from fair_forge.generators import BaseGenerator

def __init__(
    self,
    model: BaseChatModel,
    use_structured_output: bool = False,
):
    pass

async def generate_dataset(
    self,
    context_loader: BaseContextLoader,
    source: str,
    assistant_id: str,
    num_queries_per_chunk: int = 3,
    language: str = "english",
    conversation_mode: bool = False,
    selection_strategy: SelectionStrategy | None = None,
    seed_examples: list[str] | None = None,
) -> list[Dataset]

from fair_forge.generators import create_markdown_loader

def create_markdown_loader(
    max_chunk_size: int = 2000,
    min_chunk_size: int = 100,
    header_levels: list[int] = [1, 2, 3],
) -> BaseContextLoader

from fair_forge.generators.context_loaders.base import BaseContextLoader

class BaseContextLoader(ABC):
    @abstractmethod
    def load(self, source: str) -> list[ContentChunk]:
        pass

class ContentChunk:
    chunk_id: str
    content: str
    metadata: dict

from fair_forge.generators import SequentialStrategy

class SequentialStrategy:
    """Process all chunks sequentially into a single dataset."""
    pass

from fair_forge.generators import RandomSamplingStrategy

class RandomSamplingStrategy:
    def __init__(
        self,
        num_samples: int,
        chunks_per_sample: int,
        seed: int | None = None,
    ):
        pass

batch.agentic = {
    "difficulty": str,      # "easy", "medium", "hard"
    "query_type": str,      # "factual", "inferential", "comparative", "application"
    "chunk_id": str,        # Source chunk ID
    "turn_number": int,     # (conversation mode) Turn number
    "builds_on": str,       # (conversation mode) Previous query reference
}