Basic ranker Implementation

.env.example

@@ -0,0 +1,3 @@
+DB_USER=admin
+DB_PASS=change_me_in_production
+DB_NAME=search_engine

.github/workflows/ci.yml

@@ -127,8 +127,15 @@ jobs:
         python-version: '3.9'
         cache: 'pip'
 
+    - name: Install System Dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y librocksdb-dev zlib1g-dev libbz2-dev liblz4-dev libsnappy-dev libzstd-dev
+
     - name: Install Dependencies
-      run: pip install -r requirements.txt
+      run: |
+        pip install "Cython<3.0" setuptools wheel
+        pip install --no-build-isolation -r requirements.txt
 
     - name: Syntax Check
       run: python -m compileall .

API/config/routes.rb

@@ -8,5 +8,5 @@
   get "/search", to: "search#index"
 
   # Defines the root path route ("/")
-  # root "posts#index"
+  root "search#index"
 end

README.md

@@ -1 +1,24 @@
 ![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/Digvijay-x1/Search-Engine?utm_source=oss&utm_medium=github&utm_campaign=Digvijay-x1%2FSearch-Engine&labelColor=171717&color=FF570A&link=https%3A%2F%2Fcoderabbit.ai&label=CodeRabbit+Reviews)
+
+## Setup
+
+### Environment Variables
+
+This project uses environment variables for configuration, including database credentials.
+
+1.  Copy the example environment file:
+    ```bash
+    cp .env.example .env
+    ```
+2.  Edit `.env` and set your own secure passwords and configuration:
+    ```ini
+    DB_USER=admin
+    DB_PASS=your_secure_password
+    DB_NAME=search_engine
+    ```
+
+### Running with Docker
+
+```bash
+docker-compose up --build
+```

cpp/indexer/Dockerfile

@@ -1,4 +1,4 @@
-FROM ubuntu:latest
+FROM ubuntu:22.04
 
 RUN apt-get update && apt-get install -y \
     build-essential \

docker-compose.yml

@@ -13,9 +13,9 @@ services:
   postgres_service:
     image: postgres:17.2-alpine3.21
     environment:
-      POSTGRES_USER: admin
-      POSTGRES_PASSWORD: password123
-      POSTGRES_DB: search_engine
+      POSTGRES_USER: ${DB_USER}
+      POSTGRES_PASSWORD: ${DB_PASS}
+      POSTGRES_DB: ${DB_NAME}
     volumes:
       - ./data/init.sql:/docker-entrypoint-initdb.d/init.sql # Runs on first startup
       - pg_data:/var/lib/postgresql/data # Persistence
@@ -29,8 +29,13 @@ services:
       - "5000:5000"
     volumes:
       - ./python/ranker:/app # Hot-reloading for Python
+      - ./data/crawled_pages:/shared_data
     environment:
       - FLASK_ENV=development
+      - DB_HOST=postgres_service
+      - DB_NAME=${DB_NAME}
+      - DB_USER=${DB_USER}
+      - DB_PASS=${DB_PASS}
     networks:
       - search_net
 
@@ -65,9 +70,9 @@ services:
       - ./data/crawled_pages:/shared_data
     environment:
       - DB_HOST=postgres_service
-      - DB_NAME=search_engine
-      - DB_USER=admin
-      - DB_PASS=password123
+      - DB_NAME=${DB_NAME}
+      - DB_USER=${DB_USER}
+      - DB_PASS=${DB_PASS}
     depends_on:
       - redis_service
       - postgres_service

python/ranker/Dockerfile

@@ -1,6 +1,28 @@
-FROM python:3.9-slim
+FROM ubuntu:22.04
+
+# Install system dependencies
+# python3-dev is needed for headers
+RUN apt-get update && apt-get install -y \
+    python3 \
+    python3-pip \
+    python3-dev \
+    git \
+    build-essential \
+    librocksdb-dev \
+    libpq-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    liblz4-dev \
+    libsnappy-dev \
+    libzstd-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create a symlink for python if needed, though python3 is standard
+RUN ln -s /usr/bin/python3 /usr/bin/python
+
 WORKDIR /app
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip3 install --no-cache-dir "Cython<3"
+RUN pip3 install --no-cache-dir -r requirements.txt
 COPY . .
-CMD ["python", "app.py"]
+CMD ["python3", "app.py"]

python/ranker/app.py

@@ -1,23 +1,48 @@
 from flask import Flask, jsonify, request
+from engine import Ranker
+import time
+import atexit
 
 app = Flask(__name__)
 
-# Mock Data (The "Database")
-MOCK_INDEX = {
-    "computer": [{"id": 1, "title": "History of Computers"}, {"id": 2, "title": "Computer Science 101"}],
-    "cats": [{"id": 3, "title": "Funny Cats"}, {"id": 4, "title": "Cat Care"}]
-}
+# Initialize Ranker (Global Singleton)
+ranker = None
+try:
+    ranker = Ranker()
+    atexit.register(ranker.close)
+except Exception as e:
+    print(f"Failed to initialize Ranker: {e}")
 
 @app.route('/health')
 def health():
-    return jsonify({"status": "healthy", "service": "ranker"})
+    status = "healthy" if ranker else "degraded"
+    return jsonify({"status": status, "service": "ranker"})
 
 @app.route('/search')
 def search():
+    global ranker
+    if not ranker:
+        # Fallback for dev/restart if before_first_request didn't fire or failed
+        try:
+            ranker = Ranker()
+        except Exception as e:
+            return jsonify({"error": f"Ranker not initialized: {str(e)}"}), 500
+
     query = request.args.get('q', '').lower()
     print(f"Received query: {query}")
-    results = MOCK_INDEX.get(query, [])
-    return jsonify({"query": query, "results": results})
+
+    start_time = time.time()
+    results = ranker.search(query)
+    duration_ms = (time.time() - start_time) * 1000
+
+    return jsonify({
+        "query": query, 
+        "results": results,
+        "meta": {
+            "count": len(results),
+            "latency_ms": round(duration_ms, 2)
+        }
+    })
 
 if __name__ == '__main__':
     # host='0.0.0.0' is CRITICAL for Docker networking