Initial commit: Project foundation

- Backend: Go API server with Gin framework
- Frontend: React setup (placeholder)
- ML Service: Python FastAPI skeleton
- Docker Compose: Full stack configuration
- Database: PostgreSQL schema with migrations
- Documentation: Implementation plan and README

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

ml-service/.gitignore

@@ -0,0 +1,26 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+*.egg-info/
+dist/
+build/
+
+# Virtual environment
+venv/
+env/
+ENV/
+
+# ML models
+models/*.pkl
+models/*.joblib
+!models/.gitkeep
+
+# Jupyter
+.ipynb_checkpoints/
+
+# Cache
+.pytest_cache/
+.mypy_cache/

ml-service/Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    gcc \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements file
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY app/ ./app/
+
+# Create models directory
+RUN mkdir -p models
+
+# Expose port
+EXPOSE 8000
+
+# Run the application
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

ml-service/app/__init__.py

@@ -0,0 +1 @@
+# ML Service Package

ml-service/app/main.py

@@ -0,0 +1,122 @@
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from typing import List, Dict, Any, Optional
+import logging
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+app = FastAPI(
+    title="VictoriaLogs ML Service",
+    description="Machine Learning service for anomaly detection in logs",
+    version="1.0.0"
+)
+
+# CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Request/Response models
+class TrainRequest(BaseModel):
+    model_name: str
+    query: str
+    start_time: str
+    end_time: str
+    contamination: float = 0.1
+
+class DetectRequest(BaseModel):
+    model_name: str
+    logs: List[Dict[str, Any]]
+
+class TrainResponse(BaseModel):
+    status: str
+    model_name: str
+    model_path: str
+    message: str
+
+class DetectResponse(BaseModel):
+    status: str
+    anomalies: List[Dict[str, Any]]
+    anomaly_count: int
+
+@app.get("/")
+async def root():
+    return {
+        "service": "VictoriaLogs ML Service",
+        "status": "running",
+        "version": "1.0.0"
+    }
+
+@app.get("/health")
+async def health_check():
+    return {"status": "healthy"}
+
+@app.post("/api/ml/train", response_model=TrainResponse)
+async def train_model(request: TrainRequest):
+    """
+    Train an anomaly detection model on historical logs
+    """
+    logger.info(f"Training model: {request.model_name}")
+
+    # TODO: Implement model training
+    # 1. Fetch logs from VictoriaLogs
+    # 2. Extract features
+    # 3. Train Isolation Forest model
+    # 4. Save model to disk
+
+    return TrainResponse(
+        status="success",
+        model_name=request.model_name,
+        model_path=f"/app/models/{request.model_name}.pkl",
+        message="Model training not yet implemented"
+    )
+
+@app.post("/api/ml/detect", response_model=DetectResponse)
+async def detect_anomalies(request: DetectRequest):
+    """
+    Detect anomalies in a batch of logs using a trained model
+    """
+    logger.info(f"Detecting anomalies with model: {request.model_name}")
+
+    # TODO: Implement anomaly detection
+    # 1. Load trained model
+    # 2. Extract features from logs
+    # 3. Predict anomalies
+    # 4. Return flagged logs with scores
+
+    return DetectResponse(
+        status="success",
+        anomalies=[],
+        anomaly_count=0
+    )
+
+@app.get("/api/ml/models")
+async def list_models():
+    """
+    List all trained models
+    """
+    # TODO: List model files from disk
+    return {
+        "models": [],
+        "count": 0
+    }
+
+@app.delete("/api/ml/models/{model_name}")
+async def delete_model(model_name: str):
+    """
+    Delete a trained model
+    """
+    logger.info(f"Deleting model: {model_name}")
+
+    # TODO: Delete model file
+    return {
+        "status": "success",
+        "message": f"Model {model_name} deleted"
+    }

ml-service/requirements.txt

@@ -0,0 +1,9 @@
+fastapi==0.109.0
+uvicorn[standard]==0.27.0
+pydantic==2.5.3
+scikit-learn==1.4.0
+pandas==2.2.0
+numpy==1.26.3
+httpx==0.26.0
+python-multipart==0.0.6
+joblib==1.3.2