Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+embeddings.txt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,9 @@
+# ## Умный поиск книг
+
+## 🦸‍♂️Команда
+1. [Валерия](https://github.com/valeri2393)
+2. [Сауле]([SauleBis](https://github.com/SauleBis))
+3. [Савр](https://github.com/SavrOverSide)
+
+## 🎯 Задача 
+собрать выборку из не менее, чем 5000 аннотаций c [сайта](https://www.biblio-globus.ru/category?cid=182&pagenumber=1) и построить систему поиска наиболее подходящих под пользовательский запрос книг.

app.py

@@ -0,0 +1,135 @@
+import streamlit as st
+import pandas as pd
+import torch
+import numpy as np
+from transformers import AutoTokenizer, AutoModel
+import faiss
+from streamlit.errors import StreamlitAPIException
+import urllib.parse
+
+
+
+import os
+os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
+
+# Load model and tokenizer
+model_name = "sentence-transformers/msmarco-distilbert-base-v3"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+
+# Load data
+books = pd.read_csv('data/data_final_version.csv')
+
+MAX_LEN = 300
+
+def embed_bert_cls(text, model=model, tokenizer=tokenizer):
+    t = tokenizer(text,
+                  padding=True,
+                  truncation=True,
+                  return_tensors='pt',
+                  max_length=MAX_LEN)
+    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().squeeze()
+
+# Load embeddings
+embeddings = np.loadtxt('embeddings.txt')
+embeddings_tensor = [torch.tensor(embedding) for embedding in embeddings]
+
+# Create Faiss index
+embeddings_matrix = np.stack(embeddings)
+index = faiss.IndexFlatIP(embeddings_matrix.shape[1])
+index.add(embeddings_matrix)
+
+
+# CSS стили для заднего фона
+background_image = """
+    <style>
+    .stApp {
+        background-image: url("https://img.freepik.com/premium-photo/blur-image-book_9563-1100.jpg");
+        background-size: cover;
+        background-position: center;
+        background-repeat: no-repeat;
+    }
+    </style>
+"""
+
+# Вставляем CSS стили в приложение Streamlit
+st.markdown(background_image, unsafe_allow_html=True)
+
+
+# Вставляем CSS стили для окошка с прозрачным фоном
+transparent_title = """
+    <style>
+    .transparent-title {
+        background-color: rgba(255, 255, 255, 0.7);
+        padding: 10px;
+        border-radius: 5px;
+        box-shadow: 0px 0px 10px rgba(0, 0, 0, 0.1);
+    }
+    </style>
+"""
+
+transparent_box = """
+    <style>
+    .transparent-box {
+        background-color: rgba(255, 255, 255, 0.7);
+        padding: 10px;
+        border-radius: 5px;
+        box-shadow: 0px 0px 10px rgba(0, 0, 0, 0.1);
+    }
+    </style>
+"""
+
+# Вставляем CSS стили в приложение Streamlit
+st.markdown(transparent_title, unsafe_allow_html=True)
+st.markdown(transparent_box, unsafe_allow_html=True)
+
+# Streamlit interface
+st.markdown('<h1 class="transparent-title">🎓📚Приложение для рекомендаций книг📚🎓</h1>', unsafe_allow_html=True)
+
+# Далее ваш код Streamlit
+text = st.text_input('Введите ваш запрос для поиска книг:')
+num_results = st.number_input('Количество результатов:', min_value=1, max_value=20, value=3)
+recommend_button = st.button('Получить рекомендации')
+
+
+if text and recommend_button:  # Check if the user entered text and clicked the button
+
+    # Embed the query and search for nearest vectors using Faiss
+    query_embedding = embed_bert_cls(text)
+    query_embedding = query_embedding.numpy().astype('float32')
+    _, indices = index.search(np.expand_dims(query_embedding, axis=0), num_results)
+
+    st.subheader('Рекомендации по вашему запросу:')
+    for i in indices[0]:
+        recommended_embedding = embeddings_tensor[i].numpy()  # Vector of the recommended book
+        similarity = np.dot(query_embedding, recommended_embedding) / (np.linalg.norm(query_embedding) * np.linalg.norm(recommended_embedding))  # Cosine similarity
+        similarity_percent = similarity * 100
+
+        col1, col2 = st.columns([1, 3])
+        with col1:
+            image_url = books['image_url'][i]
+            if pd.isna(image_url) or not image_url or image_url.strip() == '':
+                st.write("Обложка не найдена")
+            else:
+                try:
+                    st.image(image_url, use_column_width=True)
+                except Exception as e:
+                    st.write("Обложка не найдена")
+                    st.write(e)
+
+        with col2:
+            # Выводим информацию о книге на прозрачном фоне
+            st.markdown(f"""
+                <div class="transparent-box">
+                    <p><b>Название книги:</b> {books['title'][i]}</p>
+                    <p><b>Автор:</b> {books['author'][i]}</p>
+                    <p><b>Описание:</b>{books['annotation'][i]}")
+                    <p><b>Оценка сходства:</b> {similarity_percent:.2f}%</p>
+                </div>
+            """, unsafe_allow_html=True)
+
+        st.write("---")

embeddings.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72371c6be3b7ad73af2f3dcc03c00c1f86d1b341385b0778156f8b8a83d3977c
+size 30783658

requirements.txt

@@ -0,0 +1,56 @@
+altair==5.3.0
+attrs==23.2.0
+blinker==1.8.2
+cachetools==5.3.3
+certifi==2024.7.4
+charset-normalizer==3.3.2
+click==8.1.7
+faiss-cpu==1.8.0.post1
+filelock==3.15.4
+fsspec==2024.6.1
+gitdb==4.0.11
+GitPython==3.1.43
+huggingface-hub==0.23.4
+idna==3.7
+Jinja2==3.1.4
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.3
+numpy==1.26.4
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+protobuf==5.27.2
+pyarrow==16.1.0
+pydeck==0.9.1
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+regex==2024.5.15
+requests==2.32.3
+rich==13.7.1
+rpds-py==0.19.0
+safetensors==0.4.3
+six==1.16.0
+smmap==5.0.1
+streamlit==1.36.0
+sympy==1.13.0
+tenacity==8.5.0
+tokenizers==0.19.1
+toml==0.10.2
+toolz==0.12.1
+torch==2.3.1
+torchaudio==2.3.1
+torchvision==0.18.1
+tornado==6.4.1
+tqdm==4.66.4
+transformers==4.42.4
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2