feat: add structured output support with Pydantic models

[yashranaway]

• Add with_structured_output() method to ChatGradient
• Support Pydantic model validation and JSON parsing
• Include comprehensive error handling and type safety
• Add unit and integration tests
• Update documentation with examples

fixes #8

[Copilot]

Pull Request Overview

This PR adds structured output support to ChatGradient, enabling automatic parsing of LLM responses into validated Pydantic models through a new with_structured_output() method. This feature provides type-safe, validated data extraction similar to OpenAI's structured output API.

Key Changes:

• Implements StructuredOutputRunnable class with JSON extraction and Pydantic validation
• Adds with_structured_output() method to ChatGradient for creating structured output runnables
• Includes comprehensive error handling with StructuredOutputError exception

Reviewed Changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
langchain_gradient/chat_models.py	Implements core structured output functionality with StructuredOutputRunnable class and with_structured_output() method
langchain_gradient/init.py	Exports new StructuredOutputError and StructuredOutputRunnable classes
tests/unit_tests/test_structured_output.py	Comprehensive unit tests covering JSON extraction, parsing, validation, and error handling
tests/integration_tests/test_structured_output_integration.py	Integration tests with real API calls for various structured output scenarios
examples/structured_output_example.py	Demonstration examples showing different use cases of structured output
README.md	Documentation for structured output feature with usage examples and supported features

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[yashranaway]

@bnarasimha21 anything i can update