Tutorial_MainHackathon-LangChainOnly2024.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "da36da01-8f0d-4db8-a7a7-732b4757dde1",
   "metadata": {},
   "source": [
    "## LauzHack 2024 Mini hackathon on LLMs - Intro to LLM agent APIs\n",
    "Luca Fusar Bassini"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "2d0abc3d-7161-4d95-8d06-e1bb1486e745",
   "metadata": {},
   "outputs": [],
   "source": [
    "### old imports with other cool stuff, code will be made available\n",
    "\n",
    "# for an application example of this collection of APIs, see our project PaperBoat, currently under dev here: https://github.com/JBil8/paperboat/tree/jacopo\n",
    "# environment api-hackathon\n",
    "\n",
    "# tutorial copypasted and edited from various online resources! not mine :) could be quite outdated now, as i made this notebook in October 2023\n",
    "\n",
    "import requests\n",
    "from flask import Flask, request, Response\n",
    "#from scihub import SciHub\n",
    "import os\n",
    "import re\n",
    "import random\n",
    "import json\n",
    "import datetime\n",
    "from bs4 import BeautifulSoup\n",
    "from pyzotero import zotero\n",
    "from google.cloud import texttospeech as tts\n",
    "import wave\n",
    "import langchain\n",
    "from crossref.restful import Works\n",
    "from semanticscholar import SemanticScholar\n",
    "import torch\n",
    "from transformers import AutoModel, AutoTokenizer\n",
    "import numpy as np\n",
    "import scipy\n",
    "import matplotlib.pyplot as plt\n",
    "from typing import Sequence\n",
    "import openai\n",
    "import pandas as pd\n",
    "import tiktoken\n",
    "from openai.embeddings_utils import get_embedding\n",
    "from dotenv import load_dotenv, find_dotenv\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "import langchain\n",
    "from langchain_experimental.agents.agent_toolkits import create_python_agent\n",
    "from langchain.agents import load_tools, initialize_agent\n",
    "from langchain.agents import AgentType\n",
    "from langchain_experimental.tools.python.tool import PythonREPLTool\n",
    "from langchain.python import PythonREPL\n",
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.agents import tool\n",
    "from datetime import date\n",
    "from dotenv import load_dotenv, find_dotenv\n",
    "from semanticscholar import SemanticScholar"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1e4cabf8-6eef-471b-93e7-b1f9eb957b05",
   "metadata": {},
   "outputs": [],
   "source": [
    "# note: a few useful links\n",
    "# https://learn.deeplearning.ai/\n",
    "# https://platform.openai.com/docs/plugins/examples\n",
    "# https://python.langchain.com/docs/additional_resources/tutorials\n",
    "# https://github.com/openai/chatgpt-retrieval-plugin\n",
    "# https://cookbook.openai.com/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c85e0b7f-1046-49db-8316-40cf8f8db1d1",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# read in all the API keys\n",
    "\n",
    "# OpenAI\n",
    "try:\n",
    "    with open('openai_key.txt', 'r') as file:\n",
    "        openai_key = file.read()\n",
    "except Exception as e:\n",
    "        print(e)\n",
    "        \n",
    "try:\n",
    "    with open('pinecone_key.txt', 'r') as file:\n",
    "        pineconekey = file.read()\n",
    "except Exception as e:\n",
    "        print(e)\n",
    "\n",
    "# Telegram\n",
    "try:\n",
    "    with open('telegram_key.txt', 'r') as file:\n",
    "        TOKEN = file.read()\n",
    "except Exception as e:\n",
    "        print(e)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "292e83ff-8407-422c-8669-064f2a943ee9",
   "metadata": {},
   "outputs": [],
   "source": [
    "openai.api_key = openai_key"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "561751c2-7650-493a-9153-796260e38dfd",
   "metadata": {},
   "outputs": [],
   "source": [
    "mykey = openai_key"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4fdb3ccc-c19d-47d2-8c12-1be3336fa521",
   "metadata": {},
   "source": [
    "## Agents: ChatGPT + LangChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "41e838d8-3567-4326-80fd-29eb8613560d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# langchain: agents that can search the web\n",
    "llm_model = \"gpt-3.5-turbo\"\n",
    "\n",
    "# create an instance of ChatGPT\n",
    "llm = ChatOpenAI(temperature=0, model=llm_model, openai_api_key=mykey)\n",
    "\n",
    "# parse useful tools, eg, Wikipedia, that the \"agent\" can use\n",
    "tools = load_tools([\"llm-math\",\"wikipedia\"], llm=llm)\n",
    "\n",
    "agent= initialize_agent(\n",
    "    tools, \n",
    "    llm, \n",
    "    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
    "    handle_parsing_errors=True,\n",
    "    verbose = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "be95855f-4c24-4d2a-b206-7a92a35a9a06",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: We can use the Calculator tool to find 25% of 300.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Calculator\",\n",
      "  \"action_input\": \"25% of 300\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 75.0\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer\n",
      "\n",
      "Final Answer: 75.0\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'What is the 25% of 300?', 'output': '75.0'}"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent(\"What is the 25% of 300?\") # look how cool is the behind the scenes to build new tools..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5110f98f-9452-4895-8283-40ecda281c06",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I should use Wikipedia to find out which book Tom M. Mitchell wrote.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Wikipedia\",\n",
      "  \"action_input\": \"Tom M. Mitchell\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mPage: Tom M. Mitchell\n",
      "Summary: Tom Michael Mitchell (born August 9, 1951) is an American computer scientist and the Founders University Professor at Carnegie Mellon University (CMU). He is a founder and former Chair of the Machine Learning Department at CMU. Mitchell is known for his contributions to the advancement of machine learning, artificial intelligence, and cognitive neuroscience and is the author of the textbook Machine Learning. He is a member of the United States National Academy of Engineering since 2010. He is also a Fellow of the American Academy of Arts and Sciences, the American Association for the Advancement of Science and a Fellow and past President of the Association for the Advancement of Artificial Intelligence. In October 2018, Mitchell was appointed as the Interim Dean of the School of Computer Science at Carnegie Mellon.\n",
      "\n",
      "\n",
      "\n",
      "Page: Tom Mitchell (Australian footballer)\n",
      "Summary: Thomas Mitchell (born 31 May 1993) is a professional Australian rules footballer playing for the Collingwood Football Club in the Australian Football League (AFL). He previously played for the Sydney Swans from 2012 to 2016, and the Hawthorn Football Club between 2017 and 2022. Mitchell won the Brownlow Medal as the league's best and fairest player in 2018 and set the record for the most disposals in a VFL/AFL match, accruing 54 in a game against Collingwood during that season. Whom he would later join in 2023, en route to winning the 2023 AFL Grand Final and his first AFL premiership.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI should use Wikipedia to confirm the book written by Tom M. Mitchell.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Wikipedia\",\n",
      "  \"action_input\": \"Machine Learning (book)\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mPage: Machine learning\n",
      "Summary: Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Recently, artificial neural networks have been able to surpass many previous approaches in performance.Machine learning approaches have been applied to many fields including natural language processing, computer vision, speech recognition, email filtering, agriculture, and medicine. ML is known in its application across business problems under the name predictive analytics. Although not all machine learning is statistically based, computational statistics is an important source of the field's methods.\n",
      "The mathematical foundations of ML are provided by mathematical optimization (mathematical programming) methods. Data mining is a related (parallel) field of study, focusing on exploratory data analysis (EDA) through unsupervised learning.From a theoretical viewpoint, probably approximately correct (PAC) learning provides a framework for describing machine learning.\n",
      "\n",
      "Page: Quantum machine learning\n",
      "Summary: Quantum machine learning is the integration of quantum algorithms within machine learning programs.The most common use of the term refers to machine learning algorithms for the analysis of classical data executed on a quantum computer, i.e. quantum-enhanced machine learning. While machine learning algorithms are used to compute immense quantities of data, quantum machine learning utilizes qubits and quantum operations or specialized quantum systems to improve computational speed and data storage done by algorithms in a program. This includes hybrid methods that involve both classical and quantum processing, where computationally difficult subroutines are outsourced to a quantum device. These routines can be more complex in nature and executed faster on a quantum computer. Furthermore, quantum algorithms can be used to analyze quantum states instead of classical data.Beyond quantum computing, the term \"quantum machine learning\" is also associated with classical machine learning methods applied to data generated from quantum experiments (i.e. machine learning of quantum systems), such as learning the phase transitions of a quantum system or creating new quantum experiments.Quantum machine learning also extends to a branch of research that explores methodological and structural similarities between certain physical systems and learning systems, in particular neural networks. For example, some mathematical and numerical techniques from quantum physics are applicable to classical deep learning and vice versa.Furthermore, researchers investigate more abstract notions of learning theory with respect to quantum information, sometimes referred to as \"quantum learning theory\".\n",
      "\n",
      "Page: Timeline of machine learning\n",
      "Summary: This page is a timeline of machine learning. Major discoveries, achievements, milestones and other major events in machine learning are included.\n",
      "\n",
      "\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI should use Wikipedia to find out the book written by Tom M. Mitchell.\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Wikipedia\",\n",
      "  \"action_input\": \"Tom M. Mitchell\"\n",
      "}\n",
      "```\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mPage: Tom M. Mitchell\n",
      "Summary: Tom Michael Mitchell (born August 9, 1951) is an American computer scientist and the Founders University Professor at Carnegie Mellon University (CMU). He is a founder and former Chair of the Machine Learning Department at CMU. Mitchell is known for his contributions to the advancement of machine learning, artificial intelligence, and cognitive neuroscience and is the author of the textbook Machine Learning. He is a member of the United States National Academy of Engineering since 2010. He is also a Fellow of the American Academy of Arts and Sciences, the American Association for the Advancement of Science and a Fellow and past President of the Association for the Advancement of Artificial Intelligence. In October 2018, Mitchell was appointed as the Interim Dean of the School of Computer Science at Carnegie Mellon.\n",
      "\n",
      "\n",
      "\n",
      "Page: Tom Mitchell (Australian footballer)\n",
      "Summary: Thomas Mitchell (born 31 May 1993) is a professional Australian rules footballer playing for the Collingwood Football Club in the Australian Football League (AFL). He previously played for the Sydney Swans from 2012 to 2016, and the Hawthorn Football Club between 2017 and 2022. Mitchell won the Brownlow Medal as the league's best and fairest player in 2018 and set the record for the most disposals in a VFL/AFL match, accruing 54 in a game against Collingwood during that season. Whom he would later join in 2023, en route to winning the 2023 AFL Grand Final and his first AFL premiership.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer\n",
      "\n",
      "Final Answer: The book written by Tom M. Mitchell is \"Machine Learning.\"\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "question = \"Tom M. Mitchell is an American computer scientist \\\n",
    "and the Founders University Professor at Carnegie Mellon University (CMU)\\\n",
    "what book did he write?\"\n",
    "result = agent(question) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "64bbef5c-1cf9-421e-ad63-14982735b556",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Python REPL can execute arbitrary code. Use with caution.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3mWe can use the `sorted()` function in Python to sort the list of customers based on last name first and then first name.\n",
      "Action: Python_REPL\n",
      "Action Input: customers = [['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']]\n",
      "sorted_customers = sorted(customers, key=lambda x: (x[1], x[0]))\n",
      "print(sorted_customers)\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m[['Jen', 'Ayai'], ['Lang', 'Chain'], ['Harrison', 'Chase'], ['Elle', 'Elem'], ['Trance', 'Former'], ['Geoff', 'Fusion'], ['Dolly', 'Too']]\n",
      "\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mThe customers have been sorted by last name and then first name.\n",
      "Final Answer: [['Jen', 'Ayai'], ['Lang', 'Chain'], ['Harrison', 'Chase'], ['Elle', 'Elem'], ['Trance', 'Former'], ['Geoff', 'Fusion'], ['Dolly', 'Too']]\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"[['Jen', 'Ayai'], ['Lang', 'Chain'], ['Harrison', 'Chase'], ['Elle', 'Elem'], ['Trance', 'Former'], ['Geoff', 'Fusion'], ['Dolly', 'Too']]\""
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# make an agent that can write and EXECUTE inside it freshly-written, dynamic Python code!\n",
    "agent = create_python_agent(\n",
    "    llm,\n",
    "    tool=PythonREPLTool(),\n",
    "    verbose=True\n",
    ")\n",
    "\n",
    "customer_list = [[\"Harrison\", \"Chase\"], \n",
    "                 [\"Lang\", \"Chain\"],\n",
    "                 [\"Dolly\", \"Too\"],\n",
    "                 [\"Elle\", \"Elem\"], \n",
    "                 [\"Geoff\",\"Fusion\"], \n",
    "                 [\"Trance\",\"Former\"],\n",
    "                 [\"Jen\",\"Ayai\"]\n",
    "                ]\n",
    "\n",
    "agent.run(f\"\"\"Sort these customers by \\\n",
    "last name and then first name \\\n",
    "and print the output: {customer_list}\"\"\") "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "90560fd4-4594-4be3-97e5-156f3a884872",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32;1m\u001b[1;3m[chain/start]\u001b[0m \u001b[1m[1:chain:AgentExecutor] Entering Chain run with input:\n",
      "\u001b[0m{\n",
      "  \"input\": \"Sort these customers by last name and then first name and print the output: [['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']]\"\n",
      "}\n",
      "\u001b[32;1m\u001b[1;3m[chain/start]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 2:chain:LLMChain] Entering Chain run with input:\n",
      "\u001b[0m{\n",
      "  \"input\": \"Sort these customers by last name and then first name and print the output: [['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']]\",\n",
      "  \"agent_scratchpad\": \"\",\n",
      "  \"stop\": [\n",
      "    \"\\nObservation:\",\n",
      "    \"\\n\\tObservation:\"\n",
      "  ]\n",
      "}\n",
      "\u001b[32;1m\u001b[1;3m[llm/start]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 2:chain:LLMChain > 3:llm:ChatOpenAI] Entering LLM run with input:\n",
      "\u001b[0m{\n",
      "  \"prompts\": [\n",
      "    \"Human: You are an agent designed to write and execute python code to answer questions.\\nYou have access to a python REPL, which you can use to execute python code.\\nIf you get an error, debug your code and try again.\\nOnly use the output of your code to answer the question. \\nYou might know the answer without running any code, but you should still run the code to get the answer.\\nIf it does not seem like you can write code to answer the question, just return \\\"I don't know\\\" as the answer.\\n\\n\\nPython_REPL: A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Python_REPL]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Sort these customers by last name and then first name and print the output: [['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']]\\nThought:\"\n",
      "  ]\n",
      "}\n",
      "\u001b[36;1m\u001b[1;3m[llm/end]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 2:chain:LLMChain > 3:llm:ChatOpenAI] [1.92s] Exiting LLM run with output:\n",
      "\u001b[0m{\n",
      "  \"generations\": [\n",
      "    [\n",
      "      {\n",
      "        \"text\": \"We can use the `sorted()` function in Python to sort the list of customers based on their last name and then first name.\\nAction: Python_REPL\\nAction Input: sorted([['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']], key=lambda x: (x[1], x[0]))\",\n",
      "        \"generation_info\": {\n",
      "          \"finish_reason\": \"stop\"\n",
      "        },\n",
      "        \"type\": \"ChatGeneration\",\n",
      "        \"message\": {\n",
      "          \"lc\": 1,\n",
      "          \"type\": \"constructor\",\n",
      "          \"id\": [\n",
      "            \"langchain\",\n",
      "            \"schema\",\n",
      "            \"messages\",\n",
      "            \"AIMessage\"\n",
      "          ],\n",
      "          \"kwargs\": {\n",
      "            \"content\": \"We can use the `sorted()` function in Python to sort the list of customers based on their last name and then first name.\\nAction: Python_REPL\\nAction Input: sorted([['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']], key=lambda x: (x[1], x[0]))\",\n",
      "            \"additional_kwargs\": {}\n",
      "          }\n",
      "        }\n",
      "      }\n",
      "    ]\n",
      "  ],\n",
      "  \"llm_output\": {\n",
      "    \"token_usage\": {\n",
      "      \"prompt_tokens\": 328,\n",
      "      \"completion_tokens\": 101,\n",
      "      \"total_tokens\": 429\n",
      "    },\n",
      "    \"model_name\": \"gpt-3.5-turbo\"\n",
      "  },\n",
      "  \"run\": null\n",
      "}\n",
      "\u001b[36;1m\u001b[1;3m[chain/end]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 2:chain:LLMChain] [1.92s] Exiting Chain run with output:\n",
      "\u001b[0m{\n",
      "  \"text\": \"We can use the `sorted()` function in Python to sort the list of customers based on their last name and then first name.\\nAction: Python_REPL\\nAction Input: sorted([['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']], key=lambda x: (x[1], x[0]))\"\n",
      "}\n",
      "\u001b[32;1m\u001b[1;3m[tool/start]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 4:tool:Python_REPL] Entering Tool run with input:\n",
      "\u001b[0m\"sorted([['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']], key=lambda x: (x[1], x[0]))\"\n",
      "\u001b[36;1m\u001b[1;3m[tool/end]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 4:tool:Python_REPL] [3ms] Exiting Tool run with output:\n",
      "\u001b[0m\"\"\n",
      "\u001b[32;1m\u001b[1;3m[chain/start]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 5:chain:LLMChain] Entering Chain run with input:\n",
      "\u001b[0m{\n",
      "  \"input\": \"Sort these customers by last name and then first name and print the output: [['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']]\",\n",
      "  \"agent_scratchpad\": \"We can use the `sorted()` function in Python to sort the list of customers based on their last name and then first name.\\nAction: Python_REPL\\nAction Input: sorted([['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']], key=lambda x: (x[1], x[0]))\\nObservation: \\nThought:\",\n",
      "  \"stop\": [\n",
      "    \"\\nObservation:\",\n",
      "    \"\\n\\tObservation:\"\n",
      "  ]\n",
      "}\n",
      "\u001b[32;1m\u001b[1;3m[llm/start]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 5:chain:LLMChain > 6:llm:ChatOpenAI] Entering LLM run with input:\n",
      "\u001b[0m{\n",
      "  \"prompts\": [\n",
      "    \"Human: You are an agent designed to write and execute python code to answer questions.\\nYou have access to a python REPL, which you can use to execute python code.\\nIf you get an error, debug your code and try again.\\nOnly use the output of your code to answer the question. \\nYou might know the answer without running any code, but you should still run the code to get the answer.\\nIf it does not seem like you can write code to answer the question, just return \\\"I don't know\\\" as the answer.\\n\\n\\nPython_REPL: A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Python_REPL]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Sort these customers by last name and then first name and print the output: [['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']]\\nThought:We can use the `sorted()` function in Python to sort the list of customers based on their last name and then first name.\\nAction: Python_REPL\\nAction Input: sorted([['Harrison', 'Chase'], ['Lang', 'Chain'], ['Dolly', 'Too'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Jen', 'Ayai']], key=lambda x: (x[1], x[0]))\\nObservation: \\nThought:\"\n",
      "  ]\n",
      "}\n",
      "\u001b[36;1m\u001b[1;3m[llm/end]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 5:chain:LLMChain > 6:llm:ChatOpenAI] [1.70s] Exiting LLM run with output:\n",
      "\u001b[0m{\n",
      "  \"generations\": [\n",
      "    [\n",
      "      {\n",
      "        \"text\": \"I now know the final answer\\nFinal Answer: [['Jen', 'Ayai'], ['Harrison', 'Chase'], ['Lang', 'Chain'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Dolly', 'Too']]\",\n",
      "        \"generation_info\": {\n",
      "          \"finish_reason\": \"stop\"\n",
      "        },\n",
      "        \"type\": \"ChatGeneration\",\n",
      "        \"message\": {\n",
      "          \"lc\": 1,\n",
      "          \"type\": \"constructor\",\n",
      "          \"id\": [\n",
      "            \"langchain\",\n",
      "            \"schema\",\n",
      "            \"messages\",\n",
      "            \"AIMessage\"\n",
      "          ],\n",
      "          \"kwargs\": {\n",
      "            \"content\": \"I now know the final answer\\nFinal Answer: [['Jen', 'Ayai'], ['Harrison', 'Chase'], ['Lang', 'Chain'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Dolly', 'Too']]\",\n",
      "            \"additional_kwargs\": {}\n",
      "          }\n",
      "        }\n",
      "      }\n",
      "    ]\n",
      "  ],\n",
      "  \"llm_output\": {\n",
      "    \"token_usage\": {\n",
      "      \"prompt_tokens\": 435,\n",
      "      \"completion_tokens\": 61,\n",
      "      \"total_tokens\": 496\n",
      "    },\n",
      "    \"model_name\": \"gpt-3.5-turbo\"\n",
      "  },\n",
      "  \"run\": null\n",
      "}\n",
      "\u001b[36;1m\u001b[1;3m[chain/end]\u001b[0m \u001b[1m[1:chain:AgentExecutor > 5:chain:LLMChain] [1.71s] Exiting Chain run with output:\n",
      "\u001b[0m{\n",
      "  \"text\": \"I now know the final answer\\nFinal Answer: [['Jen', 'Ayai'], ['Harrison', 'Chase'], ['Lang', 'Chain'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Dolly', 'Too']]\"\n",
      "}\n",
      "\u001b[36;1m\u001b[1;3m[chain/end]\u001b[0m \u001b[1m[1:chain:AgentExecutor] [3.63s] Exiting Chain run with output:\n",
      "\u001b[0m{\n",
      "  \"output\": \"[['Jen', 'Ayai'], ['Harrison', 'Chase'], ['Lang', 'Chain'], ['Elle', 'Elem'], ['Geoff', 'Fusion'], ['Trance', 'Former'], ['Dolly', 'Too']]\"\n",
      "}\n"
     ]
    }
   ],
   "source": [
    "# inspect the full behind the scenes - this is slow\n",
    "langchain.debug=True\n",
    "agent.run(f\"\"\"Sort these customers by \\\n",
    "last name and then first name \\\n",
    "and print the output: {customer_list}\"\"\") \n",
    "langchain.debug=False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "95dd3141-5699-48a8-8540-88fbc688442e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I should use the `time` tool to find out today's date.\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"time\",\n",
      "  \"action_input\": \"\"\n",
      "}\n",
      "```\n",
      "\n",
      "\u001b[0m\n",
      "Observation: \u001b[38;5;200m\u001b[1;3m2024-04-16\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mFinal Answer: 2024-04-16\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "# building langchain agents/tools with prompting \n",
    "\n",
    "@tool\n",
    "def time(text: str) -> str:\n",
    "    \"\"\"Returns todays date, use this for any \\\n",
    "    questions related to knowing todays date. \\\n",
    "    The input should always be an empty string, \\\n",
    "    and this function will always return todays \\\n",
    "    date - any date mathmatics should occur \\\n",
    "    outside this function.\"\"\"\n",
    "    return str(date.today())\n",
    "\n",
    "agent= initialize_agent(\n",
    "    tools + [time], \n",
    "    llm, \n",
    "    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
    "    handle_parsing_errors=True,\n",
    "    verbose = True)\n",
    "\n",
    "try:\n",
    "    result = agent(\"whats the date today?\") \n",
    "except: \n",
    "    print(\"exception on external access\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9fe0141c-1bd2-499a-83bf-540651cf8a04",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "a92fe874-ab1c-4e0c-ac68-7ec0ae7437f5",
   "metadata": {},
   "source": [
    "## Structuring ChatGPT's \"reasoning chain\" & prompting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "cf786d36-02be-4f46-aada-b2ca6794a0f6",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Step 1:#### The user is comparing the prices of two specific products.\n",
      "Step 2:#### The user is comparing the BlueWave Chromebook and the TechPro Desktop.\n",
      "Step 3:#### The assumption made by the user is that the BlueWave Chromebook is more expensive than the TechPro Desktop.\n",
      "Step 4:#### The TechPro Desktop is priced at $999.99, and the BlueWave Chromebook is priced at $249.99. Therefore, the BlueWave Chromebook is $750 cheaper than the TechPro Desktop.\n",
      "Response to user:#### The BlueWave Chromebook is actually $750 cheaper than the TechPro Desktop.\n"
     ]
    }
   ],
   "source": [
    "# \"chain-of-thought\" prompting: structuring LLM's activity to resemble human reasoning at structured tasks involving language\n",
    "# note how you can use prompting creatively\n",
    "\n",
    "def get_completion_from_messages(messages, \n",
    "                                 model=\"gpt-3.5-turbo\", \n",
    "                                 temperature=0, max_tokens=500):\n",
    "    response = openai.ChatCompletion.create(\n",
    "        model=model,\n",
    "        messages=messages,\n",
    "        temperature=temperature, \n",
    "        max_tokens=max_tokens, \n",
    "    )\n",
    "    return response.choices[0].message[\"content\"]\n",
    "\n",
    "delimiter = \"####\"\n",
    "system_message = f\"\"\"\n",
    "Follow these steps to answer the customer queries.\n",
    "The customer query will be delimited with four hashtags,\\\n",
    "i.e. {delimiter}. \n",
    "\n",
    "Step 1:{delimiter} First decide whether the user is \\\n",
    "asking a question about a specific product or products. \\\n",
    "Product cateogry doesn't count. \n",
    "\n",
    "Step 2:{delimiter} If the user is asking about \\\n",
    "specific products, identify whether \\\n",
    "the products are in the following list.\n",
    "All available products: \n",
    "1. Product: TechPro Ultrabook\n",
    "   Category: Computers and Laptops\n",
    "   Brand: TechPro\n",
    "   Model Number: TP-UB100\n",
    "   Warranty: 1 year\n",
    "   Rating: 4.5\n",
    "   Features: 13.3-inch display, 8GB RAM, 256GB SSD, Intel Core i5 processor\n",
    "   Description: A sleek and lightweight ultrabook for everyday use.\n",
    "   Price: $799.99\n",
    "\n",
    "2. Product: BlueWave Gaming Laptop\n",
    "   Category: Computers and Laptops\n",
    "   Brand: BlueWave\n",
    "   Model Number: BW-GL200\n",
    "   Warranty: 2 years\n",
    "   Rating: 4.7\n",
    "   Features: 15.6-inch display, 16GB RAM, 512GB SSD, NVIDIA GeForce RTX 3060\n",
    "   Description: A high-performance gaming laptop for an immersive experience.\n",
    "   Price: $1199.99\n",
    "\n",
    "3. Product: PowerLite Convertible\n",
    "   Category: Computers and Laptops\n",
    "   Brand: PowerLite\n",
    "   Model Number: PL-CV300\n",
    "   Warranty: 1 year\n",
    "   Rating: 4.3\n",
    "   Features: 14-inch touchscreen, 8GB RAM, 256GB SSD, 360-degree hinge\n",
    "   Description: A versatile convertible laptop with a responsive touchscreen.\n",
    "   Price: $699.99\n",
    "\n",
    "4. Product: TechPro Desktop\n",
    "   Category: Computers and Laptops\n",
    "   Brand: TechPro\n",
    "   Model Number: TP-DT500\n",
    "   Warranty: 1 year\n",
    "   Rating: 4.4\n",
    "   Features: Intel Core i7 processor, 16GB RAM, 1TB HDD, NVIDIA GeForce GTX 1660\n",
    "   Description: A powerful desktop computer for work and play.\n",
    "   Price: $999.99\n",
    "\n",
    "5. Product: BlueWave Chromebook\n",
    "   Category: Computers and Laptops\n",
    "   Brand: BlueWave\n",
    "   Model Number: BW-CB100\n",
    "   Warranty: 1 year\n",
    "   Rating: 4.1\n",
    "   Features: 11.6-inch display, 4GB RAM, 32GB eMMC, Chrome OS\n",
    "   Description: A compact and affordable Chromebook for everyday tasks.\n",
    "   Price: $249.99\n",
    "\n",
    "Step 3:{delimiter} If the message contains products \\\n",
    "in the list above, list any assumptions that the \\\n",
    "user is making in their \\\n",
    "message e.g. that Laptop X is bigger than \\\n",
    "Laptop Y, or that Laptop Z has a 2 year warranty.\n",
    "\n",
    "Step 4:{delimiter}: If the user made any assumptions, \\\n",
    "figure out whether the assumption is true based on your \\\n",
    "product information. \n",
    "\n",
    "Step 5:{delimiter}: First, politely correct the \\\n",
    "customer's incorrect assumptions if applicable. \\\n",
    "Only mention or reference products in the list of \\\n",
    "5 available products, as these are the only 5 \\\n",
    "products that the store sells. \\\n",
    "Answer the customer in a friendly tone.\n",
    "\n",
    "Use the following format:\n",
    "Step 1:{delimiter} <step 1 reasoning>\n",
    "Step 2:{delimiter} <step 2 reasoning>\n",
    "Step 3:{delimiter} <step 3 reasoning>\n",
    "Step 4:{delimiter} <step 4 reasoning>\n",
    "Response to user:{delimiter} <response to customer>\n",
    "\n",
    "Make sure to include {delimiter} to separate every step.\n",
    "\"\"\"\n",
    "\n",
    "# again note the steps the \"chain\"\n",
    "user_message = f\"\"\"\n",
    "by how much is the BlueWave Chromebook more expensive \\\n",
    "than the TechPro Desktop\"\"\"\n",
    "\n",
    "messages =  [  \n",
    "{'role':'system', \n",
    " 'content': system_message},    \n",
    "{'role':'user', \n",
    " 'content': f\"{delimiter}{user_message}{delimiter}\"},  \n",
    "] \n",
    "\n",
    "response = get_completion_from_messages(messages)\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "393efc6d-6655-4098-bb1c-159b67f68a9b",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "8e275c3b-b148-4734-b838-deed1254c419",
   "metadata": {},
   "source": [
    "## OpenAI vector embeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "fce3cbbf-9d20-43f2-bd52-cfc57bc35ebf",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Time</th>\n",
       "      <th>ProductId</th>\n",
       "      <th>UserId</th>\n",
       "      <th>Score</th>\n",
       "      <th>Summary</th>\n",
       "      <th>Text</th>\n",
       "      <th>combined</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1303862400</td>\n",
       "      <td>B001E4KFG0</td>\n",
       "      <td>A3SGXH7AUHU8GW</td>\n",
       "      <td>5</td>\n",
       "      <td>Good Quality Dog Food</td>\n",
       "      <td>I have bought several of the Vitality canned d...</td>\n",
       "      <td>Title: Good Quality Dog Food; Content: I have ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1346976000</td>\n",
       "      <td>B00813GRG4</td>\n",
       "      <td>A1D87F6ZCVE5NK</td>\n",
       "      <td>1</td>\n",
       "      <td>Not as Advertised</td>\n",
       "      <td>Product arrived labeled as Jumbo Salted Peanut...</td>\n",
       "      <td>Title: Not as Advertised; Content: Product arr...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Time   ProductId          UserId  Score                Summary  \\\n",
       "Id                                                                         \n",
       "1   1303862400  B001E4KFG0  A3SGXH7AUHU8GW      5  Good Quality Dog Food   \n",
       "2   1346976000  B00813GRG4  A1D87F6ZCVE5NK      1      Not as Advertised   \n",
       "\n",
       "                                                 Text  \\\n",
       "Id                                                      \n",
       "1   I have bought several of the Vitality canned d...   \n",
       "2   Product arrived labeled as Jumbo Salted Peanut...   \n",
       "\n",
       "                                             combined  \n",
       "Id                                                     \n",
       "1   Title: Good Quality Dog Food; Content: I have ...  \n",
       "2   Title: Not as Advertised; Content: Product arr...  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# ChatGPT vector embeddings\n",
    "\n",
    "# embedding model parameters\n",
    "embedding_model = \"text-embedding-ada-002\"\n",
    "embedding_encoding = \"cl100k_base\"  # this the encoding for text-embedding-ada-002\n",
    "max_tokens = 8000  # the maximum for text-embedding-ada-002 is 8191\n",
    "\n",
    "# load & inspect dataset\n",
    "input_datapath = \"Reviews.csv\" \n",
    "df = pd.read_csv(input_datapath, index_col=0)\n",
    "df = df[[\"Time\", \"ProductId\", \"UserId\", \"Score\", \"Summary\", \"Text\"]]\n",
    "df = df.dropna()\n",
    "df[\"combined\"] = (\n",
    "    \"Title: \" + df.Summary.str.strip() + \"; Content: \" + df.Text.str.strip()\n",
    ")\n",
    "df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "15694c62-525b-49d1-a82d-81833e6bce08",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ProductId</th>\n",
       "      <th>UserId</th>\n",
       "      <th>Score</th>\n",
       "      <th>Summary</th>\n",
       "      <th>Text</th>\n",
       "      <th>combined</th>\n",
       "      <th>n_tokens</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>220697</th>\n",
       "      <td>B003JK537S</td>\n",
       "      <td>A3JBPC3WFUT5ZP</td>\n",
       "      <td>1</td>\n",
       "      <td>Arrived in pieces</td>\n",
       "      <td>Not pleased at all. When I opened the box, mos...</td>\n",
       "      <td>Title: Arrived in pieces; Content: Not pleased...</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>107908</th>\n",
       "      <td>B000JMBE7M</td>\n",
       "      <td>AQX1N6A51QOKG</td>\n",
       "      <td>4</td>\n",
       "      <td>It isn't blanc mange, but isn't bad . . .</td>\n",
       "      <td>I'm not sure that custard is really custard wi...</td>\n",
       "      <td>Title: It isn't blanc mange, but isn't bad . ....</td>\n",
       "      <td>267</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>107800</th>\n",
       "      <td>B004AHGBX4</td>\n",
       "      <td>A2UY46X0OSNVUQ</td>\n",
       "      <td>3</td>\n",
       "      <td>These also have SALT and it's not sea salt.</td>\n",
       "      <td>I like the fact that you can see what you're g...</td>\n",
       "      <td>Title: These also have SALT and it's not sea s...</td>\n",
       "      <td>239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>205313</th>\n",
       "      <td>B001BORBHO</td>\n",
       "      <td>A1AFOYZ9HSM2CZ</td>\n",
       "      <td>5</td>\n",
       "      <td>Happy with the product</td>\n",
       "      <td>My dog was suffering with itchy skin.  He had ...</td>\n",
       "      <td>Title: Happy with the product; Content: My dog...</td>\n",
       "      <td>86</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>284450</th>\n",
       "      <td>B008PSM0BQ</td>\n",
       "      <td>A3OUFIMGL2K6RS</td>\n",
       "      <td>4</td>\n",
       "      <td>Good Sauce</td>\n",
       "      <td>This is a good all purpose sauce.  Has good fl...</td>\n",
       "      <td>Title: Good Sauce; Content: This is a good all...</td>\n",
       "      <td>107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>378704</th>\n",
       "      <td>B008YA1LQK</td>\n",
       "      <td>A9YEAAQVHFUTX</td>\n",
       "      <td>5</td>\n",
       "      <td>Blackcat</td>\n",
       "      <td>Great coffee!  Love all Green Mountain coffee ...</td>\n",
       "      <td>Title: Blackcat; Content: Great coffee!  Love ...</td>\n",
       "      <td>34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>456909</th>\n",
       "      <td>B001KP6B98</td>\n",
       "      <td>ABWCUS3HBDZRS</td>\n",
       "      <td>5</td>\n",
       "      <td>Excellent product</td>\n",
       "      <td>After scouring every store in town for orange ...</td>\n",
       "      <td>Title: Excellent product; Content: After scour...</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>378703</th>\n",
       "      <td>B008YA1LQK</td>\n",
       "      <td>A2RSB6FVQ9K9OD</td>\n",
       "      <td>5</td>\n",
       "      <td>Bulk k-Cups</td>\n",
       "      <td>This is the best way to buy coffee for my offi...</td>\n",
       "      <td>Title: Bulk k-Cups; Content: This is the best ...</td>\n",
       "      <td>44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>312410</th>\n",
       "      <td>B001E5E2QI</td>\n",
       "      <td>A23WYVBCNE75X1</td>\n",
       "      <td>3</td>\n",
       "      <td>It's Okay</td>\n",
       "      <td>Next time, I will buy Gevalia Irish Cream deca...</td>\n",
       "      <td>Title: It's Okay; Content: Next time, I will b...</td>\n",
       "      <td>38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65135</th>\n",
       "      <td>B000H9K4KA</td>\n",
       "      <td>A2WMZYYF8OSGD6</td>\n",
       "      <td>5</td>\n",
       "      <td>FABULOUS...</td>\n",
       "      <td>Absolutely wonderful.  A real licorice taste. ...</td>\n",
       "      <td>Title: FABULOUS...; Content: Absolutely wonder...</td>\n",
       "      <td>46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>463584</th>\n",
       "      <td>B004QDA8WC</td>\n",
       "      <td>ANM000BVVUSCT</td>\n",
       "      <td>5</td>\n",
       "      <td>Exactly what I was looking for: Fast, fantasti...</td>\n",
       "      <td>I was skeptical as to how good an all-in-one C...</td>\n",
       "      <td>Title: Exactly what I was looking for: Fast, f...</td>\n",
       "      <td>106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>199739</th>\n",
       "      <td>B000K8T3OQ</td>\n",
       "      <td>AK43Y4WT6FFR3</td>\n",
       "      <td>1</td>\n",
       "      <td>Broken in a million pieces</td>\n",
       "      <td>Chips were broken into small pieces. Problem i...</td>\n",
       "      <td>Title: Broken in a million pieces; Content: Ch...</td>\n",
       "      <td>120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96676</th>\n",
       "      <td>B0051C0J6M</td>\n",
       "      <td>AWFA8N9IXELVH</td>\n",
       "      <td>1</td>\n",
       "      <td>Deceptive description</td>\n",
       "      <td>On Oct 9 I ordered from a different vendor the...</td>\n",
       "      <td>Title: Deceptive description; Content: On Oct ...</td>\n",
       "      <td>157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96677</th>\n",
       "      <td>B0051C0J6M</td>\n",
       "      <td>AG4YGLLIE8BWP</td>\n",
       "      <td>5</td>\n",
       "      <td>Makes me drool just thinking of them</td>\n",
       "      <td>The Brit's have out done us. The flavor is sup...</td>\n",
       "      <td>Title: Makes me drool just thinking of them; C...</td>\n",
       "      <td>52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>194114</th>\n",
       "      <td>B003J9HAU2</td>\n",
       "      <td>A23WYVBCNE75X1</td>\n",
       "      <td>3</td>\n",
       "      <td>it's alright</td>\n",
       "      <td>My kitten prefers Kitten Chow or Iams.  He lea...</td>\n",
       "      <td>Title: it's alright; Content: My kitten prefer...</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47333</th>\n",
       "      <td>B001444G5Q</td>\n",
       "      <td>A3FIA99WOIL40T</td>\n",
       "      <td>2</td>\n",
       "      <td>these are mini candy bars.</td>\n",
       "      <td>I was very disappointed with this order becaus...</td>\n",
       "      <td>Title: these are mini candy bars.; Content: I ...</td>\n",
       "      <td>81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>287001</th>\n",
       "      <td>B006Q7YG24</td>\n",
       "      <td>A7EU2BWLLCJY2</td>\n",
       "      <td>5</td>\n",
       "      <td>My dogs love them!</td>\n",
       "      <td>I've tried several different kinds of freeze-d...</td>\n",
       "      <td>Title: My dogs love them!; Content: I've tried...</td>\n",
       "      <td>229</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>420377</th>\n",
       "      <td>B008JKSJJ2</td>\n",
       "      <td>A1XV4W7JWX341C</td>\n",
       "      <td>5</td>\n",
       "      <td>Loved these gluten free healthy bars, saved $$...</td>\n",
       "      <td>These Kind Bars are so good and healthy &amp; glut...</td>\n",
       "      <td>Title: Loved these gluten free healthy bars, s...</td>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>420378</th>\n",
       "      <td>B008JKSJJ2</td>\n",
       "      <td>A34XBAIFT02B60</td>\n",
       "      <td>1</td>\n",
       "      <td>Should advertise coconut as an ingredient more...</td>\n",
       "      <td>First, these should be called Mac - Coconut ba...</td>\n",
       "      <td>Title: Should advertise coconut as an ingredie...</td>\n",
       "      <td>78</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         ProductId          UserId  Score  \\\n",
       "Id                                          \n",
       "220697  B003JK537S  A3JBPC3WFUT5ZP      1   \n",
       "107908  B000JMBE7M   AQX1N6A51QOKG      4   \n",
       "107800  B004AHGBX4  A2UY46X0OSNVUQ      3   \n",
       "205313  B001BORBHO  A1AFOYZ9HSM2CZ      5   \n",
       "284450  B008PSM0BQ  A3OUFIMGL2K6RS      4   \n",
       "378704  B008YA1LQK   A9YEAAQVHFUTX      5   \n",
       "456909  B001KP6B98   ABWCUS3HBDZRS      5   \n",
       "378703  B008YA1LQK  A2RSB6FVQ9K9OD      5   \n",
       "312410  B001E5E2QI  A23WYVBCNE75X1      3   \n",
       "65135   B000H9K4KA  A2WMZYYF8OSGD6      5   \n",
       "463584  B004QDA8WC   ANM000BVVUSCT      5   \n",
       "199739  B000K8T3OQ   AK43Y4WT6FFR3      1   \n",
       "96676   B0051C0J6M   AWFA8N9IXELVH      1   \n",
       "96677   B0051C0J6M   AG4YGLLIE8BWP      5   \n",
       "194114  B003J9HAU2  A23WYVBCNE75X1      3   \n",
       "47333   B001444G5Q  A3FIA99WOIL40T      2   \n",
       "287001  B006Q7YG24   A7EU2BWLLCJY2      5   \n",
       "420377  B008JKSJJ2  A1XV4W7JWX341C      5   \n",
       "420378  B008JKSJJ2  A34XBAIFT02B60      1   \n",
       "\n",
       "                                                  Summary  \\\n",
       "Id                                                          \n",
       "220697                                  Arrived in pieces   \n",
       "107908          It isn't blanc mange, but isn't bad . . .   \n",
       "107800        These also have SALT and it's not sea salt.   \n",
       "205313                             Happy with the product   \n",
       "284450                                         Good Sauce   \n",
       "378704                                           Blackcat   \n",
       "456909                                  Excellent product   \n",
       "378703                                        Bulk k-Cups   \n",
       "312410                                          It's Okay   \n",
       "65135                                         FABULOUS...   \n",
       "463584  Exactly what I was looking for: Fast, fantasti...   \n",
       "199739                         Broken in a million pieces   \n",
       "96676                               Deceptive description   \n",
       "96677                Makes me drool just thinking of them   \n",
       "194114                                       it's alright   \n",
       "47333                          these are mini candy bars.   \n",
       "287001                                 My dogs love them!   \n",
       "420377  Loved these gluten free healthy bars, saved $$...   \n",
       "420378  Should advertise coconut as an ingredient more...   \n",
       "\n",
       "                                                     Text  \\\n",
       "Id                                                          \n",
       "220697  Not pleased at all. When I opened the box, mos...   \n",
       "107908  I'm not sure that custard is really custard wi...   \n",
       "107800  I like the fact that you can see what you're g...   \n",
       "205313  My dog was suffering with itchy skin.  He had ...   \n",
       "284450  This is a good all purpose sauce.  Has good fl...   \n",
       "378704  Great coffee!  Love all Green Mountain coffee ...   \n",
       "456909  After scouring every store in town for orange ...   \n",
       "378703  This is the best way to buy coffee for my offi...   \n",
       "312410  Next time, I will buy Gevalia Irish Cream deca...   \n",
       "65135   Absolutely wonderful.  A real licorice taste. ...   \n",
       "463584  I was skeptical as to how good an all-in-one C...   \n",
       "199739  Chips were broken into small pieces. Problem i...   \n",
       "96676   On Oct 9 I ordered from a different vendor the...   \n",
       "96677   The Brit's have out done us. The flavor is sup...   \n",
       "194114  My kitten prefers Kitten Chow or Iams.  He lea...   \n",
       "47333   I was very disappointed with this order becaus...   \n",
       "287001  I've tried several different kinds of freeze-d...   \n",
       "420377  These Kind Bars are so good and healthy & glut...   \n",
       "420378  First, these should be called Mac - Coconut ba...   \n",
       "\n",
       "                                                 combined  n_tokens  \n",
       "Id                                                                   \n",
       "220697  Title: Arrived in pieces; Content: Not pleased...        35  \n",
       "107908  Title: It isn't blanc mange, but isn't bad . ....       267  \n",
       "107800  Title: These also have SALT and it's not sea s...       239  \n",
       "205313  Title: Happy with the product; Content: My dog...        86  \n",
       "284450  Title: Good Sauce; Content: This is a good all...       107  \n",
       "378704  Title: Blackcat; Content: Great coffee!  Love ...        34  \n",
       "456909  Title: Excellent product; Content: After scour...       100  \n",
       "378703  Title: Bulk k-Cups; Content: This is the best ...        44  \n",
       "312410  Title: It's Okay; Content: Next time, I will b...        38  \n",
       "65135   Title: FABULOUS...; Content: Absolutely wonder...        46  \n",
       "463584  Title: Exactly what I was looking for: Fast, f...       106  \n",
       "199739  Title: Broken in a million pieces; Content: Ch...       120  \n",
       "96676   Title: Deceptive description; Content: On Oct ...       157  \n",
       "96677   Title: Makes me drool just thinking of them; C...        52  \n",
       "194114  Title: it's alright; Content: My kitten prefer...        35  \n",
       "47333   Title: these are mini candy bars.; Content: I ...        81  \n",
       "287001  Title: My dogs love them!; Content: I've tried...       229  \n",
       "420377  Title: Loved these gluten free healthy bars, s...        96  \n",
       "420378  Title: Should advertise coconut as an ingredie...        78  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# subsample to 1k most recent reviews and remove samples that are too long\n",
    "top_n = 1000\n",
    "df = df.sort_values(\"Time\").tail(top_n * 2)  # first cut to first 2k entries, assuming less than half will be filtered out\n",
    "df.drop(\"Time\", axis=1, inplace=True)\n",
    "\n",
    "encoding = tiktoken.get_encoding(embedding_encoding)\n",
    "\n",
    "# omit reviews that are too long to embed\n",
    "df[\"n_tokens\"] = df.combined.apply(lambda x: len(encoding.encode(x)))\n",
    "df = df[df.n_tokens <= max_tokens].tail(top_n)\n",
    "\n",
    "df = df.iloc[1:20,]\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "61d27df7-1fd9-4159-8247-43c07cafb138",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# this may take a few minutes\n",
    "df[\"embedding\"] = df.combined.apply(lambda x: get_embedding(x, engine=embedding_model))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "d77114ec-0c69-458f-8cd4-ad79fae56329",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ProductId</th>\n",
       "      <th>UserId</th>\n",
       "      <th>Score</th>\n",
       "      <th>Summary</th>\n",
       "      <th>Text</th>\n",
       "      <th>combined</th>\n",
       "      <th>n_tokens</th>\n",
       "      <th>embedding</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Id</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>220697</th>\n",
       "      <td>B003JK537S</td>\n",
       "      <td>A3JBPC3WFUT5ZP</td>\n",
       "      <td>1</td>\n",
       "      <td>Arrived in pieces</td>\n",
       "      <td>Not pleased at all. When I opened the box, mos...</td>\n",
       "      <td>Title: Arrived in pieces; Content: Not pleased...</td>\n",
       "      <td>35</td>\n",
       "      <td>[-0.023657305166125298, -0.011915579438209534,...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>107908</th>\n",
       "      <td>B000JMBE7M</td>\n",
       "      <td>AQX1N6A51QOKG</td>\n",
       "      <td>4</td>\n",
       "      <td>It isn't blanc mange, but isn't bad . . .</td>\n",
       "      <td>I'm not sure that custard is really custard wi...</td>\n",
       "      <td>Title: It isn't blanc mange, but isn't bad . ....</td>\n",
       "      <td>267</td>\n",
       "      <td>[0.0001991958706639707, 0.005254689138382673, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>107800</th>\n",
       "      <td>B004AHGBX4</td>\n",
       "      <td>A2UY46X0OSNVUQ</td>\n",
       "      <td>3</td>\n",
       "      <td>These also have SALT and it's not sea salt.</td>\n",
       "      <td>I like the fact that you can see what you're g...</td>\n",
       "      <td>Title: These also have SALT and it's not sea s...</td>\n",
       "      <td>239</td>\n",
       "      <td>[0.010382632724940777, -0.013499382883310318, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>205313</th>\n",
       "      <td>B001BORBHO</td>\n",
       "      <td>A1AFOYZ9HSM2CZ</td>\n",
       "      <td>5</td>\n",
       "      <td>Happy with the product</td>\n",
       "      <td>My dog was suffering with itchy skin.  He had ...</td>\n",
       "      <td>Title: Happy with the product; Content: My dog...</td>\n",
       "      <td>86</td>\n",
       "      <td>[0.015346125699579716, -0.003973433747887611, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>284450</th>\n",
       "      <td>B008PSM0BQ</td>\n",
       "      <td>A3OUFIMGL2K6RS</td>\n",
       "      <td>4</td>\n",
       "      <td>Good Sauce</td>\n",
       "      <td>This is a good all purpose sauce.  Has good fl...</td>\n",
       "      <td>Title: Good Sauce; Content: This is a good all...</td>\n",
       "      <td>107</td>\n",
       "      <td>[-0.016191359609365463, 0.005975224543362856, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>378704</th>\n",
       "      <td>B008YA1LQK</td>\n",
       "      <td>A9YEAAQVHFUTX</td>\n",
       "      <td>5</td>\n",
       "      <td>Blackcat</td>\n",
       "      <td>Great coffee!  Love all Green Mountain coffee ...</td>\n",
       "      <td>Title: Blackcat; Content: Great coffee!  Love ...</td>\n",
       "      <td>34</td>\n",
       "      <td>[-0.01409711129963398, -0.016294565051794052, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>456909</th>\n",
       "      <td>B001KP6B98</td>\n",
       "      <td>ABWCUS3HBDZRS</td>\n",
       "      <td>5</td>\n",
       "      <td>Excellent product</td>\n",
       "      <td>After scouring every store in town for orange ...</td>\n",
       "      <td>Title: Excellent product; Content: After scour...</td>\n",
       "      <td>100</td>\n",
       "      <td>[0.0006881337030790746, -0.017053602263331413,...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>378703</th>\n",
       "      <td>B008YA1LQK</td>\n",
       "      <td>A2RSB6FVQ9K9OD</td>\n",
       "      <td>5</td>\n",
       "      <td>Bulk k-Cups</td>\n",
       "      <td>This is the best way to buy coffee for my offi...</td>\n",
       "      <td>Title: Bulk k-Cups; Content: This is the best ...</td>\n",
       "      <td>44</td>\n",
       "      <td>[-0.002279900014400482, -0.0001825799117796123...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>312410</th>\n",
       "      <td>B001E5E2QI</td>\n",
       "      <td>A23WYVBCNE75X1</td>\n",
       "      <td>3</td>\n",
       "      <td>It's Okay</td>\n",
       "      <td>Next time, I will buy Gevalia Irish Cream deca...</td>\n",
       "      <td>Title: It's Okay; Content: Next time, I will b...</td>\n",
       "      <td>38</td>\n",
       "      <td>[-0.017475998029112816, -0.01266452670097351, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65135</th>\n",
       "      <td>B000H9K4KA</td>\n",
       "      <td>A2WMZYYF8OSGD6</td>\n",
       "      <td>5</td>\n",
       "      <td>FABULOUS...</td>\n",
       "      <td>Absolutely wonderful.  A real licorice taste. ...</td>\n",
       "      <td>Title: FABULOUS...; Content: Absolutely wonder...</td>\n",
       "      <td>46</td>\n",
       "      <td>[-0.0108223557472229, -0.0048522138968110085, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>463584</th>\n",
       "      <td>B004QDA8WC</td>\n",
       "      <td>ANM000BVVUSCT</td>\n",
       "      <td>5</td>\n",
       "      <td>Exactly what I was looking for: Fast, fantasti...</td>\n",
       "      <td>I was skeptical as to how good an all-in-one C...</td>\n",
       "      <td>Title: Exactly what I was looking for: Fast, f...</td>\n",
       "      <td>106</td>\n",
       "      <td>[0.0018487726338207722, 0.002289900556206703, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>199739</th>\n",
       "      <td>B000K8T3OQ</td>\n",
       "      <td>AK43Y4WT6FFR3</td>\n",
       "      <td>1</td>\n",
       "      <td>Broken in a million pieces</td>\n",
       "      <td>Chips were broken into small pieces. Problem i...</td>\n",
       "      <td>Title: Broken in a million pieces; Content: Ch...</td>\n",
       "      <td>120</td>\n",
       "      <td>[-0.0005945640150457621, -0.004139306023716927...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96676</th>\n",
       "      <td>B0051C0J6M</td>\n",
       "      <td>AWFA8N9IXELVH</td>\n",
       "      <td>1</td>\n",
       "      <td>Deceptive description</td>\n",
       "      <td>On Oct 9 I ordered from a different vendor the...</td>\n",
       "      <td>Title: Deceptive description; Content: On Oct ...</td>\n",
       "      <td>157</td>\n",
       "      <td>[0.006905762013047934, 0.016764424741268158, -...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96677</th>\n",
       "      <td>B0051C0J6M</td>\n",
       "      <td>AG4YGLLIE8BWP</td>\n",
       "      <td>5</td>\n",
       "      <td>Makes me drool just thinking of them</td>\n",
       "      <td>The Brit's have out done us. The flavor is sup...</td>\n",
       "      <td>Title: Makes me drool just thinking of them; C...</td>\n",
       "      <td>52</td>\n",
       "      <td>[-0.00230499729514122, -0.02137329801917076, 0...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>194114</th>\n",
       "      <td>B003J9HAU2</td>\n",
       "      <td>A23WYVBCNE75X1</td>\n",
       "      <td>3</td>\n",
       "      <td>it's alright</td>\n",
       "      <td>My kitten prefers Kitten Chow or Iams.  He lea...</td>\n",
       "      <td>Title: it's alright; Content: My kitten prefer...</td>\n",
       "      <td>35</td>\n",
       "      <td>[0.002220588969066739, 0.010267132893204689, 0...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47333</th>\n",
       "      <td>B001444G5Q</td>\n",
       "      <td>A3FIA99WOIL40T</td>\n",
       "      <td>2</td>\n",
       "      <td>these are mini candy bars.</td>\n",
       "      <td>I was very disappointed with this order becaus...</td>\n",
       "      <td>Title: these are mini candy bars.; Content: I ...</td>\n",
       "      <td>81</td>\n",
       "      <td>[-0.02758827619254589, -0.009117042645812035, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>287001</th>\n",
       "      <td>B006Q7YG24</td>\n",
       "      <td>A7EU2BWLLCJY2</td>\n",
       "      <td>5</td>\n",
       "      <td>My dogs love them!</td>\n",
       "      <td>I've tried several different kinds of freeze-d...</td>\n",
       "      <td>Title: My dogs love them!; Content: I've tried...</td>\n",
       "      <td>229</td>\n",
       "      <td>[-0.015452444553375244, -0.009876413270831108,...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>420377</th>\n",
       "      <td>B008JKSJJ2</td>\n",
       "      <td>A1XV4W7JWX341C</td>\n",
       "      <td>5</td>\n",
       "      <td>Loved these gluten free healthy bars, saved $$...</td>\n",
       "      <td>These Kind Bars are so good and healthy &amp; glut...</td>\n",
       "      <td>Title: Loved these gluten free healthy bars, s...</td>\n",
       "      <td>96</td>\n",
       "      <td>[-0.0023678855504840612, -0.013224039226770401...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>420378</th>\n",
       "      <td>B008JKSJJ2</td>\n",
       "      <td>A34XBAIFT02B60</td>\n",
       "      <td>1</td>\n",
       "      <td>Should advertise coconut as an ingredient more...</td>\n",
       "      <td>First, these should be called Mac - Coconut ba...</td>\n",
       "      <td>Title: Should advertise coconut as an ingredie...</td>\n",
       "      <td>78</td>\n",
       "      <td>[-0.017644274979829788, -7.453539728885517e-05...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         ProductId          UserId  Score  \\\n",
       "Id                                          \n",
       "220697  B003JK537S  A3JBPC3WFUT5ZP      1   \n",
       "107908  B000JMBE7M   AQX1N6A51QOKG      4   \n",
       "107800  B004AHGBX4  A2UY46X0OSNVUQ      3   \n",
       "205313  B001BORBHO  A1AFOYZ9HSM2CZ      5   \n",
       "284450  B008PSM0BQ  A3OUFIMGL2K6RS      4   \n",
       "378704  B008YA1LQK   A9YEAAQVHFUTX      5   \n",
       "456909  B001KP6B98   ABWCUS3HBDZRS      5   \n",
       "378703  B008YA1LQK  A2RSB6FVQ9K9OD      5   \n",
       "312410  B001E5E2QI  A23WYVBCNE75X1      3   \n",
       "65135   B000H9K4KA  A2WMZYYF8OSGD6      5   \n",
       "463584  B004QDA8WC   ANM000BVVUSCT      5   \n",
       "199739  B000K8T3OQ   AK43Y4WT6FFR3      1   \n",
       "96676   B0051C0J6M   AWFA8N9IXELVH      1   \n",
       "96677   B0051C0J6M   AG4YGLLIE8BWP      5   \n",
       "194114  B003J9HAU2  A23WYVBCNE75X1      3   \n",
       "47333   B001444G5Q  A3FIA99WOIL40T      2   \n",
       "287001  B006Q7YG24   A7EU2BWLLCJY2      5   \n",
       "420377  B008JKSJJ2  A1XV4W7JWX341C      5   \n",
       "420378  B008JKSJJ2  A34XBAIFT02B60      1   \n",
       "\n",
       "                                                  Summary  \\\n",
       "Id                                                          \n",
       "220697                                  Arrived in pieces   \n",
       "107908          It isn't blanc mange, but isn't bad . . .   \n",
       "107800        These also have SALT and it's not sea salt.   \n",
       "205313                             Happy with the product   \n",
       "284450                                         Good Sauce   \n",
       "378704                                           Blackcat   \n",
       "456909                                  Excellent product   \n",
       "378703                                        Bulk k-Cups   \n",
       "312410                                          It's Okay   \n",
       "65135                                         FABULOUS...   \n",
       "463584  Exactly what I was looking for: Fast, fantasti...   \n",
       "199739                         Broken in a million pieces   \n",
       "96676                               Deceptive description   \n",
       "96677                Makes me drool just thinking of them   \n",
       "194114                                       it's alright   \n",
       "47333                          these are mini candy bars.   \n",
       "287001                                 My dogs love them!   \n",
       "420377  Loved these gluten free healthy bars, saved $$...   \n",
       "420378  Should advertise coconut as an ingredient more...   \n",
       "\n",
       "                                                     Text  \\\n",
       "Id                                                          \n",
       "220697  Not pleased at all. When I opened the box, mos...   \n",
       "107908  I'm not sure that custard is really custard wi...   \n",
       "107800  I like the fact that you can see what you're g...   \n",
       "205313  My dog was suffering with itchy skin.  He had ...   \n",
       "284450  This is a good all purpose sauce.  Has good fl...   \n",
       "378704  Great coffee!  Love all Green Mountain coffee ...   \n",
       "456909  After scouring every store in town for orange ...   \n",
       "378703  This is the best way to buy coffee for my offi...   \n",
       "312410  Next time, I will buy Gevalia Irish Cream deca...   \n",
       "65135   Absolutely wonderful.  A real licorice taste. ...   \n",
       "463584  I was skeptical as to how good an all-in-one C...   \n",
       "199739  Chips were broken into small pieces. Problem i...   \n",
       "96676   On Oct 9 I ordered from a different vendor the...   \n",
       "96677   The Brit's have out done us. The flavor is sup...   \n",
       "194114  My kitten prefers Kitten Chow or Iams.  He lea...   \n",
       "47333   I was very disappointed with this order becaus...   \n",
       "287001  I've tried several different kinds of freeze-d...   \n",
       "420377  These Kind Bars are so good and healthy & glut...   \n",
       "420378  First, these should be called Mac - Coconut ba...   \n",
       "\n",
       "                                                 combined  n_tokens  \\\n",
       "Id                                                                    \n",
       "220697  Title: Arrived in pieces; Content: Not pleased...        35   \n",
       "107908  Title: It isn't blanc mange, but isn't bad . ....       267   \n",
       "107800  Title: These also have SALT and it's not sea s...       239   \n",
       "205313  Title: Happy with the product; Content: My dog...        86   \n",
       "284450  Title: Good Sauce; Content: This is a good all...       107   \n",
       "378704  Title: Blackcat; Content: Great coffee!  Love ...        34   \n",
       "456909  Title: Excellent product; Content: After scour...       100   \n",
       "378703  Title: Bulk k-Cups; Content: This is the best ...        44   \n",
       "312410  Title: It's Okay; Content: Next time, I will b...        38   \n",
       "65135   Title: FABULOUS...; Content: Absolutely wonder...        46   \n",
       "463584  Title: Exactly what I was looking for: Fast, f...       106   \n",
       "199739  Title: Broken in a million pieces; Content: Ch...       120   \n",
       "96676   Title: Deceptive description; Content: On Oct ...       157   \n",
       "96677   Title: Makes me drool just thinking of them; C...        52   \n",
       "194114  Title: it's alright; Content: My kitten prefer...        35   \n",
       "47333   Title: these are mini candy bars.; Content: I ...        81   \n",
       "287001  Title: My dogs love them!; Content: I've tried...       229   \n",
       "420377  Title: Loved these gluten free healthy bars, s...        96   \n",
       "420378  Title: Should advertise coconut as an ingredie...        78   \n",
       "\n",
       "                                                embedding  \n",
       "Id                                                         \n",
       "220697  [-0.023657305166125298, -0.011915579438209534,...  \n",
       "107908  [0.0001991958706639707, 0.005254689138382673, ...  \n",
       "107800  [0.010382632724940777, -0.013499382883310318, ...  \n",
       "205313  [0.015346125699579716, -0.003973433747887611, ...  \n",
       "284450  [-0.016191359609365463, 0.005975224543362856, ...  \n",
       "378704  [-0.01409711129963398, -0.016294565051794052, ...  \n",
       "456909  [0.0006881337030790746, -0.017053602263331413,...  \n",
       "378703  [-0.002279900014400482, -0.0001825799117796123...  \n",
       "312410  [-0.017475998029112816, -0.01266452670097351, ...  \n",
       "65135   [-0.0108223557472229, -0.0048522138968110085, ...  \n",
       "463584  [0.0018487726338207722, 0.002289900556206703, ...  \n",
       "199739  [-0.0005945640150457621, -0.004139306023716927...  \n",
       "96676   [0.006905762013047934, 0.016764424741268158, -...  \n",
       "96677   [-0.00230499729514122, -0.02137329801917076, 0...  \n",
       "194114  [0.002220588969066739, 0.010267132893204689, 0...  \n",
       "47333   [-0.02758827619254589, -0.009117042645812035, ...  \n",
       "287001  [-0.015452444553375244, -0.009876413270831108,...  \n",
       "420377  [-0.0023678855504840612, -0.013224039226770401...  \n",
       "420378  [-0.017644274979829788, -7.453539728885517e-05...  "
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.to_csv(\"fine_food_reviews_with_embeddings_1k.csv\")\n",
    "\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "913c1b30-764f-4375-b84e-95164d92f3a8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1536\n",
      "1536\n"
     ]
    }
   ],
   "source": [
    "# how long are the review embeddings?\n",
    "# we could now treat each review as a 1536-features element of a vector space to do clusterings etc!!\n",
    "# much more here: https://platform.openai.com/docs/guides/embeddings/use-cases\n",
    "\n",
    "print(len(df[\"embedding\"].iloc[1,]))\n",
    "print(len(df[\"embedding\"].iloc[17,]))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2655146d-c5ea-440a-95f2-df2a8ec19702",
   "metadata": {},
   "source": [
    "# Search over pdf documents with LangChain + others"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "1737fd32-ec26-4f1a-bc9c-826857f9c71d",
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "outputs": [
    {
     "ename": "ImportError",
     "evalue": "cannot import name 'open_filename' from 'pdfminer.utils' (/Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages/pdfminer/utils.py)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mImportError\u001b[0m                               Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[34], line 10\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[38;5;66;03m#loader = UnstructuredPDFLoader(\"field-guide-to-data-science.pdf\")\u001b[39;00m\n\u001b[1;32m      8\u001b[0m loader \u001b[38;5;241m=\u001b[39m OnlinePDFLoader(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhttps://www.biorxiv.org/content/10.1101/2023.07.20.549945v1.full.pdf\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 10\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[43mloader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_and_split\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m \n\u001b[1;32m     12\u001b[0m \u001b[38;5;28mprint\u001b[39m (\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mYou have \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(data)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m document(s) in your data\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m     13\u001b[0m \u001b[38;5;28mprint\u001b[39m (\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mThere are \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(data[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mpage_content)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m characters in your document\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
      "File \u001b[0;32m~/anaconda3/envs/api_hackathon/lib/python3.8/site-packages/langchain/document_loaders/base.py:43\u001b[0m, in \u001b[0;36mBaseLoader.load_and_split\u001b[0;34m(self, text_splitter)\u001b[0m\n\u001b[1;32m     41\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m     42\u001b[0m     _text_splitter \u001b[38;5;241m=\u001b[39m text_splitter\n\u001b[0;32m---> 43\u001b[0m docs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     44\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _text_splitter\u001b[38;5;241m.\u001b[39msplit_documents(docs)\n",
      "File \u001b[0;32m~/anaconda3/envs/api_hackathon/lib/python3.8/site-packages/langchain/document_loaders/pdf.py:134\u001b[0m, in \u001b[0;36mOnlinePDFLoader.load\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    132\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Load documents.\"\"\"\u001b[39;00m\n\u001b[1;32m    133\u001b[0m loader \u001b[38;5;241m=\u001b[39m UnstructuredPDFLoader(\u001b[38;5;28mstr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfile_path))\n\u001b[0;32m--> 134\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mloader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/anaconda3/envs/api_hackathon/lib/python3.8/site-packages/langchain/document_loaders/unstructured.py:86\u001b[0m, in \u001b[0;36mUnstructuredBaseLoader.load\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     84\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m List[Document]:\n\u001b[1;32m     85\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Load file.\"\"\"\u001b[39;00m\n\u001b[0;32m---> 86\u001b[0m     elements \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_elements\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     87\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_post_process_elements(elements)\n\u001b[1;32m     88\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124melements\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n",
      "File \u001b[0;32m~/anaconda3/envs/api_hackathon/lib/python3.8/site-packages/langchain/document_loaders/pdf.py:57\u001b[0m, in \u001b[0;36mUnstructuredPDFLoader._get_elements\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     56\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_get_elements\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m List:\n\u001b[0;32m---> 57\u001b[0m     \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01munstructured\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpartition\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpdf\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m partition_pdf\n\u001b[1;32m     59\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m partition_pdf(filename\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfile_path, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39munstructured_kwargs)\n",
      "File \u001b[0;32m~/anaconda3/envs/api_hackathon/lib/python3.8/site-packages/unstructured/partition/pdf.py:36\u001b[0m\n\u001b[1;32m     28\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpdfminer\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlayout\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[1;32m     29\u001b[0m     LTChar,\n\u001b[1;32m     30\u001b[0m     LTContainer,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     33\u001b[0m     LTTextBox,\n\u001b[1;32m     34\u001b[0m )\n\u001b[1;32m     35\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpdfminer\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpdftypes\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m PDFObjRef\n\u001b[0;32m---> 36\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpdfminer\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m open_filename\n\u001b[1;32m     37\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mPIL\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Image \u001b[38;5;28;01mas\u001b[39;00m PILImage\n\u001b[1;32m     39\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01munstructured\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mchunking\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m add_chunking_strategy\n",
      "\u001b[0;31mImportError\u001b[0m: cannot import name 'open_filename' from 'pdfminer.utils' (/Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages/pdfminer/utils.py)"
     ]
    }
   ],
   "source": [
    "from langchain.document_loaders import UnstructuredPDFLoader, OnlinePDFLoader\n",
    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
    "from langchain.vectorstores import Chroma, Pinecone\n",
    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
    "import pinecone\n",
    "\n",
    "#loader = UnstructuredPDFLoader(\"field-guide-to-data-science.pdf\")\n",
    "loader = OnlinePDFLoader(\"https://www.biorxiv.org/content/10.1101/2023.07.20.549945v1.full.pdf\")\n",
    "\n",
    "data = loader.load_and_split() \n",
    "\n",
    "print (f'You have {len(data)} document(s) in your data')\n",
    "print (f'There are {len(data[0].page_content)} characters in your document')\n",
    "\n",
    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
    "texts = text_splitter.split_documents(data)\n",
    "\n",
    "print (f'Now you have {len(texts)} documents')\n",
    "\n",
    "OPENAI_API_KEY = mykey\n",
    "\n",
    "embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)\n",
    "\n",
    "import pinecone      \n",
    "\n",
    "pinecone.init(      \n",
    "\tapi_key=pineconekey,      \n",
    "\tenvironment='gcp-starter'      \n",
    ")      \n",
    "index = pinecone.Index('langchain')\n",
    "\n",
    "index_name = \"langchain\"  ####### I0VE STARTED A VERY RANDOM INDEX ON FREE TIER IN PINECONE!!\n",
    "\n",
    "docsearch = Pinecone.from_texts([t.page_content for t in texts], embeddings, index_name=index_name)\n",
    "\n",
    "query = \"what is Voyager?\"\n",
    "docs = docsearch.similarity_search(query)#, include_metadata=True)\n",
    "\n",
    "print(docs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "98cf55aa-4c05-472b-9d93-8d93210fb3e2",
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "module 'docsearch' has no attribute 'similarity_search'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[39], line 8\u001b[0m\n\u001b[1;32m      5\u001b[0m chain \u001b[38;5;241m=\u001b[39m load_qa_chain(llm, chain_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstuff\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      7\u001b[0m query \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msummarize the technical improvements in Voyager\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 8\u001b[0m docs \u001b[38;5;241m=\u001b[39m \u001b[43mdocsearch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msimilarity_search\u001b[49m(query)\u001b[38;5;66;03m#, include_metadata=True)\u001b[39;00m\n\u001b[1;32m     10\u001b[0m chain\u001b[38;5;241m.\u001b[39mrun(input_documents\u001b[38;5;241m=\u001b[39mdocs, question\u001b[38;5;241m=\u001b[39mquery)\n",
      "\u001b[0;31mAttributeError\u001b[0m: module 'docsearch' has no attribute 'similarity_search'"
     ]
    }
   ],
   "source": [
    "from langchain.llms import OpenAI\n",
    "from langchain.chains.question_answering import load_qa_chain\n",
    "\n",
    "llm = OpenAI(temperature=0, openai_api_key=mykey) ### temperature parameter controls the \"creativity\" (aka, hallucinations)\n",
    "chain = load_qa_chain(llm, chain_type=\"stuff\")\n",
    "\n",
    "query = \"summarize the technical improvements in Voyager\"\n",
    "docs = docsearch.similarity_search(query)#, include_metadata=True)\n",
    "\n",
    "chain.run(input_documents=docs, question=query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "567e527e-6f24-4fb9-9b96-86aa4fcf06fd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting docsearch\n",
      "  Downloading docsearch-1.0.tar.gz (4.3 kB)\n",
      "  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25hRequirement already satisfied: scipy in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from docsearch) (1.10.1)\n",
      "Collecting stop_words (from docsearch)\n",
      "  Downloading stop-words-2018.7.23.tar.gz (31 kB)\n",
      "  Preparing metadata (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25hRequirement already satisfied: nltk in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from docsearch) (3.8.1)\n",
      "Collecting gensim (from docsearch)\n",
      "  Downloading gensim-4.3.2-cp38-cp38-macosx_11_0_arm64.whl.metadata (8.5 kB)\n",
      "Collecting pyemd (from docsearch)\n",
      "  Downloading pyemd-1.0.0.tar.gz (87 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.2/87.2 kB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25h  Installing build dependencies ... \u001b[?25ldone\n",
      "\u001b[?25h  Getting requirements to build wheel ... \u001b[?25ldone\n",
      "\u001b[?25h  Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
      "\u001b[?25hRequirement already satisfied: pandas in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from docsearch) (2.0.3)\n",
      "Requirement already satisfied: numpy>=1.18.5 in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from gensim->docsearch) (1.24.4)\n",
      "Collecting smart-open>=1.8.1 (from gensim->docsearch)\n",
      "  Downloading smart_open-7.0.4-py3-none-any.whl.metadata (23 kB)\n",
      "Requirement already satisfied: click in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from nltk->docsearch) (8.1.7)\n",
      "Requirement already satisfied: joblib in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from nltk->docsearch) (1.3.2)\n",
      "Requirement already satisfied: regex>=2021.8.3 in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from nltk->docsearch) (2023.10.3)\n",
      "Requirement already satisfied: tqdm in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from nltk->docsearch) (4.66.1)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from pandas->docsearch) (2.8.2)\n",
      "Requirement already satisfied: pytz>=2020.1 in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from pandas->docsearch) (2023.3.post1)\n",
      "Requirement already satisfied: tzdata>=2022.1 in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from pandas->docsearch) (2023.3)\n",
      "Requirement already satisfied: six>=1.5 in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from python-dateutil>=2.8.2->pandas->docsearch) (1.16.0)\n",
      "Requirement already satisfied: wrapt in /Users/fusar/anaconda3/envs/api_hackathon/lib/python3.8/site-packages (from smart-open>=1.8.1->gensim->docsearch) (1.16.0)\n",
      "Downloading gensim-4.3.2-cp38-cp38-macosx_11_0_arm64.whl (24.0 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.0/24.0 MB\u001b[0m \u001b[31m29.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading smart_open-7.0.4-py3-none-any.whl (61 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.2/61.2 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hBuilding wheels for collected packages: docsearch, pyemd, stop_words\n",
      "  Building wheel for docsearch (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for docsearch: filename=docsearch-1.0-py3-none-any.whl size=4403 sha256=ef62e476af49bfeb2d82601f69668c334e82688afc7568cd6f5b76728826cd5b\n",
      "  Stored in directory: /Users/fusar/Library/Caches/pip/wheels/7b/67/17/84cd2974bfcceb566031ea8aaafe7878bfa7df321b0b6931dd\n",
      "  Building wheel for pyemd (pyproject.toml) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for pyemd: filename=pyemd-1.0.0-cp38-cp38-macosx_11_0_arm64.whl size=182816 sha256=4b0216fbea23e8122d6b646229618c5800f9fa9e746f70351e5acab88d5a47ff\n",
      "  Stored in directory: /Users/fusar/Library/Caches/pip/wheels/f1/70/0e/06a1f01d960b40b01077a2c9c686281b93b88713260d40872e\n",
      "  Building wheel for stop_words (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for stop_words: filename=stop_words-2018.7.23-py3-none-any.whl size=32898 sha256=ce7404fdf79fc21b137db12bdc1551e8de33b998459b926b7b239eb7d677d89f\n",
      "  Stored in directory: /Users/fusar/Library/Caches/pip/wheels/eb/03/0d/3bd31c983789aeb0b4d5e2ca48590288d9db1586cf5f225062\n",
      "Successfully built docsearch pyemd stop_words\n",
      "Installing collected packages: stop_words, smart-open, pyemd, gensim, docsearch\n",
      "Successfully installed docsearch-1.0 gensim-4.3.2 pyemd-1.0.0 smart-open-7.0.4 stop_words-2018.7.23\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install docsearch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b85fd13e-ee3a-4102-a6f2-52c2edd97f29",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}