{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Welcome to Lab 3 for Week 1 Day 4\n", "\n", "Today we're going to build something with immediate value!\n", "\n", "In the folder `me` I've put a single file `linkedin.pdf` - it's a PDF download of my LinkedIn profile.\n", "\n", "Please replace it with yours!\n", "\n", "I've also made a file called `summary.txt`\n", "\n", "We're not going to use Tools just yet - we're going to add the tool tomorrow." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", "

Looking up packages

\n", " In this lab, we're going to use the wonderful Gradio package for building quick UIs, \n", " and we're also going to use the popular PyPDF PDF reader. You can get guides to these packages by asking \n", " ChatGPT or Claude, and you find all open-source packages on the repository https://pypi.org.\n", " \n", "
" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# If you don't know what any of these packages do - you can always ask ChatGPT for a guide!\n", "\n", "from dotenv import load_dotenv\n", "from openai import OpenAI\n", "from pypdf import PdfReader\n", "import gradio as gr" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "load_dotenv(override=True)\n", "openai = OpenAI()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "reader = PdfReader(\"me/linkedin.pdf\")\n", "linkedin = \"\"\n", "for page in reader.pages:\n", " text = page.extract_text()\n", " if text:\n", " linkedin += text" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "   \n", "Contact\n", "Vasanthnatarajan538@gmail.c\n", "om\n", "www.linkedin.com/in/vasanth-\n", "natarajan-b509351a5 (LinkedIn)\n", "Top Skills\n", "Programming\n", "Graduate Level\n", "PyTorch\n", "Languages\n", "English\n", "Tamil\n", "Hindi\n", "Certifications\n", "Introduction to Programming with\n", "MATLAB\n", "Internship on Content development\n", "SQL\n", "AWS Technical Essentials\n", "Professional Development Program\n", "Vasanth Natarajan\n", "Postgraduate student at UNSW (Masters in Information Technology)\n", "Sydney, New South Wales, Australia\n", "Summary\n", "• Completed my UG in Electrical and Electronics Engineering from\n", "College of Engineering Guindy.\n", "• Pursuing my Postgraduate degree in Masters of Information\n", "Technology from University of New South Wales Sydney.\n", "Experience\n", "Woolworths Group\n", "Customer Service Representative\n", "February 2024 - Present (1 year 6 months)\n", "Mphasis\n", "Software Engineer\n", "June 2022 - May 2023 (1 year)\n", "- Backend: Java, Springboot, Microservices, Junit, Servlet, JDBC, JSP.\n", "Frontend: HTML, CSS, Javascript, Angular, Bootstrap\n", "Testing: Selenium, TestNG, Docker, AWS\n", "Education\n", "UNSW\n", "Master's degree, Information Technology · (May 2023)\n", "College of Engineering, Guindy\n", "Bachelor of Engineering - BE, Electrical and Electronics\n", "Engineering · (2018 - 2022)\n", "Maharishi Vidya Mandir Senior Secondary School\n", " · (2015 - 2018)\n", "  Page 1 of 1\n" ] } ], "source": [ "print(linkedin)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n", " summary = f.read()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "name = \"Vasanth Natarajan\"" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "system_prompt = f\"You are acting as {name}. You are answering questions on {name}'s website, \\\n", "particularly questions related to {name}'s career, background, skills and experience. \\\n", "Your responsibility is to represent {name} for interactions on the website as faithfully as possible. \\\n", "You are given a summary of {name}'s background and LinkedIn profile which you can use to answer questions. \\\n", "Be professional and engaging, as if talking to a potential client or future employer who came across the website. \\\n", "If you don't know the answer, say so.\"\n", "\n", "system_prompt += f\"\\n\\n## Summary:\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n", "system_prompt += f\"With this context, please chat with the user, always staying in character as {name}.\"\n" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\"You are acting as Vasanth Natarajan. You are answering questions on Vasanth Natarajan's website, particularly questions related to Vasanth Natarajan's career, background, skills and experience. Your responsibility is to represent Vasanth Natarajan for interactions on the website as faithfully as possible. You are given a summary of Vasanth Natarajan's background and LinkedIn profile which you can use to answer questions. Be professional and engaging, as if talking to a potential client or future employer who came across the website. If you don't know the answer, say so.\\n\\n## Summary:\\nMy name is Ed Donner. I'm an entrepreneur, software engineer and data scientist. I'm originally from London, England, but I moved to NYC in 2000.\\nI love all foods, particularly French food, but strangely I'm repelled by almost all forms of cheese. I'm not allergic, I just hate the taste! I make an exception for cream cheese and mozarella though - cheesecake and pizza are the greatest.\\n\\n## LinkedIn Profile:\\n\\xa0 \\xa0\\nContact\\nVasanthnatarajan538@gmail.c\\nom\\nwww.linkedin.com/in/vasanth-\\nnatarajan-b509351a5 (LinkedIn)\\nTop Skills\\nProgramming\\nGraduate Level\\nPyTorch\\nLanguages\\nEnglish\\nTamil\\nHindi\\nCertifications\\nIntroduction to Programming with\\nMATLAB\\nInternship on Content development\\nSQL\\nAWS Technical Essentials\\nProfessional Development Program\\nVasanth Natarajan\\nPostgraduate student at UNSW (Masters in Information Technology)\\nSydney, New South Wales, Australia\\nSummary\\n• Completed my UG in Electrical and Electronics Engineering from\\nCollege of Engineering Guindy.\\n• Pursuing my Postgraduate degree in Masters of Information\\nTechnology from University of New South Wales Sydney.\\nExperience\\nWoolworths Group\\nCustomer Service Representative\\nFebruary 2024\\xa0-\\xa0Present\\xa0(1 year 6 months)\\nMphasis\\nSoftware Engineer\\nJune 2022\\xa0-\\xa0May 2023\\xa0(1 year)\\n- Backend: Java, Springboot, Microservices, Junit, Servlet, JDBC, JSP.\\nFrontend: HTML, CSS, Javascript, Angular, Bootstrap\\nTesting: Selenium, TestNG, Docker, AWS\\nEducation\\nUNSW\\nMaster's degree,\\xa0Information Technology\\xa0·\\xa0(May 2023)\\nCollege of Engineering, Guindy\\nBachelor of Engineering - BE,\\xa0Electrical and Electronics\\nEngineering\\xa0·\\xa0(2018\\xa0-\\xa02022)\\nMaharishi Vidya Mandir Senior Secondary School\\n\\xa0·\\xa0(2015\\xa0-\\xa02018)\\n\\xa0 Page 1 of 1\\n\\nWith this context, please chat with the user, always staying in character as Vasanth Natarajan.\"" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "system_prompt" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "def chat(message, history):\n", " messages = [{\"role\": \"system\", \"content\": system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n", " response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n", " return response.choices[0].message.content" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "* Running on local URL: http://127.0.0.1:7860\n", "* To create a public link, set `share=True` in `launch()`.\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "gr.ChatInterface(chat, type=\"messages\").launch()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## A lot is about to happen...\n", "\n", "1. Be able to ask an LLM to evaluate an answer\n", "2. Be able to rerun if the answer fails evaluation\n", "3. Put this together into 1 workflow\n", "\n", "All without any Agentic framework!" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "# Create a Pydantic model for the Evaluation\n", "\n", "from pydantic import BaseModel\n", "\n", "class Evaluation(BaseModel):\n", " is_acceptable: bool\n", " feedback: str\n" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "evaluator_system_prompt = f\"You are an evaluator that decides whether a response to a question is acceptable. \\\n", "You are provided with a conversation between a User and an Agent. Your task is to decide whether the Agent's latest response is acceptable quality. \\\n", "The Agent is playing the role of {name} and is representing {name} on their website. \\\n", "The Agent has been instructed to be professional and engaging, as if talking to a potential client or future employer who came across the website. \\\n", "The Agent has been provided with context on {name} in the form of their summary and LinkedIn details. Here's the information:\"\n", "\n", "evaluator_system_prompt += f\"\\n\\n## Summary:\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n", "evaluator_system_prompt += f\"With this context, please evaluate the latest response, replying with whether the response is acceptable and your feedback.\"" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "def evaluator_user_prompt(reply, message, history):\n", " user_prompt = f\"Here's the conversation between the User and the Agent: \\n\\n{history}\\n\\n\"\n", " user_prompt += f\"Here's the latest message from the User: \\n\\n{message}\\n\\n\"\n", " user_prompt += f\"Here's the latest response from the Agent: \\n\\n{reply}\\n\\n\"\n", " user_prompt += \"Please evaluate the response, replying with whether it is acceptable and your feedback.\"\n", " return user_prompt" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "import os\n", "gemini = OpenAI(\n", " api_key=os.getenv(\"GOOGLE_API_KEY\"), \n", " base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\"\n", ")" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "def evaluate(reply, message, history) -> Evaluation:\n", "\n", " messages = [{\"role\": \"system\", \"content\": evaluator_system_prompt}] + [{\"role\": \"user\", \"content\": evaluator_user_prompt(reply, message, history)}]\n", " response = gemini.beta.chat.completions.parse(model=\"gemini-2.0-flash\", messages=messages, response_format=Evaluation)\n", " return response.choices[0].message.parsed" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [], "source": [ "messages = [{\"role\": \"system\", \"content\": system_prompt}] + [{\"role\": \"user\", \"content\": \"do you hold a patent?\"}]\n", "response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n", "reply = response.choices[0].message.content" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'I do not currently hold a patent. My focus has mainly been on my education and professional experience in software development and information technology. If you have any specific questions related to my skills or projects, feel free to ask!'" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "reply" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Evaluation(is_acceptable=True, feedback=\"The response is acceptable. It's accurate based on the provided context, and it's phrased in a professional and engaging manner. The agent appropriately redirects the conversation back to areas of Vasanth's expertise.\")" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "evaluate(reply, \"do you hold a patent?\", messages[:1])" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [], "source": [ "def rerun(reply, message, history, feedback):\n", " updated_system_prompt = system_prompt + \"\\n\\n## Previous answer rejected\\nYou just tried to reply, but the quality control rejected your reply\\n\"\n", " updated_system_prompt += f\"## Your attempted answer:\\n{reply}\\n\\n\"\n", " updated_system_prompt += f\"## Reason for rejection:\\n{feedback}\\n\\n\"\n", " messages = [{\"role\": \"system\", \"content\": updated_system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n", " response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n", " return response.choices[0].message.content" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Passed evaluation - returning reply\n", "Passed evaluation - returning reply\n" ] } ], "source": [ "def chat(message, history):\n", " if \"Patent\" in message:\n", " system = system_prompt + \"\\n\\nEverything in your reply needs to be in pig latin - \\\n", " it is mandatory that you respond only and entirely in pig latin\"\n", " else:\n", " system = system_prompt\n", " messages = [{\"role\": \"system\", \"content\": system}] + history + [{\"role\": \"user\", \"content\": message}]\n", " response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n", " reply =response.choices[0].message.content\n", "\n", " evaluation = evaluate(reply, message, history)\n", " \n", " if evaluation.is_acceptable:\n", " print(\"Passed evaluation - returning reply\")\n", " else:\n", " print(\"Failed evaluation - retrying\")\n", " print(evaluation.feedback)\n", " reply = rerun(reply, message, history, evaluation.feedback) \n", " return reply" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "* Running on local URL: http://127.0.0.1:7862\n", "* To create a public link, set `share=True` in `launch()`.\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" }, { "name": "stdout", "output_type": "stream", "text": [ "Passed evaluation - returning reply\n" ] } ], "source": [ "gr.ChatInterface(chat, type=\"messages\").launch()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": ".venv", "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": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 2 }