Codificador cruzado

Milvus admite codificadores cruzados a través de la clase CrossEncoderRerankFunction. Esta funcionalidad permite puntuar eficazmente la relevancia de los pares consulta-documento.

Para utilizar esta función, instale las dependencias necesarias:

pip install --upgrade pymilvus
pip install "pymilvus[model]"

A continuación, instancie la clase CrossEncoderRerankFunction:

from pymilvus.model.reranker import CrossEncoderRerankFunction

# Define the rerank function
ce_rf = CrossEncoderRerankFunction(
    model_name="cross-encoder/ms-marco-MiniLM-L-6-v2",  # Specify the model name.
    device="cpu" # Specify the device to use, e.g., 'cpu' or 'cuda:0'
)

Parámetros:

• model_name (cadena)

  Nombre del modelo que se va a utilizar. Puede especificar cualquiera de los nombres de modelo Cross-Encoder disponibles, por ejemplo, cross-encoder/ms-marco-TinyBERT-L-2-v2, cross-encoder/ms-marco-MiniLM-L-2-v2, etc. Si deja este parámetro sin especificar, se utilizará una cadena vacía. Para obtener una lista de los modelos disponibles, consulte Cross-Encoders preentrenados.

• device (cadena)

  El dispositivo que se utilizará para ejecutar el modelo. Puedes especificar cpu para la CPU y cuda:n para la enésima GPU.

A continuación, utilice el siguiente código para clasificar los documentos en función de la consulta:

query = "What event in 1956 marked the official birth of artificial intelligence as a discipline?"

documents = [
    "In 1950, Alan Turing published his seminal paper, 'Computing Machinery and Intelligence,' proposing the Turing Test as a criterion of intelligence, a foundational concept in the philosophy and development of artificial intelligence.",
    "The Dartmouth Conference in 1956 is considered the birthplace of artificial intelligence as a field; here, John McCarthy and others coined the term 'artificial intelligence' and laid out its basic goals.",
    "In 1951, British mathematician and computer scientist Alan Turing also developed the first program designed to play chess, demonstrating an early example of AI in game strategy.",
    "The invention of the Logic Theorist by Allen Newell, Herbert A. Simon, and Cliff Shaw in 1955 marked the creation of the first true AI program, which was capable of solving logic problems, akin to proving mathematical theorems."
]

results = ce_rf(
    query=query,
    documents=documents,
    top_k=3,
)

for result in results:
    print(f"Index: {result.index}")
    print(f"Score: {result.score:.6f}")
    print(f"Text: {result.text}\n")

El resultado esperado es similar al siguiente:

Index: 1
Score: 6.250533
Text: The Dartmouth Conference in 1956 is considered the birthplace of artificial intelligence as a field; here, John McCarthy and others coined the term 'artificial intelligence' and laid out its basic goals.

Index: 0
Score: -2.954602
Text: In 1950, Alan Turing published his seminal paper, 'Computing Machinery and Intelligence,' proposing the Turing Test as a criterion of intelligence, a foundational concept in the philosophy and development of artificial intelligence.

Index: 3
Score: -4.771512
Text: The invention of the Logic Theorist by Allen Newell, Herbert A. Simon, and Cliff Shaw in 1955 marked the creation of the first true AI program, which was capable of solving logic problems, akin to proving mathematical theorems.