Datagen

from camel.agents import ChatAgent
from camel.datagen import CoTDataGenerator

# Initialize agents
generator_agent = ChatAgent("Generator agent for simple math computation.")
verifier_agent = ChatAgent("Verified agent for simple math computation.")

# Define golden answers
question = "What's the answer of 1 + 2?"

golden_answers = {
    question: "3",
}

# Create generator
cot_generator = CoTDataGenerator(
    generator_agent=generator_agent,
    verifier_agent=verifier_agent,
    golden_answers=golden_answers,
    search_limit=3,
)

# Generate solution
solution = cot_generator.solve(question)

# Import QA pairs from JSON
cot_generator.import_qa_from_json("qa_pairs.json")

# Export solutions
cot_generator.export_solutions("solutions.json")

from camel.agents import ChatAgent
from camel.datagen.self_instruct import SelfInstructPipeline

# Initialize agent
agent = ChatAgent()

# Create pipeline with default settings
pipeline = SelfInstructPipeline(
    agent=agent,
    seed='seed_tasks.jsonl',  # Path to human-written seed tasks
    num_machine_instructions=5,
    data_output_path='./data_output.json',
    human_to_machine_ratio=(6, 2)
)

# Generate instructions
pipeline.generate()

from camel.datagen.self_instruct import SelfInstructPipeline
from camel.datagen.self_instruct.filter import InstructionFilter

# Configure filters
filter_config = {
    "length": {},
    "keyword": {},
    "punctuation": {},
    "non_english": {},
    "rouge_similarity": {
        "threshold": 0.7,
        "metric": "rouge-l"
    }
}

pipeline = SelfInstructPipeline(
    agent=agent,
    seed='seed_tasks.jsonl',
    instruction_filter=InstructionFilter(filter_config),
    num_machine_instructions=5
)

from camel.datagen.source2synth import (
    UserDataProcessor,
    ProcessorConfig
)

# Create configuration
config = ProcessorConfig(
    seed=42,
    min_length=50,
    max_length=1000,
    complexity_threshold=0.5,
    dataset_size=10,
    use_ai_model=True,
)

# Initialize processor
processor = UserDataProcessor(config)

# Process a single text
result = processor.process_text(
    "Your source text here",
    source="example_source"
)

# Process multiple texts
texts = ["Text 1", "Text 2", "Text 3"]
sources = ["source1", "source2", "source3"]
batch_results = processor.process_batch(texts, sources)

from camel.agents import ChatAgent
from camel.datagen import SelfImprovingCoTPipeline

# Initialize agents
reason_agent = ChatAgent(
    """Answer my question and give your
    final answer within \\boxed{}."""
)

evaluate_agent = ChatAgent(
    "You are a highly critical teacher who evaluates the student's answers "
    "with a meticulous and demanding approach."
)

# Prepare your problems
problems = [
    {"problem": "Your problem text here"},
    # Add more problems...
]

# Create and run the pipeline
pipeline = SelfImprovingCoTPipeline(
    reason_agent=reason_agent,
    evaluate_agent=evaluate_agent,
    problems=problems,
    max_iterations=3,
    output_path="star_output.json"
)

results = pipeline.generate()

from camel.models.reward import NemotronRewardModel

# Initialize reward model
reward_model = NemotronRewardModel(
    model_type=ModelType.NVIDIA_NEMOTRON_340B_REWARD,
    url="https://integrate.api.nvidia.com/v1",
    api_key="your_api_key"
)

# Create pipeline with reward model
pipeline = SelfImprovingCoTPipeline(
    reason_agent=reason_agent,
    evaluate_agent=evaluate_agent,
    problems=problems,
    reward_model=reward_model,
    score_threshold={
        "correctness": 0.8,
        "clarity": 0.7,
        "completeness": 0.7
    }
)