Sakil/sentence_similarity_semantic_search

pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer, InputExample, losses
import pandas as pd
from sentence_transformers import SentenceTransformer, InputExample
from torch.utils.data import DataLoader
from sentence_transformers import SentenceTransformer, util

model_name="Sakil/sentence_similarity_semantic_search"
model = SentenceTransformer(model_name)
sentences = ['A man is eating food.',
'A man is eating a piece of bread.',
'The girl is carrying a baby.',
'A man is riding a horse.',
'A woman is playing violin.',
'Two men pushed carts through the woods.',
'A man is riding a white horse on an enclosed ground.',
'A monkey is playing drums.',
'Someone in a gorilla costume is playing a set of drums.'
]

#Encode all sentences
embeddings = model.encode(sentences)

#Compute cosine similarity between all pairs
cos_sim = util.cos_sim(embeddings, embeddings)

#Add all pairs to a list with their cosine similarity score
all_sentence_combinations = []

for i in range(len(cos_sim)-1):

    for j in range(i+1, len(cos_sim)):
        
        all_sentence_combinations.append([cos_sim[i][j], i, j])

#Sort list by the highest cosine similarity score

all_sentence_combinations = sorted(all_sentence_combinations, key=lambda x: x[0], reverse=True)

print("Top-5 most similar pairs:")

for score, i, j in all_sentence_combinations[0:5]:
    print("{} \t {} \t {:.4f}".format(sentences[i], sentences[j], cos_sim[i][j]))