python scripts/create_provider_plugin.py MyProvider --with-schema

custom_provider_plugin/
├── pyproject.toml                      # Package configuration and metadata
├── README.md                            # This file
├── langextract_provider_example/        # Package directory
│   ├── __init__.py                     # Package initialization
│   ├── provider.py                     # Custom provider implementation
│   └── schema.py                       # Custom schema implementation (optional)
└── test_example_provider.py            # Test script

from langextract.core import base_model
from langextract.providers import router

@router.register(
    r'^gemini',  # Pattern for model IDs this provider handles
)
class CustomGeminiProvider(base_model.BaseLanguageModel):
    def __init__(self, model_id: str, **kwargs):
        # Initialize your backend client

    def infer(self, batch_prompts, **kwargs):
        # Call your backend API and return results

[project.entry-points."langextract.providers"]
custom_gemini = "langextract_provider_example:CustomGeminiProvider"

from langextract.core import schema as core_schema

class CustomProviderSchema(core_schema.BaseSchema):
    @classmethod
    def from_examples(cls, examples_data, attribute_suffix="_attributes"):
        # Analyze examples to find patterns
        # Build schema based on extraction classes and attributes seen
        return cls(schema_dict)

    def to_provider_config(self):
        # Convert schema to provider kwargs
        return {
            "response_schema": self._schema_dict,
            "enable_structured_output": True
        }

    @property
    def requires_raw_output(self):
        # True = provider emits raw JSON, no markdown fences needed
        return True

class CustomProvider(base_model.BaseLanguageModel):
    @classmethod
    def get_schema_class(cls):
        return CustomProviderSchema  # Tell LangExtract about your schema

    def __init__(self, **kwargs):
        # Receive schema config in kwargs when use_schema_constraints=True
        self.response_schema = kwargs.get('response_schema')

    def infer(self, batch_prompts, **kwargs):
        # Use schema during API calls
        if self.response_schema:
            config['response_schema'] = self.response_schema

# Navigate to this example directory first
cd examples/custom_provider_plugin

# Install in development mode
pip install -e .

# Test the provider (must be run from this directory)
python test_example_provider.py

import langextract as lx

# Option A: build a model explicitly and pass it to extract()
config = lx.factory.ModelConfig(
    model_id="gemini-2.5-flash",
    provider="CustomGeminiProvider",
    provider_kwargs={"api_key": "your-api-key"},
)
model = lx.factory.create_model(config)

result = lx.extract(
    text_or_documents="Your text here",
    model=model,
    prompt_description="Extract key information",
    examples=[...],
)

# Option B: let extract() build the model from a ModelConfig
result = lx.extract(
    text_or_documents="Your text here",
    config=lx.factory.ModelConfig(
        model_id="gemini-2.5-flash",
        provider="CustomGeminiProvider",
        provider_kwargs={"api_key": "your-api-key"},
    ),
    prompt_description="Extract key information",
    examples=[...],
)

# Copy this example directory
cp -r examples/custom_provider_plugin/ ~/langextract-myprovider/

# Rename the package directory
cd ~/langextract-myprovider/
mv langextract_provider_example langextract_myprovider

# Install in development mode
pip install -e .

# Test your provider
python -c "
from langextract.providers import load_plugins_once, router
load_plugins_once()
print('Provider registered:', any('myprovider' in str(e) for e in router.list_entries()))
"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*