|
|
from sentence_transformers import SentenceTransformer, util |
|
|
from sklearn.linear_model import LogisticRegression |
|
|
import pickle |
|
|
from sklearn.model_selection import train_test_split |
|
|
from sklearn.metrics.pairwise import cosine_similarity |
|
|
import torch |
|
|
import pandas as pd |
|
|
import os |
|
|
|
|
|
topics = [ |
|
|
"Ankle Sprain : Recovery exercises for ankle sprains and rehabilitation tips.", |
|
|
"Back Pain : Best practices for relieving back pain and strengthening exercises.", |
|
|
"Shoulder Injury : Shoulder injury rehabilitation, strengthening, and recovery techniques." |
|
|
] |
|
|
|
|
|
def get_encoding_model(): |
|
|
model_encode = SentenceTransformer('Alibaba-NLP/gte-base-en-v1.5', trust_remote_code=True) |
|
|
save_model(model_encode,"embedding_model.pkl") |
|
|
|
|
|
def get_embedding(text): |
|
|
if not os.path.exists("embedding_model.pkl"): |
|
|
loaded_model = get_encoding_model() |
|
|
|
|
|
model_encode = load_model("embedding_model.pkl") |
|
|
embedding = model_encode.encode(text) |
|
|
return embedding |
|
|
|
|
|
def save_model(model, filename): |
|
|
with open(filename, 'wb') as model_file: |
|
|
pickle.dump(model, model_file) |
|
|
print(f"Model saved to {filename}") |
|
|
|
|
|
|
|
|
def load_model(filename): |
|
|
|
|
|
with open(filename, 'rb') as model_file: |
|
|
loaded_model = pickle.load(model_file) |
|
|
print(f"Model loaded from {filename}") |
|
|
return loaded_model |
|
|
|
|
|
def get_cosine_similarity(prompt): |
|
|
message = "Phsyiotherapy" |
|
|
embendding = get_embedding([message,prompt]) |
|
|
similarity = util.cos_sim(embendding[0], embendding[1]).item() |
|
|
return round(similarity, 4) |
