Coralogix Log Analyzer - Professional Edition

A sophisticated, professional tool for analyzing Coralogix logs and detecting failures with intelligent remediation suggestions. This tool provides both basic pattern-based and LLM-driven analysis capabilities.

🚀 Features

🔍 Dual Analysis Modes: Both pattern-based and AI-driven analysis
🤖 LLM Integration: GPT-4 powered intelligent investigation
📊 Rich Reporting: Beautiful console output with detailed analysis
🔧 Professional CLI: Command-line interface with comprehensive options
🔌 MCP Support: Model Context Protocol integration for AI assistants
⚡ Fast & Efficient: Optimized for production use
🛡️ Error Handling: Robust error handling and validation
📈 Extensible: Modular architecture for easy extension

🛠️ Installation

Prerequisites

Python 3.8 or higher
Coralogix API key with DataQuerying permission
OpenAI API key (for LLM-driven analysis)

Install from Source

# Clone the repository
git clone https://github.com/your-org/coralogix-log-analyzer.git
cd coralogix-log-analyzer

# Install dependencies
pip install -r requirements.txt

# Install the package
pip install -e .

Install with pip

pip install coralogix-log-analyzer

🚀 Quick Start

1. Set Environment Variables

export CORALOGIX_API_KEY="test"
export CORALOGIX_TEAM_HOSTNAME="test"
export CORALOGIX_DOMAIN="test"  # or your domain
export CORALOGIX_VERIFY_SSL="false"  # set to "false" for development if SSL issues occur
export OPENAI_API_KEY="test"  # for LLM analysis

2. Basic Analysis

# Analyze logs using pattern-based detection
python main.py analyze "Why is my app failing?" --namespace my-app

# Or use the installed command
coralogix-analyzer analyze "Why is my app failing?" --namespace my-app

3. LLM-Driven Investigation

# Use AI-powered investigation
python main.py investigate "What's causing the performance issues?" --namespace production

# Or use the installed command
coralogix-analyzer investigate "What's causing the performance issues?" --namespace production

4. Health Check

# Check service connectivity
python main.py health

5. MCP Server

# Start MCP server for AI assistant integration
python mcp_server.py

# Or use the installed command
coralogix-mcp

📖 Usage

Command Line Interface

The tool provides a comprehensive CLI with multiple commands:

# Basic pattern-based analysis
coralogix-analyzer analyze [QUERY] [OPTIONS]

# LLM-driven investigation
coralogix-analyzer investigate [QUERY] [OPTIONS]

# Health check
coralogix-analyzer health

# MCP server
coralogix-mcp

# Version information
coralogix-analyzer version

### Analysis Options

```bash
# Basic analysis with options
coralogix-analyzer analyze "Check for errors" \
  --namespace my-app \
  --pod my-pod \
  --hours-back 2 \
  --output results.txt \
  --format json

# LLM investigation with options
coralogix-analyzer investigate "Why is the app slow?" \
  --namespace production \
  --hours-back 4 \
  --max-iterations 10 \
  --output investigation.json \
  --format json

Output Formats

The tool supports multiple output formats:

Text: Human-readable console output (default)
JSON: Structured data for programmatic consumption

# Save results to file
coralogix-analyzer analyze "Check errors" --output results.txt

# Get JSON output
coralogix-analyzer investigate "Analyze failures" --format json --output results.json

⚙️ Configuration

Environment Variables

Variable	Description	Required	Default
`CORALOGIX_API_KEY`	Coralogix API key	Yes	-
`CORALOGIX_TEAM_HOSTNAME`	Team hostname	Yes	-
`CORALOGIX_DOMAIN`	Coralogix domain	No	eu2.coralogix.com
`CORALOGIX_VERIFY_SSL`	SSL certificate verification	No	true
`OPENAI_API_KEY`	OpenAI API key	Yes (for LLM)	-
`LLM_MODEL`	LLM model to use	No	gpt-4.1
`LLM_TEMPERATURE`	LLM temperature	No	0.1
`LLM_MAX_TOKENS`	Max tokens for response	No	1000
`LLM_MAX_ITERATIONS`	Max investigation iterations	No	5
`LOG_LEVEL`	Logging level	No	INFO
`DEBUG`	Enable debug mode	No	false

Configuration File

You can also use a .env file:

# .env
CORALOGIX_API_KEY=your-api-key
CORALOGIX_TEAM_HOSTNAME=your-team
OPENAI_API_KEY=your-openai-key
LLM_MODEL=gpt-4
DEBUG=true

🏗️ Architecture

Project Structure

coralogix-log-analyzer/
├── src/
│   ├── __init__.py
│   ├── config/
│   │   ├── __init__.py
│   │   ├── settings.py
│   │   └── environment.py
│   ├── models/
│   │   ├── __init__.py
│   │   ├── log_entry.py
│   │   ├── failure_pattern.py
│   │   ├── tool_result.py
│   │   └── investigation_result.py
│   ├── core/
│   │   ├── __init__.py
│   │   ├── coralogix_client.py
│   │   ├── llm_client.py
│   │   └── analyzer.py
│   ├── cli/
│   │   ├── __init__.py
│   │   └── main.py
│   └── mcp/
│       ├── __init__.py
│       ├── server.py
│       └── tools.py
├── tests/
├── docs/
├── main.py
├── mcp_server.py
├── requirements.txt
├── pyproject.toml
├── README.md
└── MCP_INTEGRATION.md

Core Components

1. Configuration Management (`src/config/`)

Settings: Centralized configuration with validation
Environment: Environment variable loading and validation

2. Data Models (`src/models/`)

LogEntry: Represents individual log entries
FailurePattern: Detected failure patterns with metadata
ToolResult: Results from tool executions
InvestigationResult: Complete investigation outcomes

3. Core Logic (`src/core/`)

CoralogixClient: Professional API client for Coralogix
LLMClient: OpenAI integration for AI-driven analysis
BasicAnalyzer: Pattern-based analysis engine
LLMAnalyzer: LLM-driven investigation engine

4. CLI Interface (`src/cli/`)

Main CLI: Professional command-line interface
Commands: Analyze, investigate, health check, version

5. MCP Integration (`src/mcp/`)

MCP Server: Model Context Protocol server for AI assistant integration
Tools: Standardized tools for log analysis and investigation

🔍 Analysis Modes

1. Basic Pattern-Based Analysis

Fast, predictable analysis using predefined patterns:

from src.core.analyzer import BasicAnalyzer
from src.core.coralogix_client import CoralogixClient

# Initialize
client = CoralogixClient(config)
analyzer = BasicAnalyzer(client, settings)

# Analyze
result = analyzer.analyze("Check for errors", "my-namespace")

Features:

⚡ Fast execution (milliseconds)
🎯 Predictable results
💰 Low cost (no LLM calls)
🔧 Simple to understand and modify

2. LLM-Driven Investigation

Intelligent, adaptive analysis using AI:

from src.core.analyzer import LLMAnalyzer
from src.core.llm_client import LLMClient

# Initialize
llm_client = LLMClient(config)
analyzer = LLMAnalyzer(client, llm_client, settings)

# Investigate
result = analyzer.investigate("Why is my app failing?", "my-namespace")

Features:

🤖 AI-driven analysis
🔄 Adaptive investigation
📊 Context-aware results
💡 Intelligent remediation

📊 API Reference

CoralogixClient

class CoralogixClient:
    def health_check(self) -> Tuple[bool, str]
    def fetch_logs(self, namespace: str, pod_name: Optional[str] = None, 
                   hours_back: int = 1, limit: int = 1000) -> List[LogEntry]
    def search_errors(self, namespace: str, search_pattern: str, 
                     hours_back: int = 1) -> List[LogEntry]
    def get_pod_status(self, namespace: str, pod_name: Optional[str] = None) -> Dict[str, Any]

BasicAnalyzer

class BasicAnalyzer:
    def analyze(self, query: str, namespace: str, pod_name: Optional[str] = None,
                hours_back: int = 1) -> InvestigationResult
    def detect_failures(self, logs: List[LogEntry]) -> List[FailurePattern]

LLMAnalyzer

class LLMAnalyzer:
    def investigate(self, query: str, namespace: str, pod_name: Optional[str] = None,
                   hours_back: int = 1) -> InvestigationResult
    def llm_analyze_and_decide(self, user_input: str, 
                               tool_results: List[ToolResult] = None) -> Tuple[str, List[Dict[str, Any]]]

🔧 Troubleshooting

SSL Certificate Issues

If you encounter SSL certificate verification errors like:

❌ Connection failed: Connection failed: HTTPSConnectionPool(host='ng-api-http.jfrog-dev.app.coralogix.us', port=443): Max retries exceeded with url: /api/v1/health (Caused by SSLError(SSLCertVerificationError(1, "[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: Hostname mismatch, certificate is not valid for 'ng-api-http.jfrog-dev.app.coralogix.us'. (_ssl.c:1028)")))

Solutions:

For Development/Testing: Disable SSL verification temporarily:
```
export CORALOGIX_VERIFY_SSL="false"
```

For Production: Verify your domain configuration:

# Check if the domain is correct
export CORALOGIX_DOMAIN="eu2.coralogix.com"  # Use the default domain
# or
export CORALOGIX_DOMAIN="your-correct-domain.coralogix.com"

Check your team hostname:

export CORALOGIX_TEAM_HOSTNAME="your-correct-team-hostname"

Common Issues

"Missing required environment variables": Ensure all required environment variables are set
"Connection failed": Check your API key and domain configuration
"No logs found": Verify the namespace and time range settings

🧪 Testing

# Install development dependencies
pip install -e ".[dev]"

# Run all tests
pytest

# Run with coverage
pytest --cov=src

# Run specific test file
pytest tests/test_analyzer.py

Code Quality

# Format code
black src/

# Lint code
flake8 src/

# Type checking
mypy src/

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Setup

# Clone the repository
git clone https://github.com/your-org/coralogix-log-analyzer.git
cd coralogix-log-analyzer

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install development dependencies
pip install -e ".[dev]"

# Install pre-commit hooks
pre-commit install

Code Style

We use:

Black for code formatting
Flake8 for linting
MyPy for type checking
Pre-commit for automated checks

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔌 MCP Integration

For detailed information about the Model Context Protocol (MCP) integration, see MCP_INTEGRATION.md.

🙏 Acknowledgments

Built with inspiration from the HolmesGPT project
Uses OpenAI's GPT models for intelligent analysis
Integrates with Coralogix for log aggregation
MCP integration for AI assistant compatibility

📞 Support

Documentation: GitHub Wiki
Issues: GitHub Issues
Discussions: GitHub Discussions

Made with ❤️ for the DevOps community

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
src		src
.gitignore		.gitignore
MCP_INTEGRATION.md		MCP_INTEGRATION.md
MCP_SUMMARY.md		MCP_SUMMARY.md
PROJECT_SUMMARY.md		PROJECT_SUMMARY.md
README.md		README.md
main.py		main.py
mcp_server.py		mcp_server.py
pyproject.toml		pyproject.toml
requirements.txt		requirements.txt
test_ssl_fix.py		test_ssl_fix.py

Folders and files

Latest commit

History

Repository files navigation

Coralogix Log Analyzer - Professional Edition

🚀 Features

📋 Table of Contents

🛠️ Installation

Prerequisites

Install from Source

Install with pip

🚀 Quick Start

1. Set Environment Variables

2. Basic Analysis

3. LLM-Driven Investigation

4. Health Check

5. MCP Server

📖 Usage

Command Line Interface

Output Formats

⚙️ Configuration

Environment Variables

Configuration File

🏗️ Architecture

Project Structure

Core Components

1. Configuration Management (src/config/)

2. Data Models (src/models/)

3. Core Logic (src/core/)

4. CLI Interface (src/cli/)

5. MCP Integration (src/mcp/)

🔍 Analysis Modes

1. Basic Pattern-Based Analysis

2. LLM-Driven Investigation

📊 API Reference

CoralogixClient

BasicAnalyzer

LLMAnalyzer

🔧 Troubleshooting

SSL Certificate Issues

Common Issues

🧪 Testing

Code Quality

🤝 Contributing

Development Setup

Code Style

📄 License

🔌 MCP Integration

🙏 Acknowledgments

📞 Support

About

Resources

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

1. Configuration Management (`src/config/`)

2. Data Models (`src/models/`)

3. Core Logic (`src/core/`)

4. CLI Interface (`src/cli/`)

5. MCP Integration (`src/mcp/`)

Packages