PLG integration

.gitignore

@@ -1,3 +1,5 @@
+scratch*
+
 # Python
 __pycache__/
 *.py[cod]
@@ -14,6 +16,7 @@ build/
 # Environment variables
 .env
 .env.local
+.env.prod
 
 # Logs
 logs/

Dockerfile

@@ -5,6 +5,7 @@ WORKDIR /app
 # Install build dependencies in a single layer
 RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
+    vim \
     gcc \
     g++ \
     git \
@@ -18,10 +19,11 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 # Copy only requirements first for better caching
 COPY requirements.txt .
 
-# Use pip cache and install in parallel
-RUN --mount=type=cache,target=/root/.cache/pip \
-    python -m pip install --upgrade pip setuptools wheel && \
-    pip install -r requirements.txt --user --no-warn-script-location
+# Install to explicit location
+RUN python -m pip install --no-cache-dir --prefix=/install --upgrade pip setuptools wheel && \
+    pip install --no-cache-dir --no-deps --prefix=/install -r requirements.txt
+
+RUN pip install --prefix=/install -r requirements.txt --no-cache-dir
 
 # ============================================
 # Final stage - minimal runtime image
@@ -37,18 +39,15 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy installed packages from builder
-COPY --from=builder /root/.local /root/.local
-
-ENV PATH=/root/.local/bin:$PATH
+COPY --from=builder /install /usr/local
 
 # Create necessary directories
 RUN mkdir -p /app/data /app/logs /root/.cache/clip
 
+RUN ls
+
 # Copy application code (do this last for better caching)
 COPY . .
 
-# Lightweight healthcheck
-HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
-    CMD python -c "import sys; sys.exit(0)" || exit 1
 
-CMD ["python", "app.py"]
+CMD ["python", "app.py"]

Dockerfile.api

@@ -1,4 +1,4 @@
-FROM python:3.13-slim
+FROM python:3.13-slim as builder
 
 WORKDIR /app
 
@@ -7,9 +7,18 @@ RUN apt-get update && apt-get install -y --no-install-recommends curl && rm -rf
 
 # Copy requirements and install dependencies
 COPY api/requirements.txt /app/api/requirements.txt
-RUN --mount=type=cache,target=/root/.cache/pip \
-    python -m pip install --upgrade pip && \
-    pip install -r /app/api/requirements.txt
+RUN python -m pip install --prefix=/install -r --upgrade pip && \
+    pip install --prefix=/install -r /app/api/requirements.txt --no-cache-dir
+
+# ============================================
+# Final stage - minimal runtime image
+# ============================================
+FROM python:3.13-slim
+
+WORKDIR /app
+
+# Copy installed packages from builder
+COPY --from=builder /install /usr/local
 
 # Copy application code
 COPY api/ /app/api/
@@ -18,9 +27,6 @@ COPY utils/ /app/utils/
 # Expose API port
 EXPOSE 8000
 
-# Healthcheck (check if uvicorn is responding)
-HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
-    CMD curl -f http://localhost:8000/ || exit 1
 
 # Run the API
 CMD ["uvicorn", "api.api:app", "--host", "0.0.0.0", "--port", "8000"]

api/api.py

@@ -11,6 +11,7 @@
 import aio_pika
 import json
 import uuid
+from dotenv import load_dotenv
 
 from dotenv import load_dotenv
 import os
@@ -26,13 +27,23 @@
 )
 logger = logging.getLogger(__name__)
 
+load_dotenv()
+
 # RabbitMQ Configuration
 RABBITMQ_HOST = os.getenv("RABBITMQ_HOST", "localhost")
 RABBITMQ_PORT = os.getenv("RABBITMQ_PORT", "5672")
 RABBITMQ_VHOST = os.getenv("RABBITMQ_VHOST", "/")
 RABBITMQ_USER = os.getenv("RABBITMQ_USER", "admin")
 RABBITMQ_PASS = os.getenv("RABBITMQ_PASS", "admin123")
 
+#PRINT THE RABBITMQ CONFIG FOR DEBUGGING
+# logger.info("###################")
+# logger.info(f"RABBITMQ_HOST={RABBITMQ_HOST}")
+# logger.info(f"RABBITMQ_PORT={RABBITMQ_PORT}")
+# logger.info(f"RABBITMQ_VHOST={RABBITMQ_VHOST}")
+# logger.info(f"RABBITMQ_USER={RABBITMQ_USER}")
+# logger.info("###################")
+
 SUBMISSION_QUEUE = os.getenv("SUBMISSION_QUEUE", "plagiarism_submissions")
 FEEDBACK_QUEUE = os.getenv("FEEDBACK_QUEUE", "plagiarism_feedback")
 

app.py

@@ -30,6 +30,10 @@ def validate_configuration():
     ]
 
     missing = [var for var in required_env_vars if not os.getenv(var)]
+    #print the required env vars and their values for debugging
+    # for var in required_env_vars:
+    #     logger.info("###################")
+    #     logger.info(f"{var}={os.getenv(var)}")
     if missing:
         logger.error(f"Missing required environment variables: {missing}")
         raise ValueError(f"Missing required environment variables: {missing}")

config/config.py

@@ -93,7 +93,7 @@ class DetectionConfig(BaseSettings):
 
     exact_dup_threshold: float = Field(default=0.95, env="EXACT_DUPLICATE_THRESHOLD")
     near_dup_threshold: float = Field(default=0.90, env="NEAR_DUPLICATE_THRESHOLD")
-    semantic_threshold: float = Field(default=0.80, env="SEMANTIC_MATCH_THRESHOLD")
+    semantic_threshold: float = Field(default=0.70, env="SEMANTIC_MATCH_THRESHOLD")
 
     # Hash matching thresholds (Hamming distance, 0-64 bits)
     hash_threshold: int = Field(default=8, env="HASH_MATCH_THRESHOLD")

database/db_manager.py

@@ -67,6 +67,9 @@ async def init_pool(self):
         db_name = os.getenv("POSTGRES_DB") or os.getenv("DB_NAME")
         db_host = os.getenv("POSTGRES_HOST") or os.getenv("DB_HOST", "localhost")
         db_port = int(os.getenv("POSTGRES_PORT") or os.getenv("DB_PORT", "5432"))
+        # db_port = 5435  # TEMP OVERRIDE FOR TESTING
+
+
 
         if not all([db_user, db_password, db_name]):
             raise ValueError("Missing required database environment variables")
@@ -511,10 +514,10 @@ async def fetch_reference_images_by_id(self, reference_id):
             raise RuntimeError("Database pool not initialized")
 
         try:
-            image_path = await self._fetch(
+            image_path = await self._fetchval(
                 """
                     SELECT image_path 
-                    FROM reference_images where id = $1;
+                    FROM reference_images where reference_id = $1;
                     """,
                 reference_id,
             )

database/init.sql

@@ -72,12 +72,12 @@ USING hnsw (clip_embedding vector_ip_ops);
 -- Reference images corpus
 CREATE TABLE IF NOT EXISTS reference_images (
     id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
-    reference_id VARCHAR(100) UNIQUE NOT NULL,
+    reference_id VARCHAR(200) UNIQUE NOT NULL, -- will be used as assignment id when fetching references from assignments
     image_path TEXT NOT NULL,
     phash VARCHAR(64) NOT NULL,
     dhash VARCHAR(64) NOT NULL,
     ahash VARCHAR(64) NOT NULL,
-    category VARCHAR(100),
+    category VARCHAR(200),
     description TEXT,
     source VARCHAR(200),
     faiss_index_position INTEGER,

docker-compose-prod.yml

@@ -1,39 +1,109 @@
 version: '3.8'
 
 services:
+  # ===================================
+  # POSTGRESQL - Database
+  # ===================================
+  postgres:
+    image: pgvector/pgvector:pg16
+    container_name: plg-postgres
+    ports:
+      - "5432:5432"
+    environment:
+      POSTGRES_DB: ${POSTGRES_DB}
+      POSTGRES_USER: ${POSTGRES_USER}
+      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
+      POSTGRES_INITDB_ARGS: "-E UTF8"
+      POSTGRES_MAX_CONNECTIONS: 20
+      PGDATA: /var/lib/postgresql/data/pgdata
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+      - ./database/init.sql:/docker-entrypoint-initdb.d/init.sql
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U $$POSTGRES_USER -d $$POSTGRES_DB"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+    deploy:
+      resources:
+        limits:
+          cpus: '0.5'
+          memory: 512M
+        reservations:
+          cpus: '0.25'
+          memory: 256M
+    networks:
+      - plg-network
+    restart: unless-stopped
+
   # ===================================
   # PLAGIARISM CHECKER SERVICE
   # ===================================
   plagiarism-checker:
     build:
       context: .
       dockerfile: Dockerfile
-    container_name: mentorme-plagiarism-checker
+    container_name: plg-checker
     env_file:
       - .env
     volumes:
       - ./data:/app/data
       - ./logs:/app/logs
     depends_on:
-      rabbitmq:
+      postgres:
         condition: service_healthy
+    deploy:
+      resources:
+        limits:
+          cpus: '8.0'  # Increased from 4.0 - allows up to 8 CPU cores
+          memory: 8G
+        reservations:
+          cpus: '2'    # Increased from 1 - guarantees 2 cores minimum
+          memory: 2G
+    restart: unless-stopped
+    networks:
+      - plg-network
+
+  # ===================================
+  # API SERVICE
+  # ===================================
+  api:
+    build:
+      context: .
+      dockerfile: Dockerfile.api
+    container_name: plg-api
+    env_file:
+      - .env
+    volumes:
+      - ./data:/app/data
+      - ./logs:/app/logs
+    depends_on:
       postgres:
         condition: service_healthy
     deploy:
       resources:
         limits:
-          cpus: '1.0'
-          memory: 4G
+          cpus: '8.0'  # Increased from 4.0 - allows up to 8 CPU cores
+          memory: 8G
         reservations:
-          cpus: '0.5'
+          cpus: '2'    # Increased from 1 - guarantees 2 cores minimum
           memory: 2G
     restart: unless-stopped
     networks:
-      - mentorme-plagiarism-network
+      - plg-network
+
+
+# ===================================
+# VOLUMES
+# ===================================
+volumes:
+  postgres_data:
+    driver: local
 
 # ===================================
 # NETWORKS
 # ===================================
 networks:
-  mentorme-plagiarism-network:
+  plg-network:
     driver: bridge

docs/DOCUMENTATION.md

@@ -776,11 +776,11 @@ asyncio.run(test())
 #### Build Docker Image
 ```bash
 # Standard build (model downloaded on first run)
-docker build -t mentorme-plagiarism:latest .
+docker build -t plg:latest .
 
 # With HuggingFace token for model prefetch during build (optional)
 # This pre-downloads the CLIP model into the Docker image
-docker build -t mentorme-plagiarism:latest \
+docker build -t plg:latest \
   --build-arg HUGGINGFACE_HUB_TOKEN=your_token_here .
 
 # Note: HuggingFace token is optional - public models can be downloaded without authentication
@@ -804,7 +804,7 @@ docker-compose down
 # docker-compose.yml snippet
 services:
   worker:
-    image: mentorme-plagiarism:latest
+    image: plg:latest
     environment:
       - POSTGRES_HOST=postgres
       - RABBITMQ_HOST=rabbitmq