Book recommender

examples/panel/book-recommender/README.md

@@ -0,0 +1,18 @@
+# Book Recommender
+
+To run this example you need to set the `OPENAI_API_KEY` environment variable.
+
+```bash
+export OPENAI_API_KEY=<your_api_key> 
+```
+
+Create a zip from all the files and follow the instructions for deploying a [Panel](https://docs.cloud.ploomber.io/en/latest/apps/panel.html) application.
+You also need to set `OPENAI_API_KEY` as an [environment variable](https://docs.cloud.ploomber.io/en/latest/user-guide/env-vars.html) while deploying the application.
+
+To re-generate embeddings run the below command:
+
+```bash
+python rag_book_recommender.py
+```
+
+Copy the `embeddings.json` file to the `assets/` folder.

examples/panel/book-recommender/app.py

@@ -0,0 +1,132 @@
+"""
+Demonstrates how to use the `ChatInterface` and a `callback` function to respond.
+
+The chatbot Assistant echoes back the message entered by the User.
+
+https://github.com/holoviz-topics/panel-chat-examples/blob/main/docs/examples/basics/basic_chat.py
+"""
+
+import panel as pn
+from openai import OpenAI
+from scipy.spatial import KDTree
+import numpy as np
+
+from rag_book_recommender import get_book_description_by_title, EmbeddingsStore, get_authors, get_embeddings
+
+
+client = OpenAI()
+
+pn.extension()
+
+store = EmbeddingsStore()
+all_authors = get_authors()
+
+
+def detect_author(user_query):
+    system_prompt = f"""
+    You're a system that determines the author in user query. 
+
+    You need to return only he author name.Please fix any typo if possible
+"""
+    response = client.chat.completions.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": "What are some books by Sandra Boynton"},
+            {"role": "system", "content": "Sandra Boynton"},
+            {"role": "user", "content": user_query},
+        ],
+        seed=42,
+        n=1,
+    )
+    author = response.choices[0].message.content.upper()
+    return author if author in all_authors else ""
+
+
+def book_recommender_agent(user_query, verbose=False):
+    """An agent that can retrieve news by topic and summarizes them"""
+    # determine the topic based on the query
+    embeddings_json = get_embeddings()
+    author = detect_author(user_query)
+    titles = []
+    if author:
+        titles = all_authors[author]
+        if verbose:
+            print(f"Found these titles: {titles} by author: {author}")
+
+    filtered_embeddings_by_title = {}
+    for title in titles:
+        title_embedding = embeddings_json.get(title, None)
+        if title_embedding:
+            filtered_embeddings_by_title[title] = title_embedding
+    if filtered_embeddings_by_title:
+        embeddings_json = filtered_embeddings_by_title
+
+    titles = []
+    embeddings = []
+    for key, value in embeddings_json.items():
+        if value:
+            titles.append(key)
+            embeddings.append(value)
+    kdtree = KDTree(np.array(embeddings))
+    _, indexes = kdtree.query(store.get_one(user_query), k=min(len(titles), 3))
+
+    print(type(indexes))
+    if isinstance(indexes, np.int64):
+        indexes = [indexes]
+    titles_relevant = [titles[i] for i in indexes if titles[i] != "null"]
+    print(titles_relevant)
+    descriptions_relevant = [get_book_description_by_title(title) for title in titles_relevant]
+
+    recommendation_text = ""
+    for i, value in enumerate(titles_relevant):
+        recommendation_text = f"{recommendation_text}{value}: {descriptions_relevant[i]}\n\n##"
+
+    system_prompt = f"""
+You are a helpful book recommendation system that can recommend users books based on their inputs.
+
+Here are the top relevant titles and descriptions (separated by ##) in the format titles: descriptions, 
+use these to generate your answer,
+and disregard books that are not relevant to user's input. You can display 5 or less recommendations.:
+
+{recommendation_text}
+
+You should also create a summary of the description and format the answer properly. 
+You can display a maximum of 5 recommendations.
+Please do not suggest any books outside this list.
+"""
+
+    if verbose:
+        print(f"System prompt: {system_prompt}")
+
+    response = client.chat.completions.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_query},
+        ],
+        seed=42,
+        n=1,
+    )
+
+    return response.choices[0].message.content
+
+
+def callback(contents: str, user: str, instance: pn.chat.ChatInterface):
+    return book_recommender_agent(contents)
+
+
+chat_interface = pn.chat.ChatInterface(callback=callback)
+chat_interface.send(
+    "I am a book recommendation engine! "
+    "You may ask questions like: \n* Recommend books by Dan Brown.\n"
+    "* Suggest some books based in the Victorian era.\n\n"
+    "You can deploy your own by signing up at https://ploomber.io",
+    user="System",
+    respond=False,
+)
+
+pn.template.MaterialTemplate(
+    title="Book Recommender",
+    main=[chat_interface],
+).servable()

examples/panel/book-recommender/rag_book_recommender.py

@@ -0,0 +1,89 @@
+import os
+import json
+import pickle
+import pandas as pd
+
+from pathlib import Path
+from openai import OpenAI
+
+client = OpenAI()
+
+file_path = os.path.join('assets', 'goodreads.csv')
+df = pd.read_csv(file_path)
+
+
+file_path = os.path.join('assets', 'title_to_description.pkl')
+with open(file_path, 'rb') as file:
+    DESCRIPTIONS = pickle.load(file)
+
+
+def get_authors():
+    file_path = os.path.join('assets', 'author_to_title.pkl')
+    with open(file_path, 'rb') as file:
+        authors = pickle.load(file)
+    return authors
+
+
+def get_embeddings():
+    file_path = os.path.join('assets', 'embeddings.json')
+    with open(file_path, "r", encoding="utf-8") as file:
+        embeddings_json = json.load(file)
+    return embeddings_json
+
+
+def get_book_description_by_title(title):
+    return DESCRIPTIONS[title.upper()]
+
+
+class EmbeddingsStore:
+    def __init__(self):
+        self._path = Path("embeddings_another.json")
+
+        if not self._path.exists():
+            self._data = {}
+        else:
+            self._data = json.loads(self._path.read_text())
+
+    def get_one(self, text, title=None):
+        if text in self._data:
+            return self._data[text]
+
+        try:
+            response = client.embeddings.create(input=text, model="text-embedding-3-small")
+
+            embedding = response.data[0].embedding
+
+            self._data[title] = embedding
+            self._path.write_text(json.dumps(self._data))
+
+            return embedding
+        except Exception:
+            self._data[title] = []
+            self._path.write_text(json.dumps(self._data))
+            return None
+
+    def get_many(self, content, title):
+        return [self.get_one(text, title) for text in content]
+
+    def __len__(self):
+        return len(self._data)
+
+    def clear(self):
+        if self._path.exists():
+            self._path.unlink()
+            self._data = {}
+
+
+def compute_embeddings():
+    store = EmbeddingsStore()
+    store.clear()
+
+    for index, row in df.iterrows():
+        print(f"Index: {index}")
+        store.get_one(row["description"], row["title"])
+
+
+if __name__ == "__main__":
+
+    # compute embeddings
+    compute_embeddings()

examples/panel/book-recommender/requirements.txt

@@ -0,0 +1,4 @@
+panel
+openai
+scipy
+numpy