Cohere

Milvus prend en charge les modèles de reranker Cohere par le biais de la classe CohereRerankFunction. 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 CohereRerankFunction:

from pymilvus.model.reranker import CohereRerankFunction

# Define the rerank function
cohere_rf = CohereRerankFunction(
    model_name="rerank-english-v3.0",  # Specify the model name. Defaults to `rerank-english-v2.0`.
    api_key=COHERE_API_KEY # Replace with your Cohere API key
)

Paramètres

• model_name (chaîne)

  Le nom du modèle à utiliser. Vous pouvez spécifier n'importe quel nom de modèle Cohere reranker disponible, par exemple, rerank-english-v3.0, rerank-multilingual-v3.0, etc. Si ce paramètre n'est pas spécifié, rerank-english-v2.0 sera utilisé. Pour obtenir la liste des modèles disponibles, reportez-vous à Rerank.

• api_key (chaîne)

  La clé d'API permettant d'accéder à l'API Cohere. Pour plus d'informations sur la création d'une clé API, reportez-vous à Cohere dashboard.

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 = cohere_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: 0.99691266
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: 3
Score: 0.8578872
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.

Index: 0
Score: 0.3589146
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.