您现在的位置是：首页 >其他 >如何使用OpenAI进行embedding句子后，输入新句子比较网站首页其他

import openai
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity


# Set up OpenAI API credentials
openai.api_key = 'YOUR_API_KEY'
response=openai.Embedding.create(
  model="text-embedding-ada-002",
  input="The food was delicious and the waiter..."
)
print(response)


# Define the sentences to be embedded and sorted
sentences = [
    "How to use ChatGPT for sentence embedding?",
    "What are the applications of sentence embedding?",
    "Can you provide examples of sentence embedding?",
    "What is the best approach for sentence embedding?"
]

# Define a new sentence for similarity comparison
new_sentence = "How does sentence embedding work?"

# Preprocess and generate the embeddings
embeddings = []
for sentence in sentences:


    response = openai.Embedding.create(
        model="text-embedding-ada-002",
        input=sentence
    )
    embedding = response.data[0].embedding
    embeddings.append(embedding)

# Convert embeddings to numpy array
embeddings = np.array(embeddings)

# Calculate pairwise cosine similarity
similarity_matrix = cosine_similarity(embeddings)

# Sort sentences based on similarity to the first sentence
sorted_indices = np.argsort(similarity_matrix[:, 0])[::-1]
sorted_sentences = [sentences[i] for i in sorted_indices]


response = openai.Embedding.create(
    model="text-embedding-ada-002",
    input=new_sentence
)
new_embedding = response.data[0].embedding

# Calculate cosine similarity of the new embedding with existing embeddings
similarity_scores = cosine_similarity([new_embedding], embeddings)[0]

# Sort the indices based on similarity scores
sorted_indices = np.argsort(similarity_scores)[::-1]

# Retrieve the most similar sentence
most_similar_sentence = sentences[sorted_indices[0]]

# Print the sorted sentences and the most similar sentence
print("Sorted Sentences:")
for sentence in sorted_sentences:
    print(sentence)

print("
Most Similar Sentence:")
print(most_similar_sentence)