Structured Outputs \ Basics
- Basic use
- Specifying required and optional parameters via constructor
- Getters and setters
- Private vs public object field
- Basic use via mixin
- Fluent API
- Handling errors with `Maybe` helper class
- Messages API
- Mixed Type Property
- Modes
- Making some fields optional
- Automatic correction based on validation results
- Using attributes
- Using LLM API connection presets from config file
- Validation
- Custom validation using Symfony Validator
- Validation across multiple fields
- Validation with LLM
Structured Outputs \ Advanced
- Use custom configuration providers
- Context caching (structured output)
- Context caching (structured output, OpenAI)
- Customize parameters of LLM driver
- Use custom HTTP client instance
- Use custom HTTP client instance - Laravel
- Custom prompts
- Customize parameters via DSN
- Extracting arguments of function or method
- Manual Schema Building
- Streaming partial updates during inference
- Providing example inputs and outputs
- Extracting scalar values
- Extracting sequences of objects
- Streaming
- Structures
Structured Outputs \ Troubleshooting
Structured Outputs \ LLM API Support
Structured Outputs \ Extras
- Extraction of complex objects
- Extraction of complex objects (Anthropic)
- Extraction of complex objects (Cohere)
- Extraction of complex objects (Gemini)
- Custom Content Extractors
- Using structured data as an input
- Image processing - car damage detection
- Image to data (OpenAI)
- Image to data (Anthropic)
- Image to data (Gemini)
- Generating JSON Schema from PHP classes
- Return extracted data as array
- Use different class for schema and output
- Streaming with array output format
- Pure Array Processing (No Classes)
- Generating JSON Schema from PHP classes
- Generating JSON Schema dynamically
- Create tasks from meeting transcription
- Translating UI text fields
- Web page to PHP objects
LLM Inference and Embeddings \ LLM Basics
- Working directly with LLMs
- Working directly with LLMs and JSON - JSON mode
- Working directly with LLMs and JSON - JSON Schema mode
- Working directly with LLMs and JSON - MdJSON mode
- Working directly with LLMs and JSON - Tools mode
- Generating JSON Schema from PHP classes
- Generating JSON Schema from PHP classes
LLM Inference and Embeddings \ LLM Advanced
- Customize configuration providers of LLM driver
- Context caching (text inference)
- Context caching (text inference, OpenAI)
- Customize configuration of LLM driver
- Custom Embeddings Config
- Using custom LLM driver
- Customize LLM Configuration with DSN string
- Embeddings utils
- Embeddings
- Work directly with HTTP client facade
- Parallel Calls
- Reasoning Content Access
LLM Inference and Embeddings \ LLM Troubleshooting
LLM Inference and Embeddings \ LLM API Support
LLM Inference and Embeddings \ LLM Extras
HTTP Client \ HTTP Client
Agents and Agent Controllers \ Agents
Agents and Agent Controllers \ Agent Controllers
Prompting \ Zero-Shot
Prompting \ Few-Shot
Prompting \ Thought Generation
Prompting \ Ensembling
- Combine Multiple Reasoning Chains
- Use LLMs to Combine Different Responses
- Combine Different Specialized LLMs
- Prioritize Consistent Examples
- Use Distinct Example Subsets
- Use Ensembles To Test Prompts
- Generate Multiple Candidate Responses
- Use Task Specific Evaluation Metrics
- Use Translation for Paraphrasing
- Verify Responses over Majority Voting
Prompting \ Self-Criticism
Prompting \ Decomposition
Prompting \ Miscellaneous
- Arbitrary properties
- Consistent values of arbitrary properties
- Chain of Summaries
- Chain of Thought
- Single label classification
- Multiclass classification
- Entity relationship extraction
- Handling errors
- Limiting the length of lists
- Reflection Prompting
- Restating instructions
- Ask LLM to rewrite instructions
- Expanding search queries
- Summary with Keywords
- Reusing components
- Using CoT to improve interpretation of component data
LLM Inference and Embeddings \ LLM Advanced
Parallel Calls
⌘I