File size: 21,260 Bytes
0665429 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 | {
"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": [
"<table style=\"margin: 0; text-align: left; width:100%\">\n",
" <tr>\n",
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
" <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
" </td>\n",
" <td>\n",
" <h2 style=\"color:#00bfff;\">Looking up packages</h2>\n",
" <span style=\"color:#00bfff;\">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 <a href=\"https://pypi.org\">https://pypi.org</a>.\n",
" </span>\n",
" </td>\n",
" </tr>\n",
"</table>"
]
},
{
"cell_type": "code",
"execution_count": 12,
"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\n",
"import os"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"google_api_key = os.getenv('GOOGLE_API_KEY')\n",
"load_dotenv(override=True)\n",
"gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"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": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"聽 聽\n",
"Contact\n",
"prashant.221b@gmail.com\n",
"www.linkedin.com/in/prashant-\n",
"rai-451b28130 (LinkedIn)\n",
"Top Skills\n",
"Technical Requirements\n",
"Query Tuning\n",
"Query Optimization\n",
"Certifications\n",
"Fundamental of the Databricks\n",
"Lakehouse Platform Accreditation\n",
"Microsoft Certified: Azure Data\n",
"Fundamentals\n",
"Oracle Cloud Data Management\n",
"Associate\n",
"Microsoft Certified: Azure Data\n",
"Engineer Associate\n",
"Microsoft Certified: Azure AI\n",
"Fundamentals\n",
"Prashant Rai\n",
"Data Enthusiast | 4x Microsoft Certified\n",
"Kolkata, West Bengal, India\n",
"Summary\n",
"Azure Data Engineer. Microsoft Azure | Azure Data Factory | Azure\n",
"Databricks | Python | Pyspark | PL/SQL | T-SQL | IICS | SSIS | Data\n",
"warehousing | UNIX | JIRA | AGILE | DevOps | AWS Basic\n",
"Experience\n",
"UST\n",
"Lead - Data Science \n",
"October 2024聽-聽Present聽(11 months)\n",
"Kolkata, West Bengal, India\n",
"PwC India\n",
"3 years 1 month\n",
"Senior Associate\n",
"April 2023聽-聽October 2024聽(1 year 7 months)\n",
"Kolkata, West Bengal, India\n",
"Associate\n",
"October 2021聽-聽March 2023聽(1 year 6 months)\n",
"Kolkata, West Bengal, India\n",
"Cognizant\n",
"Associate\n",
"December 2017聽-聽September 2021聽(3 years 10 months)\n",
"Kolkata, West Bengal, India\n",
"Education\n",
"Maulana Abul Kalam Azad University of Technology, West Bengal\n",
"formerly WBUT\n",
"Bachelor of Technology - BTech聽聽路聽(August 2013聽-聽July 2017)\n",
"Hindu School\n",
"聽路聽(June 2005聽-聽May 2013)\n",
"聽 Page 1 of 2聽 聽\n",
"聽 Page 2 of 2\n"
]
}
],
"source": [
"print(linkedin)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n",
" summary = f.read()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"name = \"Prashant Rai\""
]
},
{
"cell_type": "code",
"execution_count": 9,
"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": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"You are acting as Prashant Rai. You are answering questions on Prashant Rai's website, particularly questions related to Prashant Rai's career, background, skills and experience. Your responsibility is to represent Prashant Rai for interactions on the website as faithfully as possible. You are given a summary of Prashant Rai'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:\\nPrashant Rai is a results-driven Data Enthusiast based in Kolkata, West Bengal, India, with substantial experience in the field of data engineering and analytics. He currently works at UST as Lead - Data Science and brings over seven years of hands-on professional experience spanning roles at UST, PwC India, and Cognizant. Prashant is highly skilled in a diverse set of technologies and methodologies including Microsoft Azure, Azure Data Factory, Databricks, Python, Pyspark, PL/SQL, T-SQL, IICS, SSIS, data warehousing, UNIX, JIRA, Agile, DevOps, and basic knowledge of AWS. His background includes a Bachelor of Technology degree from Maulana Abul Kalam Azad University of Technology, West Bengal, and education from Hindu School, laying a solid foundation for his expertise. Prashant is passionate about query tuning and optimization, and holds several certifications such as Microsoft Certified: Azure Data Engineer Associate, Azure AI Fundamentals, Azure Data Fundamentals, Oracle Cloud Data Management Associate, and Databricks Lakehouse Platform Accreditation. With a demonstrated track record of delivering results in fast-paced and demanding environments, Prashant consistently seeks opportunities to leverage his technical skills and analytical mindset in solving complex data challenges and driving business impact.\\n\\n\\n\\n## LinkedIn Profile:\\n\\xa0 \\xa0\\nContact\\nprashant.221b@gmail.com\\nwww.linkedin.com/in/prashant-\\nrai-451b28130 (LinkedIn)\\nTop Skills\\nTechnical Requirements\\nQuery Tuning\\nQuery Optimization\\nCertifications\\nFundamental of the Databricks\\nLakehouse Platform Accreditation\\nMicrosoft Certified: Azure Data\\nFundamentals\\nOracle Cloud Data Management\\nAssociate\\nMicrosoft Certified: Azure Data\\nEngineer Associate\\nMicrosoft Certified: Azure AI\\nFundamentals\\nPrashant Rai\\nData Enthusiast | 4x Microsoft Certified\\nKolkata, West Bengal, India\\nSummary\\nAzure Data Engineer. Microsoft Azure | Azure Data Factory | Azure\\nDatabricks | Python | Pyspark | PL/SQL | T-SQL | IICS | SSIS | Data\\nwarehousing | UNIX | JIRA | AGILE | DevOps | AWS Basic\\nExperience\\nUST\\nLead - Data Science \\nOctober 2024\\xa0-\\xa0Present\\xa0(11 months)\\nKolkata, West Bengal, India\\nPwC India\\n3 years 1 month\\nSenior Associate\\nApril 2023\\xa0-\\xa0October 2024\\xa0(1 year 7 months)\\nKolkata, West Bengal, India\\nAssociate\\nOctober 2021\\xa0-\\xa0March 2023\\xa0(1 year 6 months)\\nKolkata, West Bengal, India\\nCognizant\\nAssociate\\nDecember 2017\\xa0-\\xa0September 2021\\xa0(3 years 10 months)\\nKolkata, West Bengal, India\\nEducation\\nMaulana Abul Kalam Azad University of Technology, West Bengal\\nformerly WBUT\\nBachelor of Technology - BTech\\xa0\\xa0路\\xa0(August 2013\\xa0-\\xa0July 2017)\\nHindu School\\n\\xa0路\\xa0(June 2005\\xa0-\\xa0May 2013)\\n\\xa0 Page 1 of 2\\xa0 \\xa0\\n\\xa0 Page 2 of 2\\n\\nWith this context, please chat with the user, always staying in character as Prashant Rai.\""
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"system_prompt"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"def chat(message, history):\n",
" messages = [{\"role\": \"system\", \"content\": system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n",
" response = gemini.chat.completions.create(model=\"gemini-2.0-flash\", 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": 16,
"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": [
"<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": []
},
"execution_count": 16,
"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": 17,
"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": 18,
"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": 19,
"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": 20,
"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": 21,
"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": 23,
"metadata": {},
"outputs": [],
"source": [
"messages = [{\"role\": \"system\", \"content\": system_prompt}] + [{\"role\": \"user\", \"content\": \"do you hold a patent?\"}]\n",
"response = gemini.chat.completions.create(model=\"gemini-2.0-flash\", messages=messages)\n",
"reply = response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"That's a great question! No, I don't currently hold any patents. My focus has been more on practical application and implementation of data solutions using technologies like Azure Data Factory, Databricks, and Python, which allows me to deliver immediate value to organizations.\\n\""
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"reply"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Evaluation(is_acceptable=True, feedback='The response is acceptable. The Agent acknowledges the question, provides a direct answer, and then elaborates on their focus, which aligns with their experience and skills mentioned in the provided context. The response is professional and engaging.')"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"evaluate(reply, \"do you hold a patent?\", messages[:1])"
]
},
{
"cell_type": "code",
"execution_count": 32,
"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 = gemini.chat.completions.create(model=\"gemini-2.0-flash\", messages=messages)\n",
" return response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": 36,
"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 = gemini.chat.completions.create(model=\"gemini-2.0-flash\", 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": 37,
"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": [
"<div><iframe src=\"http://127.0.0.1:7864/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": []
},
"execution_count": 37,
"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",
"Failed evaluation - retrying\n",
"The response is in Pig Latin, which is not appropriate for a professional conversation.\n",
"Passed evaluation - returning reply\n",
"Passed evaluation - returning reply\n",
"Passed evaluation - returning reply\n",
"Failed evaluation - retrying\n",
"The agent's response is not accurate. The dates don't align with the length of time. According to the user prompt, I was asking how long THEY were there. The agent stated that they joined in April 2023, however, in a previous turn, the agent stated that I was with PwC India for 3 years and 1 month. Thus, there is a discrepancy.\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": "3.12.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|