|
|
<!doctype html>
|
|
|
<html lang="en">
|
|
|
|
|
|
<head>
|
|
|
<meta charset="utf-8" />
|
|
|
<meta name="viewport" content="width=device-width" />
|
|
|
<link rel="stylesheet" href="style.css" />
|
|
|
<title>CodeMind - AI-Powered Development Assistant</title>
|
|
|
</head>
|
|
|
|
|
|
<body>
|
|
|
|
|
|
<header>
|
|
|
<div class="container">
|
|
|
<nav>
|
|
|
<div class="logo">
|
|
|
<span class="logo-icon">🔧</span> CodeMind
|
|
|
</div>
|
|
|
<ul class="nav-links">
|
|
|
<li><a href="#features">Features</a></li>
|
|
|
<li><a href="#why">Why CodeMind</a></li>
|
|
|
<li><a href="#how">How It Works</a></li>
|
|
|
<li><a href="#usage">Usage</a></li>
|
|
|
<li><a href="#setup">Setup</a></li>
|
|
|
</ul>
|
|
|
</nav>
|
|
|
</div>
|
|
|
</header>
|
|
|
|
|
|
|
|
|
<section class="hero">
|
|
|
<div class="container">
|
|
|
<h1>AI-Powered Development Assistant</h1>
|
|
|
<p>CodeMind is an AI-powered development assistant that runs entirely on your local machine for intelligent
|
|
|
document analysis and commit message generation.</p>
|
|
|
<a href="#setup" class="btn">Get Started</a>
|
|
|
<a href="#features" class="btn btn-outline">Learn More</a>
|
|
|
</div>
|
|
|
</section>
|
|
|
|
|
|
|
|
|
<section id="features" class="features">
|
|
|
<div class="container">
|
|
|
<h2>Features</h2>
|
|
|
<div class="features-grid">
|
|
|
<div class="feature-card">
|
|
|
<div class="feature-icon">📄</div>
|
|
|
<h3>Document Embedding</h3>
|
|
|
<p>Using EmbeddingGemma-300m to create semantic representations of your documentation and code.</p>
|
|
|
</div>
|
|
|
<div class="feature-card">
|
|
|
<div class="feature-icon">🔍</div>
|
|
|
<h3>Semantic Search</h3>
|
|
|
<p>Using FAISS for vector similarity search to find relevant content based on meaning, not just
|
|
|
keywords.</p>
|
|
|
</div>
|
|
|
<div class="feature-card">
|
|
|
<div class="feature-icon">💬</div>
|
|
|
<h3>Commit Message Generation</h3>
|
|
|
<p>Automatically generate descriptive commit messages based on your changes using Phi-2 model.</p>
|
|
|
</div>
|
|
|
<div class="feature-card">
|
|
|
<div class="feature-icon">🤖</div>
|
|
|
<h3>Retrieval-Augmented Generation</h3>
|
|
|
<p>Answers questions using your indexed document context for accurate, relevant responses.</p>
|
|
|
</div>
|
|
|
<div class="feature-card">
|
|
|
<div class="feature-icon">💻</div>
|
|
|
<h3>Local Processing</h3>
|
|
|
<p>All AI processing happens on your machine with no data sent to cloud services.</p>
|
|
|
</div>
|
|
|
<div class="feature-card">
|
|
|
<div class="feature-icon">⚙️</div>
|
|
|
<h3>Flexible Configuration</h3>
|
|
|
<p>Customize models and parameters to suit your specific needs and preferences.</p>
|
|
|
</div>
|
|
|
</div>
|
|
|
</div>
|
|
|
</section>
|
|
|
|
|
|
|
|
|
<section id="why" class="why">
|
|
|
<div class="container">
|
|
|
<h2>Why CodeMind?</h2>
|
|
|
<div class="why-content">
|
|
|
<p>CodeMind brings together <b class="b">document semantic search</b>, <b class="b">retrieval-augmented
|
|
|
Q&A</b>, and
|
|
|
<b class="b">AI-powered commit
|
|
|
message generation</b> to help you work faster and smarter by leveraging your own project
|
|
|
context.
|
|
|
</p>
|
|
|
<br>
|
|
|
|
|
|
<h3 class="b">Efficient Knowledge Retrieval</h3>
|
|
|
<p>Makes searching and querying documentation more powerful by using semantic embeddings rather than
|
|
|
keyword search.</p><br>
|
|
|
|
|
|
<h3 class="b">Smarter Git Workflow</h3>
|
|
|
<p>Automates the creation of meaningful commit messages by analyzing git diffs and using an LLM to
|
|
|
summarize changes.</p><br>
|
|
|
|
|
|
<h3 class="b">AI-Powered Documentation</h3>
|
|
|
<p>Enables you to ask questions about your project, using your own docs/context rather than just generic
|
|
|
answers.</p>
|
|
|
</div>
|
|
|
</div>
|
|
|
</section>
|
|
|
|
|
|
|
|
|
<section id="how" class="how">
|
|
|
<div class="container">
|
|
|
<h2>How It Works</h2>
|
|
|
<div class="how-steps">
|
|
|
<div class="step">
|
|
|
<div class="step-number">1</div>
|
|
|
<div class="step-content">
|
|
|
<h3>Document Indexing</h3>
|
|
|
<p>The app uses EmbeddingGemma-300m via sentence-transformers to embed documents. Embeddings are
|
|
|
normalized and stored in a FAISS vector index for efficient similarity search. Metadata
|
|
|
(document text and filenames) are stored alongside the index.</p>
|
|
|
</div>
|
|
|
</div>
|
|
|
<div class="step">
|
|
|
<div class="step-number">2</div>
|
|
|
<div class="step-content">
|
|
|
<h3>Semantic Search</h3>
|
|
|
<p>When you search, your query is embedded using the same embedding model. FAISS searches for
|
|
|
the most similar documents based on cosine similarity. Results are filtered by a similarity
|
|
|
threshold and returned with scores.</p>
|
|
|
</div>
|
|
|
</div>
|
|
|
<div class="step">
|
|
|
<div class="step-number">3</div>
|
|
|
<div class="step-content">
|
|
|
<h3>Retrieval-Augmented Generation (RAG)</h3>
|
|
|
<p>When you ask a question, the system retrieves relevant docs (via semantic search). The
|
|
|
retrieved context is fed to the Phi-2 LLM, which generates an answer using both your
|
|
|
question and the context.</p>
|
|
|
</div>
|
|
|
</div>
|
|
|
<div class="step">
|
|
|
<div class="step-number">4</div>
|
|
|
<div class="step-content">
|
|
|
<h3>Commit Message Generation</h3>
|
|
|
<p>Analyzes your staged git changes (via a diff analyzer). Summarizes changes and sends them to
|
|
|
the Phi-2 LLM, which generates a commit message aligned to your config (tone, style,
|
|
|
length).</p>
|
|
|
</div>
|
|
|
</div>
|
|
|
</div>
|
|
|
</div>
|
|
|
</section>
|
|
|
|
|
|
|
|
|
<section id="usage" class="usage">
|
|
|
<div class="container">
|
|
|
<h2>Usage Examples</h2>
|
|
|
|
|
|
<h3>Index Your Documentation</h3>
|
|
|
<div class="code-block">
|
|
|
<span class="code-comment"># Index documents in the docs directory</span><br>
|
|
|
python cli.py init ./docs/
|
|
|
</div>
|
|
|
|
|
|
<h3>Semantic Search</h3>
|
|
|
<div class="code-block">
|
|
|
<span class="code-comment"># Search for relevant documentation</span><br>
|
|
|
python cli.py search "how to configure the model"
|
|
|
</div>
|
|
|
|
|
|
<h3>Ask Questions (RAG)</h3>
|
|
|
<div class="code-block">
|
|
|
<span class="code-comment"># Ask questions about your project</span><br>
|
|
|
python cli.py ask "What are the configuration options?"
|
|
|
</div>
|
|
|
|
|
|
<h3>Generate Commit Messages</h3>
|
|
|
<div class="code-block">
|
|
|
<span class="code-comment"># Preview a generated commit message</span><br>
|
|
|
python cli.py commit --preview<br><br>
|
|
|
|
|
|
<span class="code-comment"># Generate and apply commit message</span><br>
|
|
|
python cli.py commit --apply
|
|
|
</div>
|
|
|
</div>
|
|
|
</section>
|
|
|
|
|
|
|
|
|
<section id="setup" class="setup">
|
|
|
<div class="container">
|
|
|
<h2>Setup & Installation</h2>
|
|
|
|
|
|
<div class="setup-cards">
|
|
|
<div class="setup-card">
|
|
|
<h3>Prerequisites</h3>
|
|
|
<ul>
|
|
|
<li>Python 3.8 or higher</li>
|
|
|
<li>8GB+ RAM recommended</li>
|
|
|
<li>4GB+ disk space for model files</li>
|
|
|
<li>Git for repository cloning</li>
|
|
|
</ul>
|
|
|
</div>
|
|
|
|
|
|
<div class="setup-card">
|
|
|
<h3>Installation</h3>
|
|
|
<div class="code-block">
|
|
|
<span class="code-comment"># Clone the repository</span><br>
|
|
|
git clone https://github.com/devjas1/codemind.git<br>
|
|
|
cd codemind<br><br>
|
|
|
|
|
|
<span class="code-comment"># Create virtual environment</span><br>
|
|
|
python -m venv venv<br><br>
|
|
|
|
|
|
<span class="code-comment"># Activate on macOS/Linux</span><br>
|
|
|
source venv/bin/activate<br><br>
|
|
|
|
|
|
<span class="code-comment"># Install dependencies</span><br>
|
|
|
pip install -r requirements.txt
|
|
|
</div>
|
|
|
</div>
|
|
|
|
|
|
<div class="setup-card">
|
|
|
<h3>Model Setup</h3>
|
|
|
<p>Download these models:</p>
|
|
|
<ul>
|
|
|
<li>Phi-2 Model for commit message generation</li>
|
|
|
<li>EmbeddingGemma-300m for document embedding</li>
|
|
|
</ul>
|
|
|
<p>Place them in the models/ directory as specified in the configuration.</p>
|
|
|
</div>
|
|
|
</div>
|
|
|
</div>
|
|
|
</section>
|
|
|
|
|
|
|
|
|
<section class="faq">
|
|
|
<div class="container">
|
|
|
<h2>Frequently Asked Questions</h2>
|
|
|
|
|
|
<div class="faq-list">
|
|
|
<div class="faq-item">
|
|
|
<div class="faq-question">Can I use different models?</div>
|
|
|
<p>Yes, you can use any GGUF-compatible model for generation and any SentenceTransformers-compatible
|
|
|
model for embeddings. Update the paths in config.yaml accordingly.</p>
|
|
|
</div>
|
|
|
|
|
|
<div class="faq-item">
|
|
|
<div class="faq-question">How much RAM do I need?</div>
|
|
|
<p>For the Phi-2 Q4_0 model, 8GB RAM is recommended. Larger models will require more memory.</p>
|
|
|
</div>
|
|
|
|
|
|
<div class="faq-item">
|
|
|
<div class="faq-question">Is my data sent to the cloud?</div>
|
|
|
<p>No, all processing happens locally on your machine. No code or data is sent to external services.
|
|
|
</p>
|
|
|
</div>
|
|
|
|
|
|
<div class="faq-item">
|
|
|
<div class="faq-question">How often should I re-index my documents?</div>
|
|
|
<p>Re-index whenever your documentation or codebase changes significantly to keep search results
|
|
|
relevant.</p>
|
|
|
</div>
|
|
|
</div>
|
|
|
</div>
|
|
|
</section>
|
|
|
|
|
|
|
|
|
<footer>
|
|
|
<div class="container">
|
|
|
<div class="logo">
|
|
|
<span class="logo-icon">🔧</span> CodeMind
|
|
|
</div>
|
|
|
<p>AI-powered development assistant for your local machine</p>
|
|
|
|
|
|
<ul class="footer-links">
|
|
|
<li><a href="#features">Features</a></li>
|
|
|
<li><a href="#why">Why</a></li>
|
|
|
<li><a href="#how">How It Works</a></li>
|
|
|
<li><a href="#usage">Usage</a></li>
|
|
|
<li><a href="#setup">Setup</a></li>
|
|
|
</ul>
|
|
|
|
|
|
<p>© 2025 CodeMind. All rights reserved.
|
|
|
</p>
|
|
|
</div>
|
|
|
</footer>
|
|
|
</body>
|
|
|
|
|
|
</html> |
