llm-discovery

Getting Started

  • Installation
    • Method 1: uvx (Recommended)
    • Method 2: pip
    • Method 3: From Source
    • Requirements
    • Versioning
    • Next Steps
  • Quick Start
    • Zero Configuration Quick Start
    • Environment Variables (For Real-time Data)
      • OpenAI
      • Google AI Studio
      • Google Vertex AI
    • Basic Commands
      • Update: Fetch and Cache Models
      • List: Display Cached Models
      • Export: Save Model Data
    • Python API Basic Usage
      • Fetch All Models
      • Filter Models by Provider
    • Offline Mode
    • Change Detection
    • Next Steps

Reference

  • Python API Reference
    • Package Version
    • DiscoveryClient Class
      • Import
      • Constructor
      • fetch_models()
      • get_cached_models()
    • Config Class
      • Import
      • from_env()
    • ProviderSnapshot Class
      • Import
      • Attributes
    • Model Class
      • Import
      • Attributes
    • Data Export Formats
      • JSON Export
      • CSV Export
      • YAML Export
      • Markdown Export
      • TOML Export
    • Exception Handling
      • Exception Hierarchy
      • Example Error Handling
    • Complete Usage Example
    • Next Steps
  • CLI Reference
    • Global Command Structure
    • Global Options
      • –version
      • –help
    • Commands
      • update
      • list
      • export
    • Environment Variables
      • Required Environment Variables
      • Optional Environment Variables
    • Exit Codes
    • CI/CD Integration Examples
      • GitHub Actions
      • GitLab CI
    • Complete Workflow Example
    • Troubleshooting
      • Cache Location
      • Verbose Output
      • Common Issues
    • Next Steps

Guides

  • Advanced Usage
    • CI/CD Integration
      • GitHub Actions
      • GitLab CI
    • Provider Filtering
      • Filter by Single Provider
      • Filter by Multiple Providers
      • Filter by Capabilities
    • Custom Error Handling
      • Retry Logic with Exponential Backoff
      • Fallback to Cache on API Failure
      • Partial Success Handling
    • Google Vertex AI Setup
      • Prerequisites
      • Environment Configuration
      • Verify Setup
    • Production Deployment Checklist
    • Performance Optimization
      • Minimize API Calls
      • Cache Management
    • Next Steps
  • Troubleshooting
    • Authentication Errors
      • OpenAI Authentication Failed
      • Google AI Studio Authentication Failed
      • Vertex AI Authentication Failed
    • Network Errors
      • Connection Timeout
      • DNS Resolution Failed
    • Rate Limit Errors
      • Rate Limit Exceeded
    • Cache-Related Issues
      • Cache Not Found
      • Cache Corrupted
      • Cache Directory Permission Denied
    • Configuration Errors
      • Required Environment Variable Not Set
      • Invalid Environment Variable Value
    • Export Errors
      • Invalid Export Format
      • Permission Denied Writing Output File
    • Version Issues
      • Package Version Not Found
    • Debugging Tips
      • Enable Verbose Logging
      • Check System Information
      • Collect Diagnostic Information
    • FAQ
      • How often should I run update?
      • Can I use llm-discovery offline?
      • How do I clear all cache data?
      • Where are API keys stored?
      • How do I report a bug?
    • Getting Help
llm-discovery
  • Search

© Copyright 2025, driller.

Built with Sphinx using a theme provided by Read the Docs.