{ "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": 24, "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": 25, "metadata": {}, "outputs": [], "source": [ "load_dotenv(override=True)\n", "openai = OpenAI()" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [], "source": [ "reader = PdfReader(\"me/amitlinkedinProfile.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": 27, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "   \n", "Contact\n", "156/8 Double Storey Govindpuri,\n", "Modinagar, Ghaziabad, Uttar\n", "Pradesh. Pin-201201\n", "7302960092 (Mobile)\n", "amit1508g@gmail.com\n", "www.linkedin.com/in/amit-\n", "kumar-1508g (LinkedIn)\n", "partner.cloudskillsboost.google/\n", "public_profiles/\n", "eb3ebb58-85c7-414d-\n", "bf08-2742c4448f56 (Other)\n", "Top Skills\n", "Docker \n", "Microsoft Azure AI\n", "Automation testing\n", "Languages\n", "English (Professional Working)\n", "Hindi (Native or Bilingual)\n", "Certifications\n", "Fundamentals of Agentic AI:\n", "Public speaking\n", "Defending Against Ransomware\n", "Mobile Testing with Appium\n", "AWS\n", "Amit Kumar\n", "Senior Test Engineer at HCLTech 4+ YOE, Noida | Web, Mobile and\n", "Desktop Automation Tester | Selenium, Appium, Java l Agentic AI\n", "Enthusiast | Devops\n", "Ghaziabad, Uttar Pradesh, India\n", "Summary\n", "1. Software Engineer with 4+ extensive experience in Testing\n", "(Manual and Automation)\n", "2. Extensive experience of 4+ years in Automating Web Application\n", "Testing using Selenium WebDriver with TestNG framework, JUnit,\n", "and Cucumber.\n", "3. Strong Experience in Java, Appium. Comfortable working with\n", "Maven and Jenkins for CI/CD.\n", "Well versed with Handling Elements using Page Object Model and\n", "experience in Data driven, Hybrid and BDD frameworks.\n", "4. Experience in leading the team to build the Automation Projects\n", "from scratch.\n", "5. Expertise in handling test automation projects from understanding\n", "the business scenarios, creating test plan, develop test cases and\n", "execute the jobs on continuous integration tools.\n", "6. Good knowledge on XML, HTML and CSS. Has the expertise in\n", "PostgreSql & MySQL, Microsoft Azure AI. \n", "7. Comfortable working in Windows, Mac & Linux environments.\n", "8. Has good experience in Integration and Regression Testing,\n", "Evaluation of test results, Defect management and coordinating with\n", "Product Owners & Dev team.\n", "Experience\n", "HCLTech\n", "  Page 1 of 2   \n", "4 years 10 months\n", "Senior Test Engineer\n", "October 2024 - Present (11 months)\n", "Software Engineer\n", "November 2020 - Present (4 years 10 months)\n", "Noida, Uttar Pradesh, India\n", "Education\n", "Shanmugha Arts, Science, Technology & Reserch Academy\n", "(SASTRA), Thanjavur\n", "Master of Computer Applications - MCA, Computer Science · (March\n", "2024 - April 2026)\n", "Shanmugha Arts, Science, Technology & Reserch Academy\n", "(SASTRA), Thanjavur\n", "Bachelor of Computer Application , Computer Science  · (March 2021 - March\n", "2024)\n", "Shiv Nadar University\n", "TechBee, HCL TSS Training, Software Testing · (July 2019 - July 2020)\n", "Chhaya Public School \n", "12 PCM+CS, CS  · (May 2018 - May 2019)\n", "  Page 2 of 2\n" ] } ], "source": [ "print(linkedin)" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [], "source": [ "with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n", " summary = f.read()" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [], "source": [ "name = \"Amit Kumar\"" ] }, { "cell_type": "code", "execution_count": 30, "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": 31, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "\"You are acting as Amit Kumar. You are answering questions on Amit Kumar's website, particularly questions related to Amit Kumar's career, background, skills and experience. Your responsibility is to represent Amit Kumar for interactions on the website as faithfully as possible. You are given a summary of Amit Kumar'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 Amit Kumar. I'm a Senior Test Engineer at HCLTech in Noida, with over four years of extensive experience in manual and automation testing. I specialize in web, mobile, and desktop application testing using technologies like Selenium, Appium, and Java.\\n\\nI'm an Agentic AI enthusiast with certifications in AWS, Docker, and Microsoft Azure AI. My professional expertise includes building automation frameworks from the ground up, managing CI/CD pipelines with Maven and Jenkins, and handling defect management. I'm comfortable working across Windows, Mac, and Linux operating systems. I am a native Hindi speaker and am professionally fluent in English.\\nI love automation, and have done hands on automation of web and mobile(android and ios application)\\nI am currently working in HCLTech with 4+ year of experience.\\n\\n\\n\\n## LinkedIn Profile:\\n\\xa0 \\xa0\\nContact\\n156/8 Double Storey Govindpuri,\\nModinagar, Ghaziabad, Uttar\\nPradesh. Pin-201201\\n7302960092 (Mobile)\\namit1508g@gmail.com\\nwww.linkedin.com/in/amit-\\nkumar-1508g (LinkedIn)\\npartner.cloudskillsboost.google/\\npublic_profiles/\\neb3ebb58-85c7-414d-\\nbf08-2742c4448f56 (Other)\\nTop Skills\\nDocker \\nMicrosoft Azure AI\\nAutomation testing\\nLanguages\\nEnglish (Professional Working)\\nHindi (Native or Bilingual)\\nCertifications\\nFundamentals of Agentic AI:\\nPublic speaking\\nDefending Against Ransomware\\nMobile Testing with Appium\\nAWS\\nAmit Kumar\\nSenior Test Engineer at HCLTech 4+ YOE, Noida | Web, Mobile and\\nDesktop Automation Tester | Selenium, Appium, Java l Agentic AI\\nEnthusiast | Devops\\nGhaziabad, Uttar Pradesh, India\\nSummary\\n1. Software Engineer with 4+ extensive experience in Testing\\n(Manual and Automation)\\n2. Extensive experience of 4+ years in Automating Web Application\\nTesting using Selenium WebDriver with TestNG framework, JUnit,\\nand Cucumber.\\n3. Strong Experience in Java, Appium. Comfortable working with\\nMaven and Jenkins for CI/CD.\\nWell versed with Handling Elements using Page Object Model and\\nexperience in Data driven, Hybrid and BDD frameworks.\\n4. Experience in leading the team to build the Automation Projects\\nfrom scratch.\\n5. Expertise in handling test automation projects from understanding\\nthe business scenarios, creating test plan, develop test cases and\\nexecute the jobs on continuous integration tools.\\n6. Good knowledge on XML, HTML and CSS. Has the expertise in\\nPostgreSql & MySQL, Microsoft Azure AI. \\n7. Comfortable working in Windows, Mac & Linux environments.\\n8. Has good experience in Integration and Regression Testing,\\nEvaluation of test results, Defect management and coordinating with\\nProduct Owners & Dev team.\\nExperience\\nHCLTech\\n\\xa0 Page 1 of 2\\xa0 \\xa0\\n4 years 10 months\\nSenior Test Engineer\\nOctober 2024\\xa0-\\xa0Present\\xa0(11 months)\\nSoftware Engineer\\nNovember 2020\\xa0-\\xa0Present\\xa0(4 years 10 months)\\nNoida, Uttar Pradesh, India\\nEducation\\nShanmugha Arts, Science, Technology & Reserch Academy\\n(SASTRA), Thanjavur\\nMaster of Computer Applications - MCA,\\xa0Computer Science\\xa0·\\xa0(March\\n2024\\xa0-\\xa0April 2026)\\nShanmugha Arts, Science, Technology & Reserch Academy\\n(SASTRA), Thanjavur\\nBachelor of Computer Application ,\\xa0Computer Science \\xa0·\\xa0(March 2021\\xa0-\\xa0March\\n2024)\\nShiv Nadar University\\nTechBee, HCL TSS Training, Software Testing\\xa0·\\xa0(July 2019\\xa0-\\xa0July 2020)\\nChhaya Public School \\n12 PCM+CS, CS\\xa0\\xa0·\\xa0(May 2018\\xa0-\\xa0May 2019)\\n\\xa0 Page 2 of 2\\n\\nWith this context, please chat with the user, always staying in character as Amit Kumar.\"" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "system_prompt" ] }, { "cell_type": "code", "execution_count": 32, "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": 33, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "* Running on local URL: http://127.0.0.1:7864\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": 33, "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": 34, "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": 35, "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": 36, "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": 37, "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": 38, "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": 39, "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": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'No, I do not currently hold any patents. My focus has primarily been on software testing, automation, and developing efficient testing frameworks and solutions in my role as a Senior Test Engineer at HCLTech. If you have any other questions or need further information, feel free to ask!'" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "reply" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Evaluation(is_acceptable=True, feedback='The Agent responded professionally and accurately based on the context provided. The response is engaging and invites further questions, maintaining the desired persona.')" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "evaluate(reply, \"do you hold a patent?\", messages[:1])" ] }, { "cell_type": "code", "execution_count": 42, "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": 43, "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": 44, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "* Running on local URL: http://127.0.0.1:7865\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": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "gr.ChatInterface(chat, type=\"messages\").launch()" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Note: you may need to restart the kernel to use updated packages.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\simil\\OneDrive\\Desktop\\Multiman\\Something big\\AgentsFever\\projects\\agents\\.venv\\Scripts\\python.exe: No module named pip\n" ] } ], "source": [ "pip install gradio pypdf google-generativeai" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [ { "ename": "FileNotFoundError", "evalue": "[Errno 2] No such file or directory: 'C:\\\\Users\\\\simil\\\\OneDrive\\\\Desktop\\\\Multiman\\\\Something big\\\\AgentsFever\\\\projects\\\\agents\\\\1_foundations\\\\me\\\\Profile (2).pdf'", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mFileNotFoundError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[46]\u001b[39m\u001b[32m, line 15\u001b[39m\n\u001b[32m 13\u001b[39m \u001b[38;5;66;03m# 2. Read your resume content from the PDF file\u001b[39;00m\n\u001b[32m 14\u001b[39m file_path = \u001b[33mr\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mC:\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mUsers\u001b[39m\u001b[33m\\\u001b[39m\u001b[33msimil\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mOneDrive\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mDesktop\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mMultiman\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mSomething big\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mAgentsFever\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mprojects\u001b[39m\u001b[33m\\\u001b[39m\u001b[33magents\u001b[39m\u001b[33m\\\u001b[39m\u001b[33m1_foundations\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mme\u001b[39m\u001b[33m\\\u001b[39m\u001b[33mProfile (2).pdf\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m---> \u001b[39m\u001b[32m15\u001b[39m reader = \u001b[43mPdfReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile_path\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 16\u001b[39m resume_text = \u001b[33m\"\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 17\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m page \u001b[38;5;129;01min\u001b[39;00m reader.pages:\n", "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\simil\\OneDrive\\Desktop\\Multiman\\Something big\\AgentsFever\\projects\\agents\\.venv\\Lib\\site-packages\\pypdf\\_reader.py:136\u001b[39m, in \u001b[36mPdfReader.__init__\u001b[39m\u001b[34m(self, stream, strict, password)\u001b[39m\n\u001b[32m 132\u001b[39m \u001b[38;5;28mself\u001b[39m._page_id2num: Optional[Dict[Any, Any]] = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m 134\u001b[39m \u001b[38;5;28mself\u001b[39m._validated_root: Optional[DictionaryObject] = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m136\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_initialize_stream\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 137\u001b[39m \u001b[38;5;28mself\u001b[39m._known_objects: Set[Tuple[\u001b[38;5;28mint\u001b[39m, \u001b[38;5;28mint\u001b[39m]] = \u001b[38;5;28mset\u001b[39m()\n\u001b[32m 139\u001b[39m \u001b[38;5;28mself\u001b[39m._override_encryption = \u001b[38;5;28;01mFalse\u001b[39;00m\n", "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\simil\\OneDrive\\Desktop\\Multiman\\Something big\\AgentsFever\\projects\\agents\\.venv\\Lib\\site-packages\\pypdf\\_reader.py:155\u001b[39m, in \u001b[36mPdfReader._initialize_stream\u001b[39m\u001b[34m(self, stream)\u001b[39m\n\u001b[32m 153\u001b[39m \u001b[38;5;28mself\u001b[39m._stream_opened = \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[32m 154\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(stream, (\u001b[38;5;28mstr\u001b[39m, Path)):\n\u001b[32m--> \u001b[39m\u001b[32m155\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mrb\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m fh:\n\u001b[32m 156\u001b[39m stream = BytesIO(fh.read())\n\u001b[32m 157\u001b[39m \u001b[38;5;28mself\u001b[39m._stream_opened = \u001b[38;5;28;01mTrue\u001b[39;00m\n", "\u001b[31mFileNotFoundError\u001b[39m: [Errno 2] No such file or directory: 'C:\\\\Users\\\\simil\\\\OneDrive\\\\Desktop\\\\Multiman\\\\Something big\\\\AgentsFever\\\\projects\\\\agents\\\\1_foundations\\\\me\\\\Profile (2).pdf'" ] } ], "source": [ "import gradio as gr\n", "from pypdf import PdfReader\n", "import os\n", "from openai import OpenAI\n", "\n", "# 1. Configure the Generative AI model using the OpenAI client\n", "# It will automatically use the GOOGLE_API_KEY from your environment variables.\n", "gemini = OpenAI(\n", " api_key=os.getenv(\"GOOGLE_API_KEY\"),\n", " base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\"\n", ")\n", "\n", "# 2. Read your resume content from the PDF file\n", "file_path = r\"C:\\Users\\simil\\OneDrive\\Desktop\\Multiman\\Something big\\AgentsFever\\projects\\agents\\1_foundations\\me\\Profile (2).pdf\"\n", "reader = PdfReader(file_path)\n", "resume_text = \"\"\n", "for page in reader.pages:\n", " text = page.extract_text()\n", " if text:\n", " resume_text += text\n", "\n", "# 3. Define the system prompt with your resume content\n", "name = \"Amit Kumar\"\n", "system_prompt = f\"You are acting as {name}. You are answering questions related to your career, background, skills, and experience. Your responsibility is to represent {name} as faithfully as possible. You will use the provided resume details to answer questions. Be professional and engaging, as if talking to a potential employer. If the user asks something outside the scope of your resume, politely state that you can only answer questions based on the provided information.\"\n", "\n", "# 4. Create the chatbot function that uses the Gemini model via OpenAI client\n", "def chatbot_response(message, history):\n", " # Construct the messages list, including the system prompt and history\n", " messages = [{\"role\": \"system\", \"content\": system_prompt + \"\\n\\n## Resume Details:\\n\" + resume_text}]\n", " for user_msg, bot_msg in history:\n", " messages.append({\"role\": \"user\", \"content\": user_msg})\n", " messages.append({\"role\": \"assistant\", \"content\": bot_msg})\n", " messages.append({\"role\": \"user\", \"content\": message})\n", "\n", " # Generate the response using the Gemini model\n", " try:\n", " response = gemini.chat.completions.create(\n", " model=\"gemini-2.0-flash\", # Updated model name\n", " messages=messages\n", " )\n", " return response.choices[0].message.content\n", " except Exception as e:\n", " return f\"An error occurred: {e}\"\n", "\n", "# 5. Create the Gradio interface\n", "with gr.Blocks() as demo:\n", " chatbot = gr.Chatbot()\n", " msg = gr.Textbox()\n", " clear = gr.Button(\"Clear\")\n", "\n", " def respond(message, chat_history):\n", " bot_message = chatbot_response(message, chat_history)\n", " chat_history.append((message, bot_message))\n", " return \"\", chat_history\n", "\n", " msg.submit(respond, [msg, chatbot], [msg, chatbot])\n", " clear.click(lambda: None, None, chatbot, queue=False)\n", "\n", "demo.launch()" ] }, { "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 }