sample_data.py

SAMPLE_DOCUMENTS: list[tuple[str, str]] = [
    (
        "doc_pytorch",
        (
            "PyTorch is an open source machine learning framework "
            "based on the Torch library."
        ),
    ),
    (
        "doc_tensorflow",
        (
            "TensorFlow is a free and open-source software library "
            "for machine learning and artificial intelligence."
        ),
    ),
    (
        "doc_rag",
        (
            "RAG stands for Retrieval-Augmented Generation, a technique "
            "to provide external data to LLMs."
        ),
    ),
    (
        "doc_cross_encoder",
        (
            "A Cross-Encoder is a type of deep learning model that "
            "processes pairs of inputs simultaneously to determine relevance."
        ),
    ),
    (
        "doc_vector_db",
        (
            "Vector databases like ChromaDB store high-dimensional "
            "embeddings for fast similarity search."
        ),
    ),
    (
        "doc_gradient_descent",
        (
            "Gradient descent is an optimization algorithm used to minimize "
            "the loss function in ML models."
        ),
    ),
    (
        "doc_transformers",
        (
            "Transformers are a type of neural network architecture "
            "that has revolutionized NLP."
        ),
    ),
    (
        "doc_ollama",
        "Ollama allows you to run large language models locally on your machine.",
    ),
    (
        "doc_two_stage_rag",
        (
            "Two-stage RAG uses a fast retriever (Stage 1) and a precise "
            "re-ranker (Stage 2) for better accuracy."
        ),
    ),
]