Sentence transformers

"""
This is a simple application for sentence embeddings: semantic search

We have a corpus with various sentences. Then, for a given query sentence,
we want to find the most similar sentence in this corpus.

This script outputs for various queries the top 5 most similar sentences in the corpus.
"""
from sentence_transformers import SentenceTransformer, util
import torch

embedder = SentenceTransformer('all-MiniLM-L6-v2')

# Corpus with example sentences
corpus = ['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.',
          'A cheetah is running behind its prey.'
          ]
corpus_embeddings = embedder.encode(corpus, convert_to_tensor=True)

# Query sentences:
queries = ['A man is eating pasta.', 'Someone in a gorilla costume is playing a set of drums.', 'A cheetah chases prey on across a field.']


# Find the closest 5 sentences of the corpus for each query sentence based on cosine similarity
top_k = min(5, len(corpus))
for query in queries:
    query_embedding = embedder.encode(query, convert_to_tensor=True)

    # We use cosine-similarity and torch.topk to find the highest 5 scores
    cos_scores = util.cos_sim(query_embedding, corpus_embeddings)[0]
    top_results = torch.topk(cos_scores, k=top_k)

    print("\n\n======================\n\n")
    print("Query:", query)
    print("\nTop 5 most similar sentences in corpus:")

    for score, idx in zip(top_results[0], top_results[1]):
        print(corpus[idx], "(Score: {:.4f})".format(score))

    """
    # Alternatively, we can also use util.semantic_search to perform cosine similarty + topk
    hits = util.semantic_search(query_embedding, corpus_embeddings, top_k=5)
    hits = hits[0]      #Get the hits for the first query
    for hit in hits:
        print(corpus[hit['corpus_id']], "(Score: {:.4f})".format(hit['score']))
    """

Source: sbert.net

Similar codes

0 vote238 views1 answer
Merge multile dict
Python
0 vote232 views2 answers
Spyder 32 bit download
Python
1 vote231 views2 answers
How to change font in tkinter
Python
0 vote224 views1 answer
Difference between calling a function and referencing a function python
Python
3 votes258 views2 answers
Python print do not use scientific notation
Python
12 votes244 views6 answers
Check for missing values in pandas
Python
83 votes229 views6 answers
Activate virtual environment python windows
Python
2 votes226 views2 answers
Pd.dataframe initial columns
Python
0 vote247 views1 answer
Concatenating datfra,esin pandas
Python
11 votes232 views3 answers
Django q filter
Python Django