uv add "alquimia-fair-forge[generators]"
uv add langchain-groq  # Or your preferred LLM provider

from fair_forge.generators import BaseGenerator, create_markdown_loader
from langchain_groq import ChatGroq

# Create a context loader
loader = create_markdown_loader(
    max_chunk_size=2000,
    header_levels=[1, 2, 3],
)

# Create generator with an LLM
model = ChatGroq(model="llama-3.1-8b-instant", temperature=0.4)
generator = BaseGenerator(model=model, use_structured_output=True)

# Generate test dataset
datasets = await generator.generate_dataset(
    context_loader=loader,
    source="./documentation.md",
    assistant_id="my-assistant",
    num_queries_per_chunk=3,
    language="english",
)

# Use with metrics
for dataset in datasets:
    print(f"Generated {len(dataset.conversation)} test queries")

from fair_forge.generators import BaseGenerator

generator = BaseGenerator(
    model=your_langchain_model,
    use_structured_output=True,
)

from fair_forge.generators import create_markdown_loader

loader = create_markdown_loader(
    max_chunk_size=2000,
    header_levels=[1, 2, 3],
)

from fair_forge.generators import SequentialStrategy, RandomSamplingStrategy

# Process all chunks sequentially (default)
strategy = SequentialStrategy()

# Sample random chunks multiple times
strategy = RandomSamplingStrategy(
    num_samples=3,
    chunks_per_sample=5,
)

datasets = await generator.generate_dataset(
    context_loader=loader,
    source="./docs",
    num_queries_per_chunk=3,
    conversation_mode=False,  # Default
)

datasets = await generator.generate_dataset(
    context_loader=loader,
    source="./docs",
    num_queries_per_chunk=3,
    conversation_mode=True,  # Each turn builds on previous
)

Dataset(
    session_id="generated-uuid",
    assistant_id="my-assistant",
    language="english",
    context="Combined chunk content...",
    conversation=[
        Batch(
            qa_id="chunk-1_q1",
            query="Generated question?",
            assistant="",  # Empty - to be filled by runner
            agentic={
                "difficulty": "medium",
                "query_type": "factual",
                "chunk_id": "doc_section_1",
            },
        ),
        ...
    ]
)