Architecture

from semantica.ingest.registry import method_registry

def custom_file_ingestor(source):
    # Return a list of document dicts with 'text', 'metadata', 'source'
    return [{"text": "...", "metadata": {}, "source": source}]

# Register under the "file" task category with a unique name
method_registry.register("file", "my_custom_format", custom_file_ingestor)

available = method_registry.list_all("file")

from semantica.semantic_extract.registry import method_registry

def custom_entity_extractor(text, config=None):
    # Return a list of entity dicts with 'text', 'type', 'confidence'
    return [{"text": "...", "type": "CUSTOM_TYPE", "confidence": 0.9}]

# Register under the "entity" extraction task
method_registry.register("entity", "my_extractor", custom_entity_extractor)

from semantica.core import PluginRegistry

class MyPlugin:
    def process(self, graph, config):
        # Modify the graph in place and return it
        return graph

registry = PluginRegistry()
registry.register_plugin("my_plugin", MyPlugin, version="1.0.0")