-devoxxgenie-plugin).
- **🖥️ [CLI Runners](https://genie.devoxx.com/docs/features/cli-runners)** *(v0.9.9+)*: Execute prompts and spec tasks via external CLI tools (Claude Code, GitHub Copilot, Codex, Gemini CLI, Kimi) directly from the chat interface or the Spec Browser.
- **✨ [Inline Code Completion](https://genie.devoxx.com/docs/features/inline-completion)**: (v0.9.6+) AI-powered code suggestions as you type using Fill-in-the-Middle (FIM) models. Supports both Ollama and LM Studio with models like StarCoder2, Qwen2.5-Coder, and DeepSeek-Coder.
- **🤖 [Agent Mode](https://genie.devoxx.com/docs/features/agent-mode)** *(v0.9.4+)*: Autonomous code exploration and modification with built-in tools (read, write, edit, search files). Parallel sub-agents investigate multiple areas of your codebase concurrently, each with configurable provider/model. Enable in Agent Settings!
- **🔥️ [MCP Support with Marketplace](https://genie.devoxx.com/docs/features/mcp_expanded)**: Browse and install MCP servers from the integrated marketplace. Add MCP servers and use them in your conversations!
- **🗂️ [DEVOXXGENIE.md](https://genie.devoxx.com/docs/configuration/devoxxgenie-md)**: By incorporating this into the system prompt, the LLM will gain a deeper understanding of your project and provide more relevant responses.
- **📸 [DnD images](https://genie.devoxx.com/docs/features/dnd-images)**: You can now DnD images with multimodal LLM's.
- **🧐 [RAG Support](https://genie.devoxx.com/docs/features/rag)**: Retrieval-Augmented Generation (RAG) support for automatically incorporating project context into your prompts.
- **👀 [Chat History](https://genie.devoxx.com/docs/features/chat-interface)**: Your chats are stored locally, allowing you to easily restore them in the future.
- **🧠 [Project Scanner](https://genie.devoxx.com/docs/features/project-scanner)**: Add source code (full project or by package) to prompt context when using Anthropic, OpenAI or Gemini.
- **💰 [Token Cost Calculator](https://genie.devoxx.com/docs/configuration/token-cost)**: Calculate the cost when using Cloud LLM providers.
- **🔍 [Web Search](https://genie.devoxx.com/docs/features/web-search)**: Search the web for a given query using Google or Tavily.
- **🏎️ [Streaming responses](https://genie.devoxx.com/docs/features/chat-interface)**: See each token as it's received from the LLM in real-time.
- **🧐 [Abstract Syntax Tree (AST) context](https://genie.devoxx.com/docs/features/project-scanner)**: Automatically include parent class and class/field references in the prompt for better code analysis.
- **💬 [Chat Memory Size](https://genie.devoxx.com/docs/features/chat-memory)**: Set the size of your chat memory, by default its set to a total of 10 messages (system + user & AI msgs).
- **☕️ 100% Java**: An IDEA plugin using local and cloud based LLM models. Fully developed in Java using [Langchain4J](https://github.com/langchain4j/langchain4j)
- **👀 [Code Highlighting](https://genie.devoxx.com/docs/features/chat-interface)**: Supports highlighting of code blocks.
- **💬 [Chat conversations](https://genie.devoxx.com/docs/features/chat-memory)**: Supports chat conversations with configurable memory size.
- **📁 [Add files & code snippets to context](https://genie.devoxx.com/docs/features/chat-interface)**: You can add open files to the chat window context for producing better answers or code snippets if you want to have a super focused window
### Start in 5 Minutes with local LLM
- Download and start [Ollama](https://ollama.com/download)
- Open terminal and download a model using command "ollama run llama3.2"
- Start your IDEA and go to plugins > Marketplace and enter "Devoxx"
- Select "DevoxxGenie" and install plugin
- In the DevoxxGenie window select Ollama and available model
- Start prompting
### Start in 2 Minutes using Cloud LLM
- Start your IDEA and go to plugins > Marketplace and enter "Devoxx"
- Select "DevoxxGenie" and install plugin
- Click on DevoxxGenie cog (settings) icon and click on Cloud Provider link icon to create API KEY
- Paste API Key in Settings panel
- In the DevoxxGenie window select your cloud provider and model
- Start prompting
### 🗂️ Model Context Protocol servers support
**[📖 Full MCP Documentation](https://genie.devoxx.com/docs/mcp-support)**
Initial support for Model Context Protocol (MCP) server tools including debugging of MCP requests & responses!
MCP support is a crucial feature towards ful Agentic support within DevoxxGenie.
Watch [short demo](https://www.youtube.com/watch?v=zOPhYvgJKJU) of MCP in action using DevoxxGenie
Example of the Filesystem-server MCP which allows you to interact with the given directory.
Go to the DevoxxGenie settings to enable and add your MCP servers. Browse the **MCP Marketplace** to discover and install servers with just a few clicks!
When configured correctly you can see the tools that the MCP brings to your LLM conversations
[Agentic Magic in action](https://www.youtube.com/watch?v=T3o6t8tjoq4) 👀✨🧠
### 🗂️ DEVOXXGENIE.md
**[📖 DEVOXXGENIE.md Documentation](https://genie.devoxx.com/docs/devoxxgenie-md)**
You can now generate a **DEVOXXGENIE.md** file directly from the "Prompts" plugin settings page or just use /init in the prompt input field.
By incorporating this into the system prompt, the LLM will gain a deeper understanding of your project and provide more relevant responses.
This is a first step toward enabling agentic AI features for DevoxxGenie 🔥
Once generated, you can edit the DEVOXXGENIE.md file and add more details about your project as needed.
### 📸 "I can see" DnD images
You can now drag and drop images (and project files) directly into the input field when working with multimodal LLMs like Google Gemini, Anthropic Claude, ChatGPT 4.x,
or even local models such as [LLaVA](https://ollama.com/library/llava)
You can even combine screenshots together with some code and then ask related questions!
### 🔥 RAG Feature
**[📖 Full RAG Documentation](https://genie.devoxx.com/docs/rag)**
Devoxx Genie now includes starting from v0.4.0 a Retrieval-Augmented Generation (RAG) feature, which enables advanced code search and retrieval capabilities.
This feature uses a combination of natural language processing (NLP) and machine learning algorithms to analyze code snippets and identify relevant results based on their semantic meaning.
With RAG, you can:
* Search for code snippets using natural language queries
* Retrieve relevant code examples that match your query's intent
* Explore related concepts and ideas in the codebase
We currently use Ollama and Nomic Text embedding to generates vector representations of your project files.
These embedding vectors are then stored in a Chroma DB (v0.6.2) running locally within Docker.
The vectors are used to compute similarity scores between search queries and your code all running locally.
The RAG feature is a significant enhancement to Devoxx Genie's code search capabilities, enabling developers to quickly find relevant code examples and accelerate their coding workflow.
See also [Demo](https://www.youtube.com/watch?v=VVU8x45jIt4)
Expecting to add also [GraphRAG](https://github.com/devoxx/DevoxxGenieIDEAPlugin/issues/474) in the near future.
### LLM Settings
In the IDEA settings you can modify the REST endpoints and the LLM parameters. Make sure to press enter and apply to save your changes.
We now also support Cloud based LLMs, you can paste the API keys on the Settings page.
### Smart Model Selection and Cost Estimation
The language model dropdown is not just a list anymore, it's your compass for smart model selection.
See available context window sizes for each cloud model
View associated costs upfront
Make data-driven decisions on which model to use for your project
### Add Project to prompt & clipboard
You can now add the full project to your prompt IF your selected cloud LLM has a big enough window context.
### Calc Cost
Leverage the prompt cost calculator for precise budget management. Get real-time updates on how much of the context window you're using.
See the input/output costs and window context per Cloud LLM. Eventually we'll also allow you to edit these values.
### Handling Massive Projects?
"But wait," you might say, "my project is HUGE!" 😅
Fear not! We've got options:
1. Leverage Gemini's Massive Context:
Gemini's colossal 1 million token window isn't just big, it's massive. We're talking about the capacity to digest approximately 30,000 lines of code in a single go. That's enough to digest most codebases whole, from the tiniest scripts to some decent projects.
But if that's not enough you have more options...
2. Smart Filtering:
The new "Copy Project" panel lets you:
Exclude specific directories
Filter by file extensions
Remove JavaDocs to slim down your context
3. Selective Inclusion
Right-click to add only the most relevant parts of your project to the context.
## The Power of Full Context: A Real-World Example
The DevoxxGenie project itself, at about 70K tokens, fits comfortably within most high-end LLM context windows.
This allows for incredibly nuanced interactions – we're talking advanced queries and feature requests that leave tools like GitHub Copilot scratching their virtual heads!
## Support for JLama & LLama3.java
DevoxxGenie now also supports the 100% Modern Java LLM inference engines: [JLama](https://github.com/tjake/Jlama).
JLama offers a REST API compatible with the widely-used OpenAI API. Use the Custom OpenAI URL to connect.
You can also integrate it seamlessly with [Llama3.java](https://github.com/stephanj/Llama3JavaChatCompletionService) but using the Spring Boot OpenAI API wrapper coupled with the JLama DevoxxGenie option.
## Local LLM Cluster with Exo
Use the custom OpenAI URL to connect to Exo, a local LLM cluster for Apple Silicon which allows you to run Llama 3.1 8b, 70b and 405b on your own Apple computers 🤩
## Test Driven Generation (TDG) - Experimental
Write a unit test and let DevoxxGenie generated the implementation for that unit test.
This approach was explained by Bouke Nijhuis in his [Devoxx Belgium presentation](https://youtu.be/YRFpyGbp6h4?si=mYzJuVRMnclZJMIM)
An demo on how to accomplish this can be seen in this 𝕏 [post](https://x.com/Stephan007/status/1854949507710198209).
## DeepSeek R1 & DevoxxGenie 🔥
As of today (February 2, 2025), alongside the DeepSeek API Key, you can access the full 671B model for FREE using either [Nvidia](https://build.nvidia.com/deepseek-ai/deepseek-r1) or [Chutes](https://chutes.ai)!
Simply update the Custom OpenAI URL, Model and API Key on the Settings page as follows:
Chutes URL : https://chutes-deepseek-ai-deepseek-r1.chutes.ai/v1/
Nvidia URL : https://integrate.api.nvidia.com/v1
## Grok & DevoxxGenie
Create an account on [Grok](https://console.x.ai/) and generated an API Key. Now open the DevoxxGenie settings and enter the OpenAI compliant URL for Grok, the model you want to use and your API Key.
### Installation:
**[📖 Full Installation Guide](https://genie.devoxx.com/docs/category/installation)**
- **From IntelliJ IDEA**: Go to `Settings` -> `Plugins` -> `Marketplace` -> Enter 'Devoxx' to find [plugin](https://plugins.jetbrains.com/plugin/24169-devoxxgenie) OR Install plugin from Disk
- **From Source Code**: Clone the repository, build the plugin using `./gradlew buildPlugin`, and install the plugin from the `build/distributions` directory and select file 'DevoxxGenie-X.Y.Z.zip'
### Requirements:
- **IntelliJ** minimum version is 2023.3.4
- **Java** minimum version is JDK 17
### Build
Gradle IntelliJ Plugin prepares a ZIP archive when running the buildPlugin task.
You'll find it in the build/distributions/ directory
```shell
./gradlew buildPlugin
```
### Publish plugin
It is recommended to use the publishPlugin task for releasing the plugin
```shell
./gradlew publishPlugin
```
### Usage:
1) Select an LLM provider from the DevoxxGenie panel (right corner)
2) Select some code
4) Enter shortcode command review, explain, generate unit tests of the selected code or enter a custom prompt.
Enjoy!
## Contribute
**[📖 Contributing Guide](https://genie.devoxx.com/docs/contributing)**
### Understanding the Prompt Flow
The DevoxxGenie IDEA Plugin processes user prompts through the following steps:
### 1️⃣ User Inputs a Prompt
- [`UserPromptPanel`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/panel/UserPromptPanel.java) → Captures the prompt from the UI.
- [`PromptSubmissionListener.onPromptSubmitted()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/listener/PromptSubmissionListener.java) → Listens for the submission event.
- [`PromptExecutionController.handlePromptSubmission()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/controller/PromptExecutionController.java) → Starts execution.
### 2️⃣ Processing the Prompt
- [`PromptExecutionService.executeQuery()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/service/PromptExecutionService.java) → Handles token usage calculations and checks RAG/GitDiff settings.
- [`ChatPromptExecutor.executePrompt()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/service/ChatPromptExecutor.java) → Dispatches the prompt to the selected **LLM provider**.
- [`LLMProviderService.getAvailableModelProviders()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/service/LLMProviderService.java) → Retrieves the appropriate model from `ChatModelFactory`.
### 3️⃣ LLM Model Inference
- [`ChatModelFactory.getModels()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/chatmodel/ChatModelFactory.java) → Gets the models for the select LLM provider
- **Cloud-based LLMs:**
- [`OpenAIChatModelFactory.createChatModel()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/chatmodel/cloud/openai/OpenAIChatModelFactory.java)
- [`AnthropicChatModelFactory.createChatModel()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/chatmodel/cloud/anthropic/AnthropicChatModelFactory.java)
- ...
- **Local models:**
- [`OllamaChatModelFactory.createChatModel()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/chatmodel/local/ollama/OllamaChatModelFactory.java)
- [`GPT4AllChatModelFactory.createChatModel()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/chatmodel/local/gpt4all/GPT4AllChatModelFactory.java)
- ...
### 4️⃣ Response Handling
- **If streaming is enabled:**
- [`StreamingPromptExecutor.execute()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/service/streaming/StreamingPromptExecutor.java) → Begins token-by-token streaming.
- [`ChatStreamingResponsePanel.createHTMLRenderer()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/panel/ChatStreamingResponsePanel.java) → Updates UI in real time.
- **If non-streaming:**
- [`PromptExecutionService.executeQuery()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/service/PromptExecutionService.java) → Formats the full response.
- [`ChatResponsePanel.displayResponse()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/panel/ChatResponsePanel.java) → Renders the text and code blocks.
### 5️⃣ Enhancements (RAG)
#### **RAG (Retrieval-Augmented Generation)**
- **Indexing Source Code for Retrieval**
- [`ProjectIndexerService.indexFiles()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/service/rag/ProjectIndexerService.java) → Indexes project files
- [`ChromaDBIndexService.storeEmbeddings()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/service/chromadb/ChromaEmbeddingService.java) → Stores embeddings in **ChromaDB**.
- **Retrieval & Augmentation**
- [`SemanticSearchService.search()`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/service/rag/SemanticSearchService.java) → Fetches relevant indexed code.
- [`SemanticSearchReferencesPanel`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/panel/chatresponse/SemanticSearchReferencesPanel.java) → Displays retrieved results.
### 6️⃣ Final Display
- The response is rendered in `ChatResponsePanel` with:
- [`ResponseHeaderPanel`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/panel/chatresponse/ResponseHeaderPanel.java) → Shows metadata (LLM name, execution time).
- [`ResponseDocumentPanel`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/panel/chatresponse/ResponseDocumentPanel.java) → Formats text & code snippets.
- [`MetricExecutionInfoPanel`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/panel/chatresponse/MetricExecutionInfoPanel.java) → Displays token usage and cost.
### Understanding the Flow
Below is a **detailed flow diagram** illustrating this workflow:
---
### How to Get Started
- Start by **exploring [`PromptExecutionController.java`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/controller/PromptExecutionController.java)** to see how prompts are routed.
- Modify [`ChatResponsePanel.java`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/ui/panel/ChatResponsePanel.java) if you want to **enhance response rendering**.
- To **add a new LLM provider**, create a factory under [`chatmodel/cloud/`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/chatmodel/cloud/) or [`chatmodel/local/`](https://github.com/devoxx/DevoxxGenieIDEAPlugin/blob/master/src/main/java/com/devoxx/genie/chatmodel/local/).
Want to contribute? **Submit a PR!** 🚀