Spaces:
Runtime error
Runtime error
File size: 1,283 Bytes
a5ba329 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
from sentence_transformers import SentenceTransformer, util
import os
from tqdm import tqdm
import pandas as pd
import json
import pickle
import torch
import gradio as gr
with open('new_transcript.json', 'r', encoding='utf-8') as openfile:
# Reading from json file
json_object1 = json.load(openfile)
json_object1[0]
model = SentenceTransformer('keepitreal/vietnamese-sbert', device='cpu')
#Load sentences & embeddings from disc
with open('embeddings.pkl', "rb") as fIn:
stored_data = pickle.load(fIn)
stored_sentences = stored_data['sentences']
stored_embeddings = stored_data['embeddings']
emb = torch.from_numpy(stored_embeddings)
def semantic_search(query, top_k=20):
query_embedding = model.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, emb)[0]
top_results = torch.topk(cos_scores, k=top_k)
str_results = ""
for score, idx in zip(top_results[0], top_results[1]):
str_results += str(json_object1[idx]) + " - (Score: {:.4f})".format(score) + "\n"
return str_results
demo = gr.Interface(
fn=semantic_search,
inputs=gr.Textbox(lines=2, placeholder="Input text query..."),
outputs="text",
)
demo.launch(share=True) |