Upload 6 files

README.md

@@ -1,13 +1,30 @@
----
-title: Book Recommender
-emoji: 🐨
-colorFrom: pink
-colorTo: blue
-sdk: gradio
-sdk_version: 6.0.1
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Semantic Book Recommender
+emoji: 📚
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: 3.43.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+# 📚 Semantic Book Recommender
+
+An AI-powered book recommendation system that uses semantic search to find books based on your description.
+
+## Features
+
+- 🔍 Semantic search using sentence transformers
+- 🎭 Filter by emotional tone (Happy, Sad, Suspenseful, etc.)
+- 📂 Filter by category
+- 🖼️ Visual book gallery with cover images
+
+## How to Use
+
+1. Describe the type of book you're looking for
+2. Optionally select a category and emotional tone
+3. Click "Find Books" to see recommendations
+
+Built with LangChain, ChromaDB, and Gradio.

app.py

@@ -0,0 +1,178 @@
+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()

requirements.txt

@@ -0,0 +1,13 @@
+pandas==2.3.3
+numpy==1.26.4
+gradio==3.43.0
+langchain-core==0.3.63
+langchain-community==0.3.10
+langchain-huggingface==0.2.0
+langchain-text-splitters==0.3.8
+chromadb==1.3.5
+sentence-transformers==2.6.0
+transformers==4.57.1
+huggingface-hub==0.36.0
+torch
+torchvision