milvus-logo
LFAI
Home
  • Modèles

Encodeur croisé

Milvus prend en charge les encodeurs croisés par le biais de la classe CrossEncoderRerankFunction. Cette fonctionnalité vous permet d'évaluer efficacement la pertinence des paires requête-document.

Pour utiliser cette fonctionnalité, installez les dépendances nécessaires :

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

Ensuite, instanciez la classe 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'
)

Paramètres:

  • model_name (chaîne)

    Le nom du modèle à utiliser. Vous pouvez spécifier n'importe quel nom de modèle Cross-Encoder disponible, par exemple, cross-encoder/ms-marco-TinyBERT-L-2-v2, cross-encoder/ms-marco-MiniLM-L-2-v2, etc. Si ce paramètre n'est pas spécifié, une chaîne vide sera utilisée. Pour obtenir une liste des modèles disponibles, reportez-vous à la section Encodeurs croisés pré-entraînés.

  • device (chaîne)

    Le dispositif à utiliser pour l'exécution du modèle. Vous pouvez spécifier cpu pour le CPU et cuda:n pour le nième périphérique GPU.

Utilisez ensuite le code suivant pour classer les documents en fonction de la requête :

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")

Le résultat attendu est similaire à ce qui suit :

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.

Traduit parDeepL

Table de contenu

Try Managed Milvus for Free

Zilliz Cloud is hassle-free, powered by Milvus and 10x faster.

Get Started
Feedback

Cette page a-t - elle été utile ?