Codificatore incrociato

Milvus supporta i Cross-Encoder attraverso la classe CrossEncoderRerankFunction. Questa funzionalità consente di attribuire un punteggio alla rilevanza delle coppie query-documento in modo efficace.

Per utilizzare questa funzione, installare le dipendenze necessarie:

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

Quindi, istanziare 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'
)

Parametri:

• model_name (stringa)

  Il nome del modello da usare. È possibile specificare uno qualsiasi dei nomi dei modelli Cross-Encoder disponibili, ad esempio cross-encoder/ms-marco-TinyBERT-L-2-v2, cross-encoder/ms-marco-MiniLM-L-2-v2, ecc. Se si lascia questo parametro non specificato, verrà utilizzata una stringa vuota. Per un elenco dei modelli disponibili, consultare Cross-Encoder pre-addestrati.

• device (stringa)

  Il dispositivo da utilizzare per l'esecuzione del modello. È possibile specificare cpu per la CPU e cuda:n per l'ennesimo dispositivo GPU.

Quindi, utilizzare il codice seguente per classificare i documenti in base alla query:

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")

Il risultato atteso è simile al seguente:

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.