ab/duty-ai-ops
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
ab
2025-12-24 02:52:37 +00:00
parent 24797bdd6f
commit 53b17b488d
1 changed files with 6 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
README.md
View File

@@ -6,10 +6,8 @@ AI-powered Kubernetes monitoring and diagnostics tool that automatically detects
- 🤖 **AI-Powered Diagnostics**: Uses LLM with function calling to analyze Kubernetes issues - 🤖 **AI-Powered Diagnostics**: Uses LLM with function calling to analyze Kubernetes issues
- 🔍 **Smart Event Detection**: Monitors pods and nodes for problems (CrashLoopBackOff, NotReady, high restarts, etc.) - 🔍 **Smart Event Detection**: Monitors pods and nodes for problems (CrashLoopBackOff, NotReady, high restarts, etc.)
- 🧠 **Correlation Engine**: Detects patterns like mass pod failures and diagnoses the root cause (node issues) instead of individual symptoms - 🧠 **Correlation Engine**: Detects patterns like mass pod failures and diagnoses the root cause (node issues)
- 📱 **Telegram Notifications**: Optional real-time alerts with automatic "resolved" status updates - 📱 **Telegram Notifications**: Optional real-time alerts
- ⚡ **Concurrent Processing**: Configurable parallel AI diagnosis requests with semaphore-based rate limiting
- 🎯 **Resource-Aware**: Tracks pod CPU/memory requests and limits for better diagnostics
## How It Works ## How It Works
@@ -17,7 +15,6 @@ AI-powered Kubernetes monitoring and diagnostics tool that automatically detects
2. **Correlates** issues (e.g., if 5+ pods fail on same node within 60s, diagnose the node) 2. **Correlates** issues (e.g., if 5+ pods fail on same node within 60s, diagnose the node)
3. **Analyzes** using AI with access to k8s API tools (get pod details, logs, node status) 3. **Analyzes** using AI with access to k8s API tools (get pod details, logs, node status)
4. **Notifies** via Telegram with structured diagnostic reports 4. **Notifies** via Telegram with structured diagnostic reports
5. **Tracks** issue resolution and updates notifications automatically
## Installation ## Installation
@@ -40,10 +37,10 @@ cp config.toml.example config.toml
# API Configuration (OpenAI-compatible) # API Configuration (OpenAI-compatible)
api_base = "http://localhost:11434/v1" # Ollama, vLLM, etc. api_base = "http://localhost:11434/v1" # Ollama, vLLM, etc.
api_key = "your-key" api_key = "your-key"
model = "qwen3-tools:latest" model = "qwen3-tools:latest" # any model supporting tools
# Concurrency # Concurrency
max_concurrent_diagnoses = 1 max_concurrent_diagnoses = 1 # parallel OpenAI API requests
# Telegram (optional) # Telegram (optional)
telegram_bot_token = "your-bot-token" telegram_bot_token = "your-bot-token"
@@ -66,7 +63,7 @@ KUBECONFIG=/path/to/kubeconfig cargo run --release
## Requirements ## Requirements
- Rust 1.70+ - Rust 1.70+
- Kubernetes cluster access (via kubeconfig) - Kubernetes cluster access (via kubeconfig or kubernetes service account)
- OpenAI-compatible LLM endpoint with function calling support - OpenAI-compatible LLM endpoint with function calling support
- Tested with: Ollama (qwen3-tools, devstral-small-2) - Tested with: Ollama (qwen3-tools, devstral-small-2)
- Should work with: OpenAI, vLLM, etc. - Should work with: OpenAI, vLLM, etc.
@@ -89,4 +86,4 @@ KUBECONFIG=/path/to/kubeconfig cargo run --release
## License ## License
MIT WTFPL