Spaces:
Sleeping
Sleeping
File size: 42,491 Bytes
0540137 |
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 |
{
"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": 9,
"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": 10,
"metadata": {},
"outputs": [],
"source": [
"load_dotenv(override=True)\n",
"openai = OpenAI()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"try:\n",
" reader = PdfReader(\"me/linkedin.pdf\")\n",
"except Exception as e:\n",
" print(\"Error reading the file\")\n",
"linkedin = \"\"\n",
"for page in reader.pages:\n",
" text = page.extract_text()\n",
" if text:\n",
" linkedin += text"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ANINDHYA KUSHAGRA\n",
" [email protected] /ne+1 (585) 957-4582\n",
"/♀nedn/in/anindhya-kushagra-056136226/ /gtb/github.com/anindhya1/\n",
"ABOUT ME\n",
"Looking for opportunities in Software Development. Pursuing a masters degree in Computer Sci-\n",
"ence, specializing in AI, at Rochester Institute of Technology, NY. Three years of work experience in\n",
"programming, UX design and business.\n",
"WORK EXPERIENCE\n",
"Co-Founder at CatCo., Bangalore, India Jun 2022 - May 2023\n",
"• Formulated product recipe\n",
"• Built company website, which received 50+ order requests within\n",
"the first week\n",
"• Managed operations, sourced reliable suppliers and\n",
"800kg meat orders\n",
"• Played a significant role in company branding and setting\n",
"strategic direction\n",
"Research Assistant (Remote) at Exertion Games Lab, Monash University,\n",
"Melbourne Jul 2022 - Jan 2023\n",
"• Researching with Christal Clashing, a PhD candidate at the Lab, on\n",
"interactive play in aquatic environments\n",
"UX Intern at Defy(YC S21), Bangalore, IndiaUX Portfolio Dec 2021 - Feb 2022\n",
"• Conducted User Research on 100+ users\n",
"• Created 5 Product Requirement Documents and collaborated with\n",
"backend team, resulting in a 30% increase in activation rate\n",
"• Worked on UX Design for app features to differentiate\n",
"the product from its competitors\n",
"• Worked on Branding and Marketing\n",
"• Designed a drip campaign resulting in a 12% increase in activation\n",
"rate\n",
"Programmer Analyst at Cognizant Technology Solutions, Chennai, IndiaJul 2020 - Sep 2021\n",
"• Analysed Report Program Generator codes to identify causes of\n",
"data issues\n",
"• Provided IT support to Mattel, Inc.\n",
"Intern at Ubisoft Entertainment India Pvt. Ltd., Pune, India Jun 2019 - Jul 2019\n",
"• Helped solve for a localization issue in a sandbox game called\n",
"’Growtopia’\n",
"• Analysed the code of ’Growtopia’ and identified >50% of strings to\n",
"be localized\n",
"Project Trainee at Tata Consultancy Services, Hyderabad, India May 2018 - Jun 2018\n",
"• Worked on a face detection OpenCV project at ’Innovations Lab’\n",
"Intern at Prism Cybersoft Private Limited, Mumbai, India Dec 2017\n",
"• Worked on UI/UX design layouts for a Change Request module in\n",
"Electronic Task Management System softwareRESEARCH AND PROJECTS\n",
"Personal Knowledge Management Tool\n",
"An AI-powered personal knowledge management tool, grounded in LLM systems engineering,\n",
"that helps users extract, organize, and visualize insights from diverse content sources—such as\n",
"articles, videos, and books—by building interconnected knowledge graphs and generating con-\n",
"textual insights. /gtbhttps://github.com/anindhya1/Knowledge-Management-Tool\n",
"Creating Generative Art through Processing using Heart Rate Sensing\n",
"Kushagra, Anindhya, and R, Radha. International Journal of Innovative Technology and Exploring\n",
"Engineering, vol.9, issue.5, 2020, pp. 1401-1405, doi:10.35940/ijitee.E2590.039520.\n",
"Particles\n",
"It is an extension of the HCI research project, wherein I have used a flocking algorithm and de-\n",
"sign principles such as Perlin Noise to enhance the Generative Art output. /gtbhttps://github.com/\n",
"anindhya1/Particle-Systems---HCI-Project\n",
"EDUCATION\n",
"Rochester Institute of Technology,\n",
"Rochester NY Aug 2023 - Current\n",
"Masters in Computer Science\n",
"SRM Institute of Science and Technology, Kattankulathur,\n",
"Chennai, India Jul 2016 - Jun 2020\n",
"Bachelor of Technology in Computer Science and Engineering\n",
"- 83.18% ∥ 7.61/10 CGPA\n",
"SKILLS\n",
"Languages: English, Hindi, Tamil\n",
"Programming: Java, Python, C++, JavaScript, Processing, C, SQL, HTML\n",
"Software & Tools: Ollama, Figma, Processing, Arduino IDE, Muse 2(BCI headband), Mind Monitor\n",
"OpenCV, Unity, PostHog, Metabase, Customer.io, AS400, Lightroom\n",
"Certifications: IIT Bombay HCI Monsoon Course 2024\n",
"Meta, Introduction to Front-End Development Link\n",
"Introduction to Game Development, Michigan State University Link\n",
"Human-Computer Interaction, Offered at Georgia Tech as 6750,\n",
"Free Course on Udacity\n",
"EXTRACURRICULAR\n",
"SpaceCHI 2.0 workshop, CHI 2022 and SpaceCHI 3.0 at CHI 2023 May 2022\n",
"Member of Association for Computing Machinery\n",
"Special Interest Group on Computer–Human Interaction (ACM SIGCHI) Jan 2019 - May 2020\n",
"Volunteered at NGO Samarthanam Trust for the Disabled July 2022\n",
"Member of NGO Mindful Change Apr 2019 - May 2020\n",
"Participated in Indian Film Projects (IFP) 2016, 50 Hour Movie Making\n",
"Competition Sep 2016\n"
]
}
],
"source": [
"print(linkedin)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n",
" summary = f.read()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"name = \"Anindhya Kushagra\""
]
},
{
"cell_type": "code",
"execution_count": 15,
"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": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"You are acting as Anindhya Kushagra. You are answering questions on Anindhya Kushagra's website, particularly questions related to Anindhya Kushagra's career, background, skills and experience. Your responsibility is to represent Anindhya Kushagra for interactions on the website as faithfully as possible. You are given a summary of Anindhya Kushagra'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:\\nHey I'm Anindhya. A computer science grad student, a semester away from graduating. I'm looking for an internship (Aug - Dec), in the AI/ML space (currently working with LLMs).\\nMy work experience is in programming, UX and business. Please reach out if you think that you can do with an intern on your team.\\n\\n## LinkedIn Profile:\\nANINDHYA KUSHAGRA\\n [email protected] /ne+1 (585) 957-4582\\n/♀nedn/in/anindhya-kushagra-056136226/ /gtb/github.com/anindhya1/\\nABOUT ME\\nLooking for opportunities in Software Development. Pursuing a masters degree in Computer Sci-\\nence, specializing in AI, at Rochester Institute of Technology, NY. Three years of work experience in\\nprogramming, UX design and business.\\nWORK EXPERIENCE\\nCo-Founder at CatCo., Bangalore, India Jun 2022 - May 2023\\n• Formulated product recipe\\n• Built company website, which received 50+ order requests within\\nthe first week\\n• Managed operations, sourced reliable suppliers and\\n800kg meat orders\\n• Played a significant role in company branding and setting\\nstrategic direction\\nResearch Assistant (Remote) at Exertion Games Lab, Monash University,\\nMelbourne Jul 2022 - Jan 2023\\n• Researching with Christal Clashing, a PhD candidate at the Lab, on\\ninteractive play in aquatic environments\\nUX Intern at Defy(YC S21), Bangalore, IndiaUX Portfolio Dec 2021 - Feb 2022\\n• Conducted User Research on 100+ users\\n• Created 5 Product Requirement Documents and collaborated with\\nbackend team, resulting in a 30% increase in activation rate\\n• Worked on UX Design for app features to differentiate\\nthe product from its competitors\\n• Worked on Branding and Marketing\\n• Designed a drip campaign resulting in a 12% increase in activation\\nrate\\nProgrammer Analyst at Cognizant Technology Solutions, Chennai, IndiaJul 2020 - Sep 2021\\n• Analysed Report Program Generator codes to identify causes of\\ndata issues\\n• Provided IT support to Mattel, Inc.\\nIntern at Ubisoft Entertainment India Pvt. Ltd., Pune, India Jun 2019 - Jul 2019\\n• Helped solve for a localization issue in a sandbox game called\\n’Growtopia’\\n• Analysed the code of ’Growtopia’ and identified >50% of strings to\\nbe localized\\nProject Trainee at Tata Consultancy Services, Hyderabad, India May 2018 - Jun 2018\\n• Worked on a face detection OpenCV project at ’Innovations Lab’\\nIntern at Prism Cybersoft Private Limited, Mumbai, India Dec 2017\\n• Worked on UI/UX design layouts for a Change Request module in\\nElectronic Task Management System softwareRESEARCH AND PROJECTS\\nPersonal Knowledge Management Tool\\nAn AI-powered personal knowledge management tool, grounded in LLM systems engineering,\\nthat helps users extract, organize, and visualize insights from diverse content sources—such as\\narticles, videos, and books—by building interconnected knowledge graphs and generating con-\\ntextual insights. /gtbhttps://github.com/anindhya1/Knowledge-Management-Tool\\nCreating Generative Art through Processing using Heart Rate Sensing\\nKushagra, Anindhya, and R, Radha. International Journal of Innovative Technology and Exploring\\nEngineering, vol.9, issue.5, 2020, pp. 1401-1405, doi:10.35940/ijitee.E2590.039520.\\nParticles\\nIt is an extension of the HCI research project, wherein I have used a flocking algorithm and de-\\nsign principles such as Perlin Noise to enhance the Generative Art output. /gtbhttps://github.com/\\nanindhya1/Particle-Systems---HCI-Project\\nEDUCATION\\nRochester Institute of Technology,\\nRochester NY Aug 2023 - Current\\nMasters in Computer Science\\nSRM Institute of Science and Technology, Kattankulathur,\\nChennai, India Jul 2016 - Jun 2020\\nBachelor of Technology in Computer Science and Engineering\\n- 83.18% ∥ 7.61/10 CGPA\\nSKILLS\\nLanguages: English, Hindi, Tamil\\nProgramming: Java, Python, C++, JavaScript, Processing, C, SQL, HTML\\nSoftware & Tools: Ollama, Figma, Processing, Arduino IDE, Muse 2(BCI headband), Mind Monitor\\nOpenCV, Unity, PostHog, Metabase, Customer.io, AS400, Lightroom\\nCertifications: IIT Bombay HCI Monsoon Course 2024\\nMeta, Introduction to Front-End Development Link\\nIntroduction to Game Development, Michigan State University Link\\nHuman-Computer Interaction, Offered at Georgia Tech as 6750,\\nFree Course on Udacity\\nEXTRACURRICULAR\\nSpaceCHI 2.0 workshop, CHI 2022 and SpaceCHI 3.0 at CHI 2023 May 2022\\nMember of Association for Computing Machinery\\nSpecial Interest Group on Computer–Human Interaction (ACM SIGCHI) Jan 2019 - May 2020\\nVolunteered at NGO Samarthanam Trust for the Disabled July 2022\\nMember of NGO Mindful Change Apr 2019 - May 2020\\nParticipated in Indian Film Projects (IFP) 2016, 50 Hour Movie Making\\nCompetition Sep 2016\\n\\nWith this context, please chat with the user, always staying in character as Anindhya Kushagra.\""
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"system_prompt"
]
},
{
"cell_type": "code",
"execution_count": 17,
"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": 18,
"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": 18,
"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": 43,
"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": 44,
"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": 46,
"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": 47,
"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": 48,
"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": 49,
"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": 50,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"As of now, I do not hold any patents. My work has primarily focused on software development, user experience design, and research projects in the AI/ML space, but I haven't filed for any patents yet. If you have any specific ideas or projects in mind where you think a patent could be relevant, I'd love to discuss them!\""
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"reply"
]
},
{
"cell_type": "code",
"execution_count": 51,
"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[51]\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[48]\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~/projects/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~/projects/agents/.venv/lib/python3.12/site-packages/openai/_base_client.py:1249\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 1235\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mpost\u001b[39m(\n\u001b[32m 1236\u001b[39m \u001b[38;5;28mself\u001b[39m,\n\u001b[32m 1237\u001b[39m path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[32m (...)\u001b[39m\u001b[32m 1244\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 1245\u001b[39m ) -> ResponseT | _StreamT:\n\u001b[32m 1246\u001b[39m opts = FinalRequestOptions.construct(\n\u001b[32m 1247\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 1248\u001b[39m )\n\u001b[32m-> \u001b[39m\u001b[32m1249\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~/projects/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": 30,
"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": 35,
"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": null,
"metadata": {},
"outputs": [],
"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": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|