Uploading with claude

.gitattributes

@@ -33,3 +33,5 @@ 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
+chroma_db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text
+cover-not-found.png filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,337 @@
+import os
+import pandas as pd
+import numpy as np
+import gradio as gr
+
+from langchain_community.document_loaders import TextLoader
+from langchain_text_splitters import CharacterTextSplitter
+from langchain_chroma import Chroma
+from langchain_huggingface import HuggingFaceEmbeddings
+
+
+# =========================================================
+# BASE DIRECTORY — works both locally and on HuggingFace
+# =========================================================
+
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+
+
+# =========================================================
+# EMBEDDING MODEL
+# =========================================================
+
+embedding_model = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/all-MiniLM-L6-v2"
+)
+
+
+# =========================================================
+# LOAD BOOK DATASET
+# =========================================================
+
+books = pd.read_csv(os.path.join(BASE_DIR, "books_with_emotions.csv"))
+
+
+# =========================================================
+# CLEAN CATEGORY COLUMN
+# =========================================================
+
+books["simple_categories"] = (
+    books["simple_categories"]
+    .fillna("")
+    .astype(str)
+    .str.strip()
+)
+
+
+# =========================================================
+# HANDLE THUMBNAILS
+# =========================================================
+
+books["thumbnail"] = books["thumbnail"].fillna("")
+
+books["large_thumbnail"] = np.where(
+    books["thumbnail"] != "",
+    books["thumbnail"] + "&fife=w800",
+    "cover-not-found.png"
+)
+
+
+# =========================================================
+# LOAD EXISTING VECTOR DATABASE
+# NOTE: ChromaDB files must be inside a "chroma_db" folder
+#       at the root of your HuggingFace Space repo.
+#       Required files inside chroma_db/:
+#         - chroma.sqlite3
+#         - data_level0.bin
+#         - header.bin
+#         - length.bin
+#         - link_lists.bin
+#         - index_metadata.pickle
+# =========================================================
+
+CHROMA_PATH = os.path.join(BASE_DIR, "chroma_db")
+
+db_books = Chroma(
+    persist_directory=CHROMA_PATH,
+    embedding_function=embedding_model
+)
+
+
+# =========================================================
+# RETRIEVE SEMANTIC RECOMMENDATIONS
+# =========================================================
+
+def retrieve_semantic_recommendations(
+    query: str,
+    category: str,
+    tone: str = "All",
+    initial_top_k: int = 50,
+    final_top_k: int = 16
+) -> pd.DataFrame:
+
+    recs = db_books.similarity_search(query, k=initial_top_k)
+
+    books_list = []
+
+    for rec in recs:
+        try:
+            isbn = int(rec.page_content.strip('"').split()[0])
+            books_list.append(isbn)
+        except Exception:
+            continue
+
+    # Preserve vector search order and deduplicate
+    seen = set()
+    valid_isbns = []
+
+    for isbn in books_list:
+        if isbn in books["isbn13"].values and isbn not in seen:
+            valid_isbns.append(isbn)
+            seen.add(isbn)
+
+    if len(valid_isbns) == 0:
+        return pd.DataFrame()
+
+    book_recs = (
+        books
+        .set_index("isbn13")
+        .loc[valid_isbns]
+        .reset_index()
+    )
+
+    # Category filter
+    if category != "All":
+        book_recs = book_recs[
+            book_recs["simple_categories"].str.lower()
+            == category.strip().lower()
+        ]
+
+    # Emotional tone filter
+    tone_map = {
+        "Happy": "joy",
+        "Surprising": "surprise",
+        "Angry": "anger",
+        "Suspenseful": "fear",
+        "Sad": "sadness",
+    }
+
+    if tone in tone_map:
+        book_recs = book_recs.sort_values(
+            by=tone_map[tone], ascending=False
+        )
+
+    return book_recs.head(final_top_k)
+
+
+# =========================================================
+# GENERATE HTML BOOK CARDS
+# =========================================================
+
+def recommend_books(query: str, category: str, tone: str):
+
+    if not query.strip():
+        return """
+        <div style="text-align:center; padding:50px; color:white; font-size:20px;">
+            💡 Please enter a book description to get started.
+        </div>
+        """
+
+    recommendations = retrieve_semantic_recommendations(
+        query=query,
+        category=category,
+        tone=tone
+    )
+
+    if recommendations.empty:
+        return """
+        <div style="text-align:center; padding:50px; color:white; font-size:24px;">
+            😔 No books found for this combination.
+        </div>
+        """
+
+    html = """
+    <div style="
+        display:grid;
+        grid-template-columns:repeat(auto-fill, minmax(250px, 1fr));
+        gap:25px;
+        padding:20px;
+    ">
+    """
+
+    for _, row in recommendations.iterrows():
+
+        title = str(row["title"])
+        authors = str(row["authors"])
+        description = str(row["description"])
+
+        short_description = " ".join(description.split()[:35]) + "..."
+
+        authors_split = 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 = authors
+
+        google_books_link = (
+            f"https://books.google.com/books?vid=ISBN{row['isbn13']}"
+        )
+        amazon_link = (
+            f"https://www.amazon.com/s?k={title.replace(' ', '+')}"
+        )
+
+        html += f"""
+        <div style="
+            background:#111827;
+            border-radius:20px;
+            overflow:hidden;
+            box-shadow:0 8px 20px rgba(0,0,0,0.4);
+            transition:0.3s;
+            border:1px solid #374151;
+        ">
+            <img
+                src="{row['large_thumbnail']}"
+                onerror="this.src='cover-not-found.png'"
+                style="width:100%; height:380px; object-fit:cover;"
+            >
+            <div style="padding:18px;">
+                <h3 style="color:white; margin-bottom:10px; font-size:20px; line-height:1.3;">
+                    {title}
+                </h3>
+                <p style="color:#9CA3AF; font-size:14px; margin-bottom:12px;">
+                    by {authors_str}
+                </p>
+                <p style="color:#D1D5DB; font-size:14px; line-height:1.6; margin-bottom:20px;">
+                    {short_description}
+                </p>
+                <div style="display:flex; gap:10px; flex-wrap:wrap;">
+                    <a
+                        href="{google_books_link}"
+                        target="_blank"
+                        style="
+                            background:#2563EB;
+                            color:white;
+                            padding:10px 14px;
+                            border-radius:10px;
+                            text-decoration:none;
+                            font-size:14px;
+                            font-weight:600;
+                        "
+                    >
+                        📖 Read Preview
+                    </a>
+                    <a
+                        href="{amazon_link}"
+                        target="_blank"
+                        style="
+                            background:#F59E0B;
+                            color:black;
+                            padding:10px 14px;
+                            border-radius:10px;
+                            text-decoration:none;
+                            font-size:14px;
+                            font-weight:600;
+                        "
+                    >
+                        🛒 Buy Book
+                    </a>
+                </div>
+            </div>
+        </div>
+        """
+
+    html += "</div>"
+    return html
+
+
+# =========================================================
+# DROPDOWNS
+# =========================================================
+
+categories = ["All"] + sorted(
+    books["simple_categories"]
+    .dropna()
+    .str.strip()
+    .unique()
+    .tolist()
+)
+
+tones = ["All", "Happy", "Surprising", "Angry", "Suspenseful", "Sad"]
+
+
+# =========================================================
+# GRADIO DASHBOARD
+# =========================================================
+
+with gr.Blocks(
+    theme=gr.themes.Soft(),
+    css="footer { visibility: hidden; }"
+) as dashboard:
+
+    gr.Markdown(
+        """
+        # 📚 Semantic Book Recommender
+        Discover books using AI-powered semantic search, emotional tones, and category filtering.
+        """
+    )
+
+    with gr.Row():
+        user_query = gr.Textbox(
+            label="Enter Book Description",
+            placeholder="e.g., A dark fantasy story with dragons and magic...",
+            scale=3
+        )
+        category_dropdown = gr.Dropdown(
+            choices=categories,
+            label="Select Category",
+            value="All",
+            scale=1
+        )
+        tone_dropdown = gr.Dropdown(
+            choices=tones,
+            label="Select Emotional Tone",
+            value="All",
+            scale=1
+        )
+
+    submit_button = gr.Button("🔍 Find Recommendations", variant="primary")
+    output = gr.HTML()
+
+    submit_button.click(
+        fn=recommend_books,
+        inputs=[user_query, category_dropdown, tone_dropdown],
+        outputs=output
+    )
+
+
+# =========================================================
+# RUN APP
+# =========================================================
+
+if __name__ == "__main__":
+    dashboard.launch(server_name="0.0.0.0", server_port=7860)

chroma_db/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02bf4b0a8383a8ea908ab5b62ab1aa7cfa619aa96e7fa2794bb676b70ac14e03
+size 56733696

chroma_db/e24a8b8f-9579-4d39-ac1a-5bc76ad72f57/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517624ea599acd11cd230bd1e8eef6af4e100c9ebff4bac3991fcc734b28fa29
+size 10334216

chroma_db/e24a8b8f-9579-4d39-ac1a-5bc76ad72f57/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f8be673bb4a6dae512bbd61d8bd3695e1ff2b58f3c6db6bec36547ee560f383
+size 100

chroma_db/e24a8b8f-9579-4d39-ac1a-5bc76ad72f57/index_metadata.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0788ded149a4180ca5dd98aff0a071819d865bd1618ed6328dacccc1e50127
+size 567424

chroma_db/e24a8b8f-9579-4d39-ac1a-5bc76ad72f57/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30604bc53ac00e91203093ad69fc26d7957193fa25172b07f7b82846065ca848
+size 24664

chroma_db/e24a8b8f-9579-4d39-ac1a-5bc76ad72f57/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e562cc417b517e53ab5a47774a5821bb8e3a66168e938ac6875a60df524f7df
+size 54992

requirements.txt

@@ -0,0 +1,13 @@
+gradio
+pandas
+numpy
+torch
+python-dotenv
+langchain
+langchain-community
+langchain-text-splitters
+langchain-chroma
+langchain-huggingface
+sentence-transformers
+chromadb
+transformers