Structured Output Integrations¶

Welcome to the Instructor integrations guide. This section provides detailed information about using structured outputs with various AI model providers.

Supported Providers¶

Instructor supports a wide range of AI model providers, each with their own capabilities and features:

OpenAI-Compatible Models¶

• OpenAI - GPT-3.5, GPT-4, and other OpenAI models
• Azure OpenAI - Microsoft's Azure-hosted OpenAI models

Open Source & Self-Hosted Models¶

• Ollama - Run open-source models locally
• llama-cpp-python - Python bindings for llama.cpp
• Together AI - Host and run open source models
• Cortex - Run open source models with Cortex

Cloud AI Providers¶

• Anthropic - Claude and Claude 2 models
• Google - PaLM and Gemini models
• Vertex AI - Google Cloud's AI platform
• Cohere - Command-R and other Cohere models
• Groq - High-performance inference platform
• Mistral - Mistral's hosted models
• Fireworks - High-performance model inference
• Cerebras - Llama-3-70B and other Open Source Models at blazing fast inference speeds
• Writer - Palmyra-X-004 and other Writer models
• DeepSeek - DeepSeek Coder and DeepSeek Chat models

Model Management¶

• LiteLLM - Unified interface for multiple providers

Common Concepts¶

All integrations share some common concepts:

• Data Validation
• Streaming Support
• Model Validation
• Instructor Hooks

Need Help?¶

If you need help with a specific integration:

1. Check the provider-specific documentation
2. Look at the examples
3. Check our GitHub issues
4. Join our Discord community