AI SQL Generation

Logchef can translate natural language questions into ClickHouse SQL queries using OpenAI-compatible LLMs. The AI is schema-aware — it knows your table’s columns and types.

Usage

1. Open any log source
2. Click the AI assistant button (wand icon) in the query editor
3. Describe what you want in plain English
4. Review the generated SQL, then insert it into the editor

If you already have a query in the editor, the AI uses it as context for refinements.

Example Queries

"Show error logs from the last 6 hours"
"Count logs by severity for today"
"Find logs containing 'connection refused' from the payments service"
"Top 10 most frequent error messages this week"
"Logs where trace_id = 'abc123'"

Configuration

Configure via Administration → System Settings → AI:

Setting	Description	Default
Enabled	Toggle AI features	true
API Key	Your OpenAI API key	—
Base URL	API endpoint	https://api.openai.com/v1
Model	Model name	gpt-4o
Max Tokens	Max tokens to generate	1024
Temperature	Randomness (0.0–1.0)	0.1

Supported Providers

Any OpenAI-compatible API works:

Provider	Base URL
OpenAI	https://api.openai.com/v1 (default)
OpenRouter	https://openrouter.ai/api/v1
Azure OpenAI	Your Azure endpoint
Local models	Your local server URL

Environment Variables

For containerized deployments, seed the initial config via env vars:

export LOGCHEF_AI__ENABLED=true
export LOGCHEF_AI__API_KEY="sk-your-key"
export LOGCHEF_AI__MODEL="gpt-4o"

After first boot, the Admin UI takes precedence over env vars.

MCP Integration

For AI assistant integration outside the web UI (e.g., Claude Desktop), see MCP Server.

Limitations

AI-generated SQL should always be reviewed before execution. The model can produce incorrect queries, especially for complex aggregations or unfamiliar schemas. Start simple and iterate.