Spaces:
Sleeping
Sleeping
File size: 5,716 Bytes
00b8591 |
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 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 |
import os
import pandas as pd
import numpy as np
import gc
# Environment variables (set in HF Spaces settings)
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
# -----------------------------
# LANGCHAIN IMPORTS
# -----------------------------
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import CharacterTextSplitter
from langchain_community.vectorstores import Chroma
# Gradio
import gradio as gr
print("Loading book data...")
# -----------------------------
# LOAD BOOK DATA
# -----------------------------
books = pd.read_csv("books_with_emotions.csv")
books["large_thumbnail"] = books["thumbnail"] + "&fife=w800"
books["large_thumbnail"] = np.where(
books["large_thumbnail"].isna(),
"cover-not-found.jpg",
books["large_thumbnail"],
)
print("Loading documents...")
# -----------------------------
# LOAD DOCUMENTS FOR SEMANTIC INDEX
# -----------------------------
file_path = "tagged_description.txt"
loader = TextLoader(file_path, encoding="utf-8")
raw_documents = loader.load()
print(f"Loaded {len(raw_documents)} documents")
text_splitter = CharacterTextSplitter(
separator="\n",
chunk_size=1,
chunk_overlap=0
)
documents = text_splitter.split_documents(raw_documents)
del raw_documents, loader
gc.collect()
print("Initializing embeddings model...")
# -----------------------------
# CREATE VECTOR STORE
# -----------------------------
embeddings = HuggingFaceEmbeddings(
model_name="sentence-transformers/all-MiniLM-L6-v2",
model_kwargs={'device': 'cpu'},
encode_kwargs={'normalize_embeddings': True}
)
print("Creating vector database...")
db_books = Chroma.from_documents(
documents,
embedding=embeddings,
persist_directory="./chroma_db"
)
del documents, text_splitter
gc.collect()
print("Application ready!")
def retrieve_semantic_recommendations(
query: str,
category: str = None,
tone: str = None,
initial_top_k: int = 50,
final_top_k: int = 16,
) -> pd.DataFrame:
recs = db_books.similarity_search(query, k=initial_top_k)
books_list = [int(rec.page_content.strip('"').split()[0]) for rec in recs]
book_recs = books[books["isbn13"].isin(books_list)].head(initial_top_k)
if category != "All":
book_recs = book_recs[book_recs["simple_categories"] == category].head(final_top_k)
else:
book_recs = book_recs.head(final_top_k)
if tone == "Happy":
book_recs.sort_values(by="joy", ascending=False, inplace=True)
elif tone == "Surprising":
book_recs.sort_values(by="surprise", ascending=False, inplace=True)
elif tone == "Angry":
book_recs.sort_values(by="anger", ascending=False, inplace=True)
elif tone == "Suspenseful":
book_recs.sort_values(by="fear", ascending=False, inplace=True)
elif tone == "Sad":
book_recs.sort_values(by="sadness", ascending=False, inplace=True)
return book_recs
def recommend_books(query: str, category: str, tone: str):
try:
recommendations = retrieve_semantic_recommendations(query, category, tone)
results = []
for _, row in recommendations.iterrows():
description = row["description"]
truncated_desc_split = description.split()
truncated_description = " ".join(truncated_desc_split[:30]) + "..."
authors_split = row["authors"].split(";")
if len(authors_split) == 2:
authors_str = f"{authors_split[0]} and {authors_split[1]}"
elif len(authors_split) > 2:
authors_str = f"{', '.join(authors_split[:-1])}, and {authors_split[-1]}"
else:
authors_str = row["authors"]
caption = f"{row['title']} by {authors_str}: {truncated_description}"
results.append((row["large_thumbnail"], caption))
gc.collect()
return results
except Exception as e:
print(f"Error: {e}")
return []
categories = ["All"] + sorted(books["simple_categories"].unique())
tones = ["All"] + ["Happy", "Surprising", "Angry", "Suspenseful", "Sad"]
with gr.Blocks(theme=gr.themes.Glass()) as dashboard:
gr.Markdown("# 📚 Semantic Book Recommender")
gr.Markdown("Find your next favorite book using AI-powered semantic search!")
with gr.Row():
user_query = gr.Textbox(
label="Describe the book you're looking for:",
placeholder="e.g., A story about forgiveness and redemption",
scale=2
)
with gr.Row():
category_dropdown = gr.Dropdown(
choices=categories,
label="Category:",
value="All",
scale=1
)
tone_dropdown = gr.Dropdown(
choices=tones,
label="Emotional Tone:",
value="All",
scale=1
)
submit_button = gr.Button("🔍 Find Books", variant="primary", scale=1)
gr.Markdown("## 📖 Recommendations")
output = gr.Gallery(label="Recommended Books", columns=4, rows=4, height="auto")
submit_button.click(
fn=recommend_books,
inputs=[user_query, category_dropdown, tone_dropdown],
outputs=output
)
user_query.submit(
fn=recommend_books,
inputs=[user_query, category_dropdown, tone_dropdown],
outputs=output
)
if __name__ == "__main__":
dashboard.launch() |