final

Dataset/embeddingsrecipes.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5202b41888fd390fe421bdfcac1b57867260d58426834cbd71900f2d385cba
+size 98568532

Dataset/faissrecipes.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16751ffdb3319faf7cb5b01b726af9612598354d1e6783263e49f66429df0454
+size 32326989

Dataset/recipesdataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b13aa75d0ad9b9e9d168fce0f36d67cd5734ffd090ca09a6f5c8643f71caa95
+size 14171628

app.py

@@ -24,7 +24,7 @@ def load_data():
     df = pd.read_csv('Dataset/parcedbooks.csv')
     with open('Dataset/embeddingsbooks.txt', 'r') as file:
         embeddings_list = [list(map(float, line.split())) for line in file.readlines()]
-    index = faiss.read_index('Dataset/faiss.index')
+    index = faiss.read_index('Dataset/faissbooks.index')
     return df, embeddings_list, index
 
 df, embeddings_list, index = load_data()

pages/recipes.py

@@ -0,0 +1,75 @@
+import streamlit as st
+import pandas as pd 
+import torch
+from PIL import Image
+from io import BytesIO
+import requests
+import faiss
+
+
+from transformers import AutoTokenizer, AutoModel
+import numpy as np
+st.set_page_config(layout="wide")
+
+@st.cache_resource()
+def load_model():
+    model = AutoModel.from_pretrained("cointegrated/rubert-tiny2")
+    tokenizer = AutoTokenizer.from_pretrained("cointegrated/rubert-tiny2")
+    return model , tokenizer
+
+model, tokenizer = load_model()
+
+@st.cache_data()
+def load_data():
+    df = pd.read_csv('Dataset/recipesdataset.csv')
+    with open('Dataset/embeddingsrecipes.txt', 'r') as file:
+        embeddings_list = [list(map(float, line.split())) for line in file.readlines()]
+    index = faiss.read_index('Dataset/faissrecipes.index')
+    return df, embeddings_list, index
+
+df, embeddings_list, index = load_data()
+
+def embed_bert_cls(text, model, tokenizer):
+    t = tokenizer(text, padding=True, truncation=True, return_tensors='pt')
+    with torch.no_grad():
+        model_output = model(**{k: v.to(model.device) for k, v in t.items()})
+    embeddings = model_output.last_hidden_state[:, 0, :]
+    embeddings = torch.nn.functional.normalize(embeddings)
+    return embeddings[0].cpu().numpy()
+
+
+text = st.text_input('Введите ваше предпочтение для рекомендации')
+
+button = st.button('Отправить запрос')
+num = st.number_input('Укажите количество блюд для рекомендации', step=1, value=1)
+
+
+if text and button:
+    decode_text = embed_bert_cls(text, model, tokenizer)  # Получение вектора для введенного текста
+    k = num 
+    D, I = index.search(decode_text.reshape(1, -1), k)
+    
+    top_similar_indices = I[0]
+    top_similar_annotations = [df['annotation'].iloc[i] for i in top_similar_indices]
+    top_similar_images = [df['image_url'].iloc[i] for i in top_similar_indices]
+    images = [Image.open(BytesIO(requests.get(url).content)) for url in top_similar_images]
+    top_similar_title = [df['title'].iloc[i] for i in top_similar_indices]
+    top_similar_url = [df['page_url'].iloc[i] for i in top_similar_indices]
+    top_cosine_similarities = [1 - d / 2 for d in D[0]]  # Преобразование расстояний в косинусное сходство
+
+# Отображение изображений и названий
+    for similarity, image, annotation, title, url in zip(top_cosine_similarities, images, top_similar_annotations, top_similar_title, top_similar_url):
+        col1, col2 = st.columns([3, 4]) 
+        with col1:
+            st.image(image, width=300)
+        with col2:
+            st.write(f"***Название:*** {title}")
+            st.write(f"***Аннотация:*** {annotation}")
+            similarity = float(similarity)
+            st.write(f"***Cosine Similarity : {round(similarity, 3)}***")
+            st.write(f"***Ссылка на блюдо : {url}***")
+
+        st.markdown(
+        "<hr style='border: 2px solid #000; margin-top: 10px; margin-bottom: 10px;'>",
+        unsafe_allow_html=True
+    )