IndexFoundry MCP

# Deployment Guide for Mnehmos Screen Vision Knowledge Base --- ## Quick Start: Local Development ### Step 1: Install Dependencies ```bash cd C:\Users\mnehm\AppData\Roaming\Roo-Code\MCP\IndexFoundry\projects\mnehmos-screen-vision npm install ``` ### Step 2: Configure Environment Add your OpenAI API key to the `.env` file: ```bash # Open .env and add your key: OPENAI_API_KEY=sk-proj-your-key-here ``` ### Step 3: Start the Server ```bash npm run dev ``` You should see: ``` Loaded X sources Loaded Y chunks, Y vectors HTTP server listening on port 8765 ``` ### Step 4: Test the Frontend 1. Copy `frontend/local.config.js.example` to `frontend/local.config.js` 2. Open `frontend/index.html` in your browser 3. The status should show "Ready" (green indicator) 4. Ask a question to verify the chat works! ### Step 5: Verify API Endpoints ```bash # Health check curl http://localhost:8765/health # Search test curl -X POST http://localhost:8765/search \ -H "Content-Type: application/json" \ -d '{"query": "test", "mode": "keyword", "top_k": 5}' ``` --- ## Production Deployment ### Prerequisites | Requirement | Where to Get It | |-------------|-----------------| | GitHub Account | [github.com](https://github.com) | | Railway Account | [railway.app](https://railway.app) | | OpenAI API Key | [platform.openai.com/api-keys](https://platform.openai.com/api-keys) | --- ### Step 1: Push to GitHub ```bash cd C:\Users\mnehm\AppData\Roaming\Roo-Code\MCP\IndexFoundry\projects\mnehmos-screen-vision git init git add . git commit -m "Initial commit" gh repo create mnehmos-screen-vision --public --push ``` Or manually create a repo at [github.com/new](https://github.com/new) and push. --- ### Step 2: Deploy to Railway 1. Go to [railway.app/dashboard](https://railway.app/dashboard) 2. Click **"New Project"** → **"Deploy from GitHub repo"** 3. Select your `mnehmos-screen-vision` repository 4. Railway will auto-detect the Dockerfile --- ### Step 3: Configure Environment Variables In Railway dashboard → your service → **"Variables"** tab: | Variable | Value | Required | |----------|-------|----------| | `OPENAI_API_KEY` | `sk-proj-...` | ✅ Yes | | `PORT` | `8765` | ❌ Auto-set | | `OPENAI_MODEL` | `gpt-5-nano-2025-08-07` | ❌ Optional | > ⚠️ **Never commit API keys to Git!** --- ### Step 4: Get Your Public URL 1. In Railway → **"Settings"** → **"Networking"** 2. Click **"Generate Domain"** 3. Copy your URL: `https://mnehmos-screen-vision-production.up.railway.app` --- ### Step 5: Verify Deployment #### Health Check ```bash curl https://YOUR-APP.railway.app/health ``` #### Test Search ```bash curl -X POST https://YOUR-APP.railway.app/search \ -H "Content-Type: application/json" \ -d '{"query": "test", "mode": "keyword", "top_k": 5}' ``` #### Test Chat ```bash curl -X POST https://YOUR-APP.railway.app/chat \ -H "Content-Type: application/json" \ -d '{"question": "What is this about?"}' ``` --- ## API Reference | Endpoint | Method | Description | |----------|--------|-------------| | `/health` | GET | Health check | | `/stats` | GET | Index statistics | | `/sources` | GET | List sources | | `/search` | POST | RAG search | | `/chat` | POST | Chat with streaming | | `/chunks/:id` | GET | Get chunk by ID | --- ## Troubleshooting ### API Key Not Loaded If you get "OPENAI_API_KEY not configured": - Ensure you added your key to `.env` (not `.env.example`) - The `.env` file should NOT be committed to git ### Port Already in Use If port 8765 is busy: - Change PORT in `.env` to another port (e.g., 3001) - Update `frontend/local.config.js` to match ### Build Failed - Check build logs in Railway dashboard - Ensure `npm run build` works locally ### Health Check Failed - Verify `OPENAI_API_KEY` is set - Check runtime logs for errors ### Chat Returns 500 - Check OpenAI API quota - Verify API key is valid --- ## Frontend Deployment The project includes a ready-to-use chat interface in the `frontend/` directory. ### Option 1: GitHub Pages (Recommended for Static) 1. Push your repo to GitHub 2. Go to **Settings** → **Pages** 3. Set Source to **Deploy from a branch** 4. Select **main** branch and **`/frontend`** folder 5. Your chat UI will be live at `https://USERNAME.github.io/REPO-NAME/` ### Option 2: Serve from Railway (Same Origin) The frontend is automatically served from the root path when deployed. ### Option 3: Any Static Host Upload the contents of `frontend/` to: - Netlify - Vercel - AWS S3 + CloudFront - Any web server --- *Generated by IndexFoundry*