# intelligent-log-analyzer

**Repository Path**: jerris-code-space/intelligent-log-analyzer

## Basic Information

- **Project Name**: intelligent-log-analyzer
- **Description**: 一款使用 LangChainGo 库开发的智能日志分析器命令行工具。
- **Primary Language**: Go
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-02-16
- **Last Updated**: 2026-04-27

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Intelligent Log Analyzer

An intelligent log analysis tool built with Go, supporting multi-format log parsing, error pattern recognition, anomaly detection, and AI-driven deep analysis.

## Features

- **Multi-format Log Parsing**: Automatically parses JSON and structured logs
- **Intelligent Log Level Identification**: Automatically infers log levels (INFO, WARN, ERROR, etc.)
- **Error Pattern Detection**: Automatically discovers and categorizes common error patterns
- **Anomaly Detection**: Identifies anomalous behaviors and outliers in logs
- **AI Deep Analysis**: Integrates AI capabilities for semantic log analysis
- **Visualized Reporting**: Generates structured analysis reports
- **Flexible Configuration**: Supports YAML configuration files to customize analysis behavior

## Project Structure

```
intelligent-log-analyzer/
├── main.go              # Program entry point
├── config.go            # Configuration management module
├── model.go             # Core data structures and analysis logic
├── util.go              # Utility functions
├── config-example.yml   # Configuration file example
├── sample.log           # Sample log file
└── go.mod               # Go module definition
```

## Quick Start

### Prerequisites

- Go 1.16 or higher
- Valid AI API configuration (e.g., OpenAI API Key)

### Build and Install

```bash
# Clone the project
git clone https://gitee.com/jerris-code-space/intelligent-log-analyzer.git
cd intelligent-log-analyzer

# Build the project
go build -o log-analyzer .

# Or run directly
go run main.go
```

### Configuration

1. Copy the configuration example:
   ```bash
   cp config-example.yml config.yml
   ```

2. Edit `config.yml` to set up AI API configurations.

3. Run the analysis:
   ```bash
   ./log-analyzer -config config.yml
   ```

## Usage

### Command-line Arguments

```bash
./log-analyzer [OPTIONS]
```

### Configuration File Example (config-example.yml)

```yaml
# AI Analysis Configuration
ai:
  api_key: "your-api-key"
  endpoint: "https://api.example.com/v1"
  model: "gpt-3.5-turbo"

# Analysis Configuration
analysis:
  # Log level keywords
  log_levels:
    - "INFO"
    - "WARN"
    - "ERROR"
    - "DEBUG"
    - "FATAL"
  
  # Anomaly detection threshold
  anomaly_threshold: 0.8
  
  # Maximum concurrency
  max_concurrency: 4

# Output Configuration
output:
  format: "json"  # json or text
  verbose: false
```

### Supported Log Formats

The tool supports the following log formats:

**JSON Format:**
```json
{"timestamp": "2024-01-15T10:30:00Z", "level": "ERROR", "message": "Database connection failed", "service": "api-gateway"}
```

**Structured Log Format:**
```
[2024-01-15 10:30:00] [ERROR] Database connection failed - service: api-gateway
```

## Core API

### LogAnalyzer

The main analyzer struct, providing the following methods:

- `NewLogAnalyzer() (*LogAnalyzer, error)` - Creates a new analyzer instance
- `ParseLogFile(filename string) ([]LogEntry, error)` - Parses a log file
- `AnalyzeLogs(entries []LogEntry) (*LogAnalysis, error)` - Executes log analysis
- `PrintReport()` - Prints the analysis report

### Data Models

- `LogEntry` - Single log entry
- `LogAnalysis` - Complete analysis result
- `ErrorPattern` - Error pattern information
- `Anomaly` - Anomaly detection result
- `TimeRange` - Time range definition

## Sample Output

```
=== Log Analysis Report ===

Time Range: 2024-01-15 10:00:00 ~ 2024-01-15 11:00:00

Log Statistics:
  Total Logs: 1,234
  INFO: 1,000 (81%)
  WARN: 150 (12%)
  ERROR: 84 (7%)

Error Patterns:
  1. Database connection failed (45 occurrences)
  2. Timeout waiting for response (23 occurrences)
  3. Null pointer exception (12 occurrences)

Anomaly Detection:
  - 3 anomalous time points detected
  - Anomaly type: Sudden spike in errors

AI Analysis Suggestions:
  Prioritize investigating database connection pool configuration issues
```

## Contributing

1. Fork the project
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Create a Pull Request

## License

This project is open-sourced under the MIT License.

## Frequently Asked Questions

**Q: What log formats are supported?**  
A: Currently supports JSON format and common structured log formats.

**Q: Is an API Key required for AI analysis?**  
A: Yes, a valid AI service API Key must be configured.

**Q: How are large log files handled?**  
A: The tool automatically processes logs in batches; concurrency can be configured via the config file.

**Q: Can I customize log level detection rules?**  
A: Yes, you can define custom log level keywords in the configuration file.