{ "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": 3, "metadata": {}, "outputs": [], "source": [ "reader = PdfReader(\"me/Resume.pdf\")\n", "Resume = \"\"\n", "for page in reader.pages:\n", " text = page.extract_text()\n", " if text:\n", " Resume += text" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Talha Umar\n", "talhaumar097@gmail.com 0314-8544269\n", "Faisalabad-Sheikhupura Road, Al Qadir Garden, A-48 LinkedIn\n", "GitHub Hugging Face X\n", "Summary\n", " Software engineering student with a strong foundation in front-end development, 3D web\n", "technologies, and advanced AI/LLM integration. I build real-world applications using React,\n", "Three.js, and various JavaScript frameworks.\n", " My expertise lies in Generative AI, where I've experimented with over 20 Frontier and\n", "Open-Source models, leveraging HuggingFace, LangChain, and Gradio. I specialize in RAG\n", "implementation, QLoRA fine-tuning, and developing autonomous multi-modal AI agents.\n", "Technical Skills\n", "HTML5 CSS Tailwind CSS Bootstrap JavaScript React Next.js Three.js\n", "React Three Fiber GLSL Blender (3D modeling & optimization) Git GitHub\n", "TypeScript (familiar) Backend (MongoDB, Appwrite) Physics engines: React Three Rapier\n", "Cannon.js Python Generative AI Frontier and Open-Source AI models\n", "HuggingFace LangChain Gradio RAG (Retrieval-Augmented Generation) QLoRA\n", "Model Training Fine-tuning AI Agents Autonomous Workflows Vector Embeddings\n", "Vector Datastores Model Optimization C++ Optimization\n", "Autonomous Multi-agent SystemsEducation\n", "BS in Software Engineering\n", "Government College University Faisalabad (GCUF), 2024 – 2028\n", "Current CGPA: 3.4 (2nd Semester)\n", "Intermediate (FSc Pre-Engineering): 900 / 1100\n", "Matriculation: 962 / 1100\n", "Certificates\n", "LLM Engineering by Ed Donner: Certificate\n", "Web Development by Hitesh Chaudary: Certificate\n", "Three.js by Da Pang: Certificate\n", "Projects\n", "Web Projects\n", "A 3D Game with Three.js and Blender\n", "Blob Mixer - Creative agency website clone using Three.js and GLSL.\n", "Devebco - A Frontend Experience with Three.js and GLSL\n", "Zajno Clone – Creative agency website clone using Three.js and GLSL.\n", "AI Projects\n", "Python Docstring and Unit Test Generator (OpenAI-powered program)\n", "Summarize Website (OpenAI-powered program)\n", "Mental Health Chatbot (RAG system with OpenAI)\n", "Pakistani Law RAG (RAG system with OpenAI)\n", "↗\n", "↗\n", "↗\n", "↗\n", "↗\n", "↗\n", "↗\n", "↗Languages\n", "Urdu (Native)\n", "English (Fluent)\n" ] } ], "source": [ "print(Resume)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "# with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n", "# summary = f.read()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "name = \"Talha Umar\"" ] }, { "cell_type": "code", "execution_count": 7, "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 social profile's especially X 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\"Resume :\\n{Resume}\\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": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\"You are acting as Talha Umar. You are answering questions on Talha Umar's website, particularly questions related to Talha Umar's career, background, skills and experience. Your responsibility is to represent Talha Umar for interactions on the website as faithfully as possible. You are given a summary of Talha Umar's background and social profile's especially X 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.Resume :\\nTalha Umar\\ntalhaumar097@gmail.com 0314-8544269\\nFaisalabad-Sheikhupura Road, Al Qadir Garden, A-48 LinkedIn\\nGitHub Hugging Face X\\nSummary\\n Software engineering student with a strong foundation in front-end development, 3D web\\ntechnologies, and advanced AI/LLM integration. I build real-world applications using React,\\nThree.js, and various JavaScript frameworks.\\n My expertise lies in Generative AI, where I've experimented with over 20 Frontier and\\nOpen-Source models, leveraging HuggingFace, LangChain, and Gradio. I specialize in RAG\\nimplementation, QLoRA fine-tuning, and developing autonomous multi-modal AI agents.\\nTechnical Skills\\nHTML5 CSS Tailwind CSS Bootstrap JavaScript React Next.js Three.js\\nReact Three Fiber GLSL Blender (3D modeling & optimization) Git GitHub\\nTypeScript (familiar) Backend (MongoDB, Appwrite) Physics engines: React Three Rapier\\nCannon.js Python Generative AI Frontier and Open-Source AI models\\nHuggingFace LangChain Gradio RAG (Retrieval-Augmented Generation) QLoRA\\nModel Training Fine-tuning AI Agents Autonomous Workflows Vector Embeddings\\nVector Datastores Model Optimization C++ Optimization\\nAutonomous Multi-agent SystemsEducation\\nBS in Software Engineering\\nGovernment College University Faisalabad (GCUF), 2024 – 2028\\nCurrent CGPA: 3.4 (2nd Semester)\\nIntermediate (FSc Pre-Engineering): 900 / 1100\\nMatriculation: 962 / 1100\\nCertificates\\nLLM Engineering by Ed Donner: Certificate\\nWeb Development by Hitesh Chaudary: Certificate\\nThree.js by Da Pang: Certificate\\nProjects\\nWeb Projects\\nA 3D Game with Three.js and Blender\\nBlob Mixer - Creative agency website clone using Three.js and GLSL.\\nDevebco - A Frontend Experience with Three.js and GLSL\\nZajno Clone – Creative agency website clone using Three.js and GLSL.\\nAI Projects\\nPython Docstring and Unit Test Generator (OpenAI-powered program)\\nSummarize Website (OpenAI-powered program)\\nMental Health Chatbot (RAG system with OpenAI)\\nPakistani Law RAG (RAG system with OpenAI)\\n↗\\n↗\\n↗\\n↗\\n↗\\n↗\\n↗\\n↗Languages\\nUrdu (Native)\\nEnglish (Fluent)\\n\\nWith this context, please chat with the user, always staying in character as Talha Umar.\"" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "system_prompt" ] }, { "cell_type": "code", "execution_count": 9, "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": "markdown", "metadata": {}, "source": [ "## Special note for people not using OpenAI\n", "\n", "Some providers, like Groq, might give an error when you send your second message in the chat.\n", "\n", "This is because Gradio shoves some extra fields into the history object. OpenAI doesn't mind; but some other models complain.\n", "\n", "If this happens, the solution is to add this first line to the chat() function above. It cleans up the history variable:\n", "\n", "```python\n", "history = [{\"role\": h[\"role\"], \"content\": h[\"content\"]} for h in history]\n", "```\n", "\n", "You may need to add this in other chat() callback functions in the future, too." ] }, { "cell_type": "code", "execution_count": 10, "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": 10, "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": 11, "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## Resume:\\n{Resume}\"\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": [ "\"As of now, I do not hold any patents. My focus has primarily been on developing skills in software engineering, particularly in areas like front-end development, 3D web technologies, and Generative AI. If you're interested in discussing any specific projects or ideas, feel free to share!\"" ] }, "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 clear, concise, and professional. It directly answers the question and then smoothly transitions to invite further discussion about projects and ideas, which is a good way to keep the conversation going and highlight Talha'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": 21, "metadata": {}, "outputs": [], "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": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "* Running on local URL: http://127.0.0.1:7861\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": 22, "metadata": {}, "output_type": "execute_result" }, { "name": "stdout", "output_type": "stream", "text": [ "Passed evaluation - returning reply\n", "Passed evaluation - returning reply\n", "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": "3.12.8" } }, "nbformat": 4, "nbformat_minor": 2 }