initialize project

app.py

@@ -0,0 +1,123 @@
+import os
+import hashlib
+
+import pandas as pd
+from openai import OpenAI
+import gradio as gr
+
+input_file = "profile-generation/data/sample_gpg_data.jsonl"
+user_df = pd.read_json(input_file, lines=True)
+
+user_ids = user_df["user_id"].unique().tolist()
+client = OpenAI(api_key=os.environ.get('OPENAI_API_KEY'))
+
+
+# Simple in-memory cache
+guidance_cache = {}
+profile_cache = {}
+
+def hash_titles(titles):
+    joined = "\n".join(sorted(titles))
+    return hashlib.md5(joined.encode("utf-8")).hexdigest()
+
+def get_books(user_id):
+    if user_id is None:
+        return "Please select a user.", pd.DataFrame(), ""
+
+    user_info = user_df.loc[user_df["user_id"] == user_id]
+    print(user_info)
+    books_list = user_df.loc[user_df["user_id"] == user_id, "purchased_books"].values
+    if len(books_list) == 0:
+        return f"No books found for {user_id}.", pd.DataFrame(), ""
+
+    books = books_list[0]
+    df = pd.DataFrame(books)
+    df = df[['title', 'author', 'categories']].rename(columns={'title': 'Title', 'author': 'Author', 'categories': 'Category'})
+    books_info = generate_books(books_list)
+    titles = [book["title"] for book in books if "title" in book]
+
+    cache_key = hash_titles(titles)
+
+    if cache_key in guidance_cache:
+        guidance_response = guidance_cache[cache_key]
+        profile_response = profile_cache[cache_key]
+        print("✅ Using cached response")
+    else:
+        print("🧠 Calling OpenAI API")
+        guidance_prompt_str = guidance_prompt(books_info)
+        guidance_response = client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": guidance_prompt_str}],
+            temperature=0.3,
+            max_tokens=150
+        ).choices[0].message.content.strip()
+        guidance_cache[cache_key] = guidance_response
+        profile_response = client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "user", "content": profile_prompt(books_info, guidance_response)}
+            ],
+            temperature=0.3,
+            max_tokens=150
+        ).choices[0].message.content.strip()
+        profile_cache[cache_key] = profile_response
+        candidates_options = user_info.get("candidate_options", [])
+        rec_prompt = build_recommendation_prompt(profile_response, candidates_options)
+        choice = extract_choice(rec_prompt)
+        predicted_book = candidates_options.values[choice-1] if choice and 1 <= choice <= len(candidates_options) else None
+        target_book = user_info.get("target_asin", '')
+        print("target_book:", target_book)
+    return f"{user_id}", df, guidance_response, profile_response, rec_prompt, pd.DataFrame(candidates_options.values[0]), target_book.values, predicted_book[0]['asin']
+
+def extract_choice(response_text):
+    for token in response_text.split():
+        if token.strip("[]").isdigit():
+            return int(token.strip("[]"))
+    return None
+
+def generate_books(books):
+    book_combos = []
+    for book in books:
+        categories = ', '.join(book[0]['categories'])
+        book_combos.append(f"Title of the book is {book[0]['title']} and the category of the book is {categories}. Description of the book is {book[0]['description']}")
+    return book_combos
+
+def guidance_prompt(titles):
+    return f"""Here is a list of books a person has read:\n{chr(10).join("- " + t for t in titles)}\n\nWhat genres or themes do you notice across these books? Please list them concisely."""
+
+def profile_prompt(titles, guidance):
+    return f"""Here is a list of books a person has read:\n{chr(10).join("- " + t for t in titles)}\n\nBased on the following genres/themes: {guidance}\n\nSummarize this person's book preferences in one paragraph."""
+
+def build_recommendation_prompt(profile, candidates):
+    prompt = f"""A user has the following reading preference:\n"{profile}"\n\nHere are some books they might consider next:\n"""
+    for i, book in enumerate(candidates, start=1):
+        prompt += f"[{i}] {book[0].get('title', 'Unknown Title')}\n"
+    prompt += "\nWhich of these books best matches the user's preference? Respond ONLY with the number [1-4]."
+    return prompt
+
+
+def get_books_theme(books):
+    return
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Select User")
+    user_dropdown = gr.Dropdown(choices=user_df["user_id"].tolist(), value=None, label="User ID")
+
+    gr.Markdown("## Selected User")
+    output_text = gr.Textbox(show_label=False)
+    gr.Markdown("## Books read")
+    output_table = gr.Dataframe(label="Books Read", interactive=False, show_label=False)
+    gr.Markdown("## User Books Theme")
+    output_theme = gr.Textbox(label="User Books Theme", lines=8, show_label=False)
+    gr.Markdown("## User Profile")
+    output_profile = gr.Textbox(label="User Profile", show_label=False, lines=6)
+    output_rec_prompt = gr.Textbox(label="Recommendation Prompt")
+    output_candidate_options = gr.DataFrame(label="Candidate Books")
+    output_target_id = gr.Textbox(label="Target Book")
+    output_predicted_book = gr.Textbox(label="Predicted Book")
+    
+    user_dropdown.change(fn=get_books, inputs=user_dropdown, outputs=[output_text, output_table, output_theme, output_profile, output_rec_prompt, output_candidate_options, output_target_id, output_predicted_book])
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+pandas
+openai