Update Docs

Author: SecretSettler

.github/workflows/deploy.yml

@@ -0,0 +1,53 @@
+name: Deploy to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  build:
+    name: Build
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: npm
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Build website
+        run: npm run build
+
+      - name: Upload Build Artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: build
+
+  deploy:
+    name: Deploy
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.gitignore

@@ -0,0 +1,13 @@
+# Dependencies
+node_modules/
+
+# Build output
+build/
+.docusaurus/
+
+# Environment
+.env
+.env.local
+
+# OS
+.DS_Store

babel.config.js

@@ -0,0 +1,3 @@
+module.exports = {
+  presets: [require.resolve('@docusaurus/core/lib/babel/preset')],
+};

docs/getting_started/installation.md

@@ -0,0 +1,73 @@
+---
+id: installation
+title: Installation
+sidebar_label: Installation
+---
+
+# Installation
+
+This guide covers installing ContextPilot and its dependencies.
+
+## Requirements
+
+- Python >= 3.10
+- CUDA 12.x (for GPU-accelerated distance computation)
+- An inference engine: [SGLang](https://github.com/sgl-project/sglang), [vLLM](https://github.com/vllm-project/vllm), or any OpenAI-compatible server
+
+## Install ContextPilot
+
+```bash
+pip install contextpilot
+```
+
+Or from source (development):
+```bash
+git clone https://github.com/EfficientContext/ContextPilot.git
+cd ContextPilot
+pip install -e .
+python -m contextpilot.install_hook   # one-time: enables automatic SGLang + vLLM hooks
+```
+
+This installs the core dependencies:
+
+| Package | Purpose |
+|---------|--------|
+| `fastapi[all]` | HTTP server |
+| `aiohttp` | Async inference engine proxy |
+| `scipy` | Hierarchical clustering |
+| `transformers` | Tokenizer / chat templates |
+| `cupy-cuda12x` | GPU distance computation |
+| `elasticsearch` | BM25 retriever (optional) |
+| `datasets` | Loading benchmark datasets |
+
+## Install an Inference Engine
+
+**SGLang:**
+```bash
+pip install "sglang>=0.5"
+```
+
+**vLLM:**
+```bash
+pip install vllm
+```
+
+Both engines are supported via zero-patch runtime hooks — just set `CONTEXTPILOT_INDEX_URL` when launching. See [Online Usage Guide](../guides/online_usage#inference-engine-integration).
+
+## Distributed Setup
+
+If the ContextPilot index server and the inference engine run in **separate Python environments** (e.g., different virtualenvs or containers), the engine environment won't have the `contextpilot` package. Use the standalone hook instead:
+
+```bash
+# In the engine's Python environment (one command, no clone needed):
+pip install requests
+curl -sL https://raw.githubusercontent.com/EfficientContext/ContextPilot/main/contextpilot/install_standalone.py | python -
+```
+
+The installer downloads the hook from GitHub and installs it into site-packages. No `contextpilot` clone or install needed — just `requests` as a runtime dependency.
+
+## Verify Installation
+
+```bash
+python -c "import contextpilot; print('ContextPilot', contextpilot.__version__)"
+```