File size: 48,903 Bytes
dad14ba |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 |
{
"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 PyPDF2 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": 2,
"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": 3,
"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",
"candy519.murali@gmail.com\n",
"www.linkedin.com/in/gomurali\n",
"(LinkedIn)\n",
"www.youtube.com/\n",
"@awsclouddemos (Other)\n",
"Top Skills\n",
"Full-Stack Development\n",
"Solution Architecture\n",
"DevOps\n",
"Languages\n",
"English\n",
"Certifications\n",
"Oracle Certified Associate, Java SE\n",
"8 Programmer\n",
"ECMAScript 6\n",
"Java 8\n",
"Adobe Certified Expert\n",
"Murali Nutalapati\n",
"Full Stack Engineer specializing in AWS, Frontend, ReactJS,\n",
"NextJS, NodeJs, DevOps\n",
"United Kingdom\n",
"Summary\n",
"As a Full Stack Engineer with a specialty in React.js and AWS,\n",
"my current role involves building high-performance single-page\n",
"applications (SPAs) and embracing test-driven development (TDD)\n",
"for robust outcomes. At NTT DATA UK, my tenure as a Principal\n",
"Consultant honed my competencies in project leadership and cross-\n",
"functional team facilitation.\n",
"The development journey is marked by continuous learning and the\n",
"mentoring of junior developers, ensuring the adoption of industry-\n",
"standard practices. Our team's success reflects in the refactoring of\n",
"legacy codebases, improving system performance, and maintaining\n",
"a collaborative learning environment that drives innovation and\n",
"maintainability.\n",
"Experience\n",
"Freelance\n",
"Full Stack Engineer\n",
"September 2024 - Present (10 months)\n",
"NTT DATA UK\n",
"Principal Consultant\n",
"October 2021 - August 2024 (2 years 11 months)\n",
"London, England, United Kingdom\n",
"Sky\n",
"Contract Full Stack Developer\n",
"March 2023 - December 2023 (10 months)\n",
"London Area, United Kingdom\n",
"1. Worked with cross-functional development teams.\n",
"2. Built SPA web apps and Test-driven development.\n",
"3. Code Reviews and unit tests.\n",
" Page 1 of 4 \n",
"4. Mentored junior developers in adopting industry-standard practices while\n",
"fostering a collaborative \n",
"learning environment within the team.\n",
"5. Refactored legacy codebases to improve maintainability, readability, and\n",
"overall system performance \n",
"over time.\n",
"BT\n",
"Full Stack Engineer\n",
"October 2021 - April 2023 (1 year 7 months)\n",
"London, England, United Kingdom\n",
"1. Worked on ReactJS, Next.JS, Typescript, NodeJS, AWS.\n",
"2. Worked closely with product owners and Engineering manager.\n",
"3. Built oAuth2.0+ OIDC npm package which is used by 10+ teams in BT\n",
"4. Led architecture design decisions to ensure application scalability,\n",
"modularity,\n",
"and maintainability in the long run.\n",
"5. Utilized Azure for deploying scalable infrastructure components in a cost-\n",
"effective\n",
"manner.\n",
"VATGlobal\n",
"Senior Frontend Developer\n",
"November 2019 - September 2021 (1 year 11 months)\n",
"United Kingdom\n",
"1. Worked closely with Product owner to establish and deliver requirements.\n",
"2. Developed code fixes and enhancements.\n",
"3. Developed reusable UI components using modern JavaScript frameworks\n",
"like\n",
"React, increasing productivity of the entire development team.\n",
"4. Collaborated with UX designers to create seamless user interfaces for web\n",
"applications.\n",
"5. Reduced page load time significantly with advanced optimization techniques\n",
"like\n",
"lazy loading, minification, and caching strategies.\n",
"BP\n",
"Contract Full-stack developer\n",
"April 2019 - October 2019 (7 months)\n",
"London, United Kingdom\n",
" Page 2 of 4 \n",
"Sonata Software\n",
"5 years 3 months\n",
"Software Consultant\n",
"July 2017 - December 2018 (1 year 6 months)\n",
"Hyderabad Area, India\n",
"1. Developed code fixes and enhancements for inclusion in future code\n",
"releases and patches.\n",
"2. Identified and suggested new technologies and tools for enhancing product\n",
"value and increasing team productivity.\n",
"3. Worked closely with clients to establish problem specifications and system\n",
"designs.\n",
"4. Collaborated with developers and performance engineers to enhance\n",
"supportability and identify performance bottlenecks.\n",
"5. Maintained existing applications and designed and delivered new\n",
"applications.\n",
"Senior systems analyst\n",
"October 2013 - June 2017 (3 years 9 months)\n",
"Hyderabad Area, India\n",
"Travelopia\n",
"Frontend Developer\n",
"January 2017 - June 2017 (6 months)\n",
"United Kingdom\n",
"1. Wrote JavaScript and Java applications in MVC, MVVM architecture.\n",
"2. Collaborated with developers and performance engineers to enhance\n",
"supportability and identify performance bottlenecks.\n",
"3. Oversaw major new enhancements to existing software systems.\n",
"4. Built, tested and deployed scalable, highly available and modular software\n",
"products.\n",
"5. Debugged and modified software components.\n",
"TUI\n",
"Frontend Developer\n",
"August 2015 - November 2016 (1 year 4 months)\n",
"United Kingdom\n",
"TUI Travel PLC\n",
"UI Lead\n",
"May 2014 - August 2014 (4 months)\n",
"United Kingdom\n",
" Page 3 of 4 \n",
"Hdox India\n",
"Software Developer\n",
"March 2012 - October 2013 (1 year 8 months)\n",
"Coding javascript and java, Designing UI and SQL\n",
"Education\n",
"Mahaveer Institute of Science and Technology\n",
"Bachelor of Technology (BTech), Computer Science · (2004 - 2009)\n",
" Page 4 of 4\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 = \"Murali Nutalapati\"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n"
]
},
{
"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 Murali Nutalapati. You are answering questions on Murali Nutalapati's website, particularly questions related to Murali Nutalapati's career, background, skills and experience. Your responsibility is to represent Murali Nutalapati for interactions on the website as faithfully as possible. You are given a summary of Murali Nutalapati'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 Murali Nutalapati. 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\\ncandy519.murali@gmail.com\\nwww.linkedin.com/in/gomurali\\n(LinkedIn)\\nwww.youtube.com/\\n@awsclouddemos (Other)\\nTop Skills\\nFull-Stack Development\\nSolution Architecture\\nDevOps\\nLanguages\\nEnglish\\nCertifications\\nOracle Certified Associate, Java SE\\n8 Programmer\\nECMAScript 6\\nJava 8\\nAdobe Certified Expert\\nMurali Nutalapati\\nFull Stack Engineer specializing in AWS, Frontend, ReactJS,\\nNextJS, NodeJs, DevOps\\nUnited Kingdom\\nSummary\\nAs a Full Stack Engineer with a specialty in React.js and AWS,\\nmy current role involves building high-performance single-page\\napplications (SPAs) and embracing test-driven development (TDD)\\nfor robust outcomes. At NTT DATA UK, my tenure as a Principal\\nConsultant honed my competencies in project leadership and cross-\\nfunctional team facilitation.\\nThe development journey is marked by continuous learning and the\\nmentoring of junior developers, ensuring the adoption of industry-\\nstandard practices. Our team's success reflects in the refactoring of\\nlegacy codebases, improving system performance, and maintaining\\na collaborative learning environment that drives innovation and\\nmaintainability.\\nExperience\\nFreelance\\nFull Stack Engineer\\nSeptember 2024\\xa0-\\xa0Present\\xa0(10 months)\\nNTT DATA UK\\nPrincipal Consultant\\nOctober 2021\\xa0-\\xa0August 2024\\xa0(2 years 11 months)\\nLondon, England, United Kingdom\\nSky\\nContract Full Stack Developer\\nMarch 2023\\xa0-\\xa0December 2023\\xa0(10 months)\\nLondon Area, United Kingdom\\n1. Worked with cross-functional development teams.\\n2. Built SPA web apps and Test-driven development.\\n3. Code Reviews and unit tests.\\n\\xa0 Page 1 of 4\\xa0 \\xa0\\n4. Mentored junior developers in adopting industry-standard practices while\\nfostering a collaborative \\nlearning environment within the team.\\n5. Refactored legacy codebases to improve maintainability, readability, and\\noverall system performance \\nover time.\\nBT\\nFull Stack Engineer\\nOctober 2021\\xa0-\\xa0April 2023\\xa0(1 year 7 months)\\nLondon, England, United Kingdom\\n1. Worked on ReactJS, Next.JS, Typescript, NodeJS, AWS.\\n2. Worked closely with product owners and Engineering manager.\\n3. Built oAuth2.0+ OIDC npm package which is used by 10+ teams in BT\\n4. Led architecture design decisions to ensure application scalability,\\nmodularity,\\nand maintainability in the long run.\\n5. Utilized Azure for deploying scalable infrastructure components in a cost-\\neffective\\nmanner.\\nVATGlobal\\nSenior Frontend Developer\\nNovember 2019\\xa0-\\xa0September 2021\\xa0(1 year 11 months)\\nUnited Kingdom\\n1. Worked closely with Product owner to establish and deliver requirements.\\n2. Developed code fixes and enhancements.\\n3. Developed reusable UI components using modern JavaScript frameworks\\nlike\\nReact, increasing productivity of the entire development team.\\n4. Collaborated with UX designers to create seamless user interfaces for web\\napplications.\\n5. Reduced page load time significantly with advanced optimization techniques\\nlike\\nlazy loading, minification, and caching strategies.\\nBP\\nContract Full-stack developer\\nApril 2019\\xa0-\\xa0October 2019\\xa0(7 months)\\nLondon, United Kingdom\\n\\xa0 Page 2 of 4\\xa0 \\xa0\\nSonata Software\\n5 years 3 months\\nSoftware Consultant\\nJuly 2017\\xa0-\\xa0December 2018\\xa0(1 year 6 months)\\nHyderabad Area, India\\n1. Developed code fixes and enhancements for inclusion in future code\\nreleases and patches.\\n2. Identified and suggested new technologies and tools for enhancing product\\nvalue and increasing team productivity.\\n3. Worked closely with clients to establish problem specifications and system\\ndesigns.\\n4. Collaborated with developers and performance engineers to enhance\\nsupportability and identify performance bottlenecks.\\n5. Maintained existing applications and designed and delivered new\\napplications.\\nSenior systems analyst\\nOctober 2013\\xa0-\\xa0June 2017\\xa0(3 years 9 months)\\nHyderabad Area, India\\nTravelopia\\nFrontend Developer\\nJanuary 2017\\xa0-\\xa0June 2017\\xa0(6 months)\\nUnited Kingdom\\n1. Wrote JavaScript and Java applications in MVC, MVVM architecture.\\n2. Collaborated with developers and performance engineers to enhance\\nsupportability and identify performance bottlenecks.\\n3. Oversaw major new enhancements to existing software systems.\\n4. Built, tested and deployed scalable, highly available and modular software\\nproducts.\\n5. Debugged and modified software components.\\nTUI\\nFrontend Developer\\nAugust 2015\\xa0-\\xa0November 2016\\xa0(1 year 4 months)\\nUnited Kingdom\\nTUI Travel PLC\\nUI Lead\\nMay 2014\\xa0-\\xa0August 2014\\xa0(4 months)\\nUnited Kingdom\\n\\xa0 Page 3 of 4\\xa0 \\xa0\\nHdox India\\nSoftware Developer\\nMarch 2012\\xa0-\\xa0October 2013\\xa0(1 year 8 months)\\nCoding javascript and java, Designing UI and SQL\\nEducation\\nMahaveer Institute of Science and Technology\\nBachelor of Technology (BTech),\\xa0Computer Science\\xa0·\\xa0(2004\\xa0-\\xa02009)\\n\\xa0 Page 4 of 4\\n\\nWith this context, please chat with the user, always staying in character as Murali Nutalapati.\""
]
},
"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": [
"<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": 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": 20,
"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": 21,
"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": 23,
"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 += f\"Please evaluate the response, replying with whether it is acceptable and your feedback.\"\n",
" return user_prompt"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"gemini = OpenAI(\n",
" api_key=os.getenv(\"OPENAI_API_KEY\"), \n",
" base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 36,
"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": [
"'I do not hold any patents. My focus has primarily been on software engineering, full-stack development, and data science. If you have any other questions regarding my skills or experience, feel free to ask!'"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"reply"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"ename": "BadRequestError",
"evalue": "Error code: 400 - [{'error': {'code': 400, 'message': 'API key not valid. Please pass a valid API key.', 'status': 'INVALID_ARGUMENT', 'details': [{'@type': 'type.googleapis.com/google.rpc.ErrorInfo', 'reason': 'API_KEY_INVALID', 'domain': 'googleapis.com', 'metadata': {'service': 'generativelanguage.googleapis.com'}}, {'@type': 'type.googleapis.com/google.rpc.LocalizedMessage', 'locale': 'en-US', 'message': 'API key not valid. Please pass a valid API key.'}]}}]",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mBadRequestError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[42]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[43mevaluate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mreply\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mdo you hold a patent?\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m[\u001b[49m\u001b[43m:\u001b[49m\u001b[32;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[36]\u001b[39m\u001b[32m, line 4\u001b[39m, in \u001b[36mevaluate\u001b[39m\u001b[34m(reply, message, history)\u001b[39m\n\u001b[32m 1\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mevaluate\u001b[39m(reply, message, history) -> Evaluation:\n\u001b[32m 3\u001b[39m messages = [{\u001b[33m\"\u001b[39m\u001b[33mrole\u001b[39m\u001b[33m\"\u001b[39m: \u001b[33m\"\u001b[39m\u001b[33msystem\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mcontent\u001b[39m\u001b[33m\"\u001b[39m: evaluator_system_prompt}] + [{\u001b[33m\"\u001b[39m\u001b[33mrole\u001b[39m\u001b[33m\"\u001b[39m: \u001b[33m\"\u001b[39m\u001b[33muser\u001b[39m\u001b[33m\"\u001b[39m, \u001b[33m\"\u001b[39m\u001b[33mcontent\u001b[39m\u001b[33m\"\u001b[39m: evaluator_user_prompt(reply, message, history)}]\n\u001b[32m----> \u001b[39m\u001b[32m4\u001b[39m response = \u001b[43mgemini\u001b[49m\u001b[43m.\u001b[49m\u001b[43mbeta\u001b[49m\u001b[43m.\u001b[49m\u001b[43mchat\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcompletions\u001b[49m\u001b[43m.\u001b[49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mgemini-2.0-flash\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m=\u001b[49m\u001b[43mEvaluation\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 5\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m response.choices[\u001b[32m0\u001b[39m].message.parsed\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/openai/resources/beta/chat/completions.py:158\u001b[39m, in \u001b[36mCompletions.parse\u001b[39m\u001b[34m(self, messages, model, audio, response_format, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, reasoning_effort, seed, service_tier, stop, store, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, web_search_options, extra_headers, extra_query, extra_body, timeout)\u001b[39m\n\u001b[32m 151\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mparser\u001b[39m(raw_completion: ChatCompletion) -> ParsedChatCompletion[ResponseFormatT]:\n\u001b[32m 152\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m _parse_chat_completion(\n\u001b[32m 153\u001b[39m response_format=response_format,\n\u001b[32m 154\u001b[39m chat_completion=raw_completion,\n\u001b[32m 155\u001b[39m input_tools=tools,\n\u001b[32m 156\u001b[39m )\n\u001b[32m--> \u001b[39m\u001b[32m158\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 159\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m/chat/completions\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m 160\u001b[39m \u001b[43m \u001b[49m\u001b[43mbody\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 161\u001b[39m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\n\u001b[32m 162\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmessages\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 163\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmodel\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 164\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43maudio\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43maudio\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 165\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfrequency_penalty\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 166\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfunction_call\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunction_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 167\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mfunctions\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 168\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mlogit_bias\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 169\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mlogprobs\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 170\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmax_completion_tokens\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_completion_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 171\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmax_tokens\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 172\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmetadata\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 173\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mmodalities\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodalities\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 174\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mn\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 175\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mparallel_tool_calls\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mparallel_tool_calls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 176\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mprediction\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mprediction\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 177\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mpresence_penalty\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 178\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mreasoning_effort\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mreasoning_effort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 179\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mresponse_format\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43m_type_to_response_format\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 180\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mseed\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 181\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mservice_tier\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mservice_tier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 182\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstop\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 183\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstore\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstore\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 184\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstream\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m 185\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mstream_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 186\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtemperature\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 187\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtool_choice\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtool_choice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 188\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtools\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 189\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtop_logprobs\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_logprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 190\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mtop_p\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 191\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43muser\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 192\u001b[39m \u001b[43m \u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mweb_search_options\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mweb_search_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 193\u001b[39m \u001b[43m \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 194\u001b[39m \u001b[43m \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[43m.\u001b[49m\u001b[43mCompletionCreateParams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 195\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 196\u001b[39m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 197\u001b[39m \u001b[43m \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 198\u001b[39m \u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 199\u001b[39m \u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[43m=\u001b[49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 200\u001b[39m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 201\u001b[39m \u001b[43m \u001b[49m\u001b[43mpost_parser\u001b[49m\u001b[43m=\u001b[49m\u001b[43mparser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 202\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 203\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# we turn the `ChatCompletion` instance into a `ParsedChatCompletion`\u001b[39;49;00m\n\u001b[32m 204\u001b[39m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# in the `parser` function above\u001b[39;49;00m\n\u001b[32m 205\u001b[39m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mType\u001b[49m\u001b[43m[\u001b[49m\u001b[43mParsedChatCompletion\u001b[49m\u001b[43m[\u001b[49m\u001b[43mResponseFormatT\u001b[49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mChatCompletion\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 206\u001b[39m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m 207\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/openai/_base_client.py:1242\u001b[39m, in \u001b[36mSyncAPIClient.post\u001b[39m\u001b[34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[39m\n\u001b[32m 1228\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mpost\u001b[39m(\n\u001b[32m 1229\u001b[39m \u001b[38;5;28mself\u001b[39m,\n\u001b[32m 1230\u001b[39m path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[32m (...)\u001b[39m\u001b[32m 1237\u001b[39m stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] | \u001b[38;5;28;01mNone\u001b[39;00m = \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[32m 1238\u001b[39m ) -> ResponseT | _StreamT:\n\u001b[32m 1239\u001b[39m opts = FinalRequestOptions.construct(\n\u001b[32m 1240\u001b[39m method=\u001b[33m\"\u001b[39m\u001b[33mpost\u001b[39m\u001b[33m\"\u001b[39m, url=path, json_data=body, files=to_httpx_files(files), **options\n\u001b[32m 1241\u001b[39m )\n\u001b[32m-> \u001b[39m\u001b[32m1242\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[43m=\u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
"\u001b[36mFile \u001b[39m\u001b[32m~/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/openai/_base_client.py:1037\u001b[39m, in \u001b[36mSyncAPIClient.request\u001b[39m\u001b[34m(self, cast_to, options, stream, stream_cls)\u001b[39m\n\u001b[32m 1034\u001b[39m err.response.read()\n\u001b[32m 1036\u001b[39m log.debug(\u001b[33m\"\u001b[39m\u001b[33mRe-raising status error\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m-> \u001b[39m\u001b[32m1037\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m._make_status_error_from_response(err.response) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m 1039\u001b[39m \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[32m 1041\u001b[39m \u001b[38;5;28;01massert\u001b[39;00m response \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[33m\"\u001b[39m\u001b[33mcould not resolve response (should never happen)\u001b[39m\u001b[33m\"\u001b[39m\n",
"\u001b[31mBadRequestError\u001b[39m: Error code: 400 - [{'error': {'code': 400, 'message': 'API key not valid. Please pass a valid API key.', 'status': 'INVALID_ARGUMENT', 'details': [{'@type': 'type.googleapis.com/google.rpc.ErrorInfo', 'reason': 'API_KEY_INVALID', 'domain': 'googleapis.com', 'metadata': {'service': 'generativelanguage.googleapis.com'}}, {'@type': 'type.googleapis.com/google.rpc.LocalizedMessage', 'locale': 'en-US', 'message': 'API key not valid. Please pass a valid API key.'}]}}]"
]
}
],
"source": [
"evaluate(reply, \"do you hold a patent?\", messages[:1])"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"def rerun(reply, message, history, feedback):\n",
" updated_system_prompt = system_prompt + f\"\\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": 34,
"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": 35,
"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": [
"<div><iframe src=\"http://127.0.0.1:7861/\" 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": 35,
"metadata": {},
"output_type": "execute_result"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Traceback (most recent call last):\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/gradio/queueing.py\", line 625, in process_events\n",
" response = await route_utils.call_process_api(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/gradio/route_utils.py\", line 322, in call_process_api\n",
" output = await app.get_blocks().process_api(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/gradio/blocks.py\", line 2220, in process_api\n",
" result = await self.call_function(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/gradio/blocks.py\", line 1729, in call_function\n",
" prediction = await fn(*processed_input)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/gradio/utils.py\", line 861, in async_wrapper\n",
" response = await f(*args, **kwargs)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/gradio/chat_interface.py\", line 545, in __wrapper\n",
" return await submit_fn(*args, **kwargs)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/gradio/chat_interface.py\", line 917, in _submit_fn\n",
" response = await anyio.to_thread.run_sync(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/anyio/to_thread.py\", line 56, in run_sync\n",
" return await get_async_backend().run_sync_in_worker_thread(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py\", line 2470, in run_sync_in_worker_thread\n",
" return await future\n",
" ^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py\", line 967, in run\n",
" result = context.run(func, *args)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/var/folders/vw/tg4phm257410tb7_072xyqx00000gn/T/ipykernel_39796/2688000405.py\", line 11, in chat\n",
" evaluation = evaluate(reply, message, history)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/var/folders/vw/tg4phm257410tb7_072xyqx00000gn/T/ipykernel_39796/4188536444.py\", line 4, in evaluate\n",
" response = gemini.beta.chat.completions.parse(model=\"gpt-4o-mini\", messages=messages, response_format=Evaluation)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/openai/resources/beta/chat/completions.py\", line 158, in parse\n",
" return self._post(\n",
" ^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/openai/_base_client.py\", line 1242, in post\n",
" return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/Users/gomurali/Documents/projects/llms/agents/.venv/lib/python3.12/site-packages/openai/_base_client.py\", line 1037, in request\n",
" raise self._make_status_error_from_response(err.response) from None\n",
"openai.BadRequestError: Error code: 400 - [{'error': {'code': 400, 'message': 'API key not valid. Please pass a valid API key.', 'status': 'INVALID_ARGUMENT', 'details': [{'@type': 'type.googleapis.com/google.rpc.ErrorInfo', 'reason': 'API_KEY_INVALID', 'domain': 'googleapis.com', 'metadata': {'service': 'generativelanguage.googleapis.com'}}, {'@type': 'type.googleapis.com/google.rpc.LocalizedMessage', 'locale': 'en-US', 'message': 'API key not valid. Please pass a valid API key.'}]}}]\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
}
|