Spaces:
Sleeping
Sleeping
File size: 14,415 Bytes
c2f4c53 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 142,
"id": "ae2a25b9",
"metadata": {},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"from IPython.display import Markdown\n",
"from openai import OpenAI\n",
"from pypdf import PdfReader\n",
"import os\n",
"import gradio as gr\n"
]
},
{
"cell_type": "code",
"execution_count": 136,
"id": "2eb947db",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 136,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"load_dotenv(override=True)"
]
},
{
"cell_type": "code",
"execution_count": 137,
"id": "df80c9c8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Api key for openai is found and starts with: sk-proj-\n",
"APi key for groqai is found and starts with: gsk_Vopn\n"
]
}
],
"source": [
"openai = os.getenv(\"OPENAI_API_KEY\")\n",
"groqai = os.getenv(\"groq_api_key\")\n",
"\n",
"if openai:\n",
" print(f\"Api key for openai is found and starts with: {openai[:8]}\")\n",
"else:\n",
" print(\"key noy found.Check guide\")\n",
"if groqai:\n",
" print(f\"APi key for groqai is found and starts with: {groqai[:8]}\")\n",
"else:\n",
" print(\"groq api key not found\")"
]
},
{
"cell_type": "code",
"execution_count": 140,
"id": "15823b9e",
"metadata": {},
"outputs": [],
"source": [
"with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n",
" summary = f.read()"
]
},
{
"cell_type": "code",
"execution_count": 146,
"id": "cb071934",
"metadata": {},
"outputs": [],
"source": [
"reader = PdfReader(\"me/Profile.pdf\")\n",
"\n",
"linkedin= \"\"\n",
"for page in reader.pages:\n",
" text = page.extract_text()\n",
" if text:\n",
" linkedin += text\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4ec4be66",
"metadata": {},
"outputs": [],
"source": [
"name = \"Oluwatosin\""
]
},
{
"cell_type": "code",
"execution_count": 147,
"id": "77dbbe48",
"metadata": {},
"outputs": [],
"source": [
"system_prompt = f\"You are asking question about {name} website,\\\n",
"particularly questions related to {name} 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}.\""
]
},
{
"cell_type": "code",
"execution_count": 149,
"id": "0520c483",
"metadata": {},
"outputs": [],
"source": [
"import openai\n",
"\n",
"def chat(message, history):\n",
"\n",
" message = [{\"role\":\"system\",\"content\":system_prompt}] + history + [{\"role\":\"user\",\"content\":message}]\n",
"\n",
" response = openai.chat.completions.create(\n",
" model = \"gpt-4o-mini\",\n",
" messages = message\n",
" )\n",
" return response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": 152,
"id": "f259aa57",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"* Running on local URL: http://127.0.0.1:7873\n",
"* To create a public link, set `share=True` in `launch()`.\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7873/\" 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": 152,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gr.ChatInterface(chat, type=\"messages\").launch()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f1b9e902",
"metadata": {},
"outputs": [],
"source": [
"#Time to evaluate the model - Aim is to build a Multi-LLM pipeline\n",
"#We will use the groqapi to evaluate the openai model\n",
"\n",
"#First import a pydantc library and a basemodel class\n",
"\n",
"from pydantic import BaseModel\n",
"\n",
"class Evaluation(BaseModel):\n",
" is_acceptable: bool\n",
" feedback: str"
]
},
{
"cell_type": "code",
"execution_count": 154,
"id": "b58324ab",
"metadata": {},
"outputs": [],
"source": [
"#create an evaluator variable\n",
"\n",
"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": 155,
"id": "ae60c71f",
"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",
" return user_prompt"
]
},
{
"cell_type": "code",
"execution_count": 156,
"id": "5ce823c8",
"metadata": {},
"outputs": [],
"source": [
"#import and set enviroment for the groqai\n",
"\n",
"groqapi = OpenAI(api_key=groqai,\n",
" base_url=\"https://api.groq.com/openai/v1\"\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3d45762b",
"metadata": {},
"outputs": [],
"source": [
"def evaluate(reply, message, history) -> Evaluation:\n",
" messages = [{\"role\":\"system\",\"content\":evaluator_system_prompt}] + [{\"role\":\"user\",\"content\":evaluator_user_prompt(reply,message,history)}]\n",
" response = groqapi.chat.completions.create(\n",
" model=\"llama3-8b-8192\",\n",
" messages = messages,\n",
" #response_format=Evaluation\n",
" )\n",
"\n",
" raw_content = response.choices[0].message.content\n",
"\n",
" try:\n",
" # If response is a JSON string: {\"is_acceptable\": true, \"feedback\": \"...\"}\n",
" #using this deprectaed - evaluation = Evaluation.parse_raw(raw_content) - deprecated\n",
" evaluation = Evaluation.model_validate_json(raw_content)\n",
" except:\n",
" # Otherwise, fallback to plain text evaluation if it's not JSON\n",
" evaluation = Evaluation(\n",
" is_acceptable=\"acceptable\" in raw_content.lower(),\n",
" feedback=raw_content\n",
" )\n",
"\n",
" return evaluation\n",
"\n",
"\n",
" #return response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": 180,
"id": "1244b136",
"metadata": {},
"outputs": [],
"source": [
"messages = [{\"role\":\"system\", \"content\":\"system_prompt\"}] + [{\"role\":\"user\", \"content\":\"do you hold a patent\"}]\n",
"response = openai.chat.completions.create(\n",
" model = \"gpt-4o-mini\",\n",
" messages = messages\n",
")\n",
"\n",
"reply = response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": 181,
"id": "421c95ff",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Evaluation(is_acceptable=True, feedback='I evaluate the latest response from the agent as ACCEPTABLE.\\n\\nThe response is well-structured, concise, and directly addresses the user\\'s question. The agent acknowledges that they don\\'t hold a patent, which is an honest and clear answer. Additionally, the agent proactively offers to provide information on patents, application processes, or discuss patent law if the user has further questions, showing their willingness to engage and be helpful.\\n\\nFeedback:\\nThe response effectively addresses the user\\'s query, and the agent\\'s tone is professional and engaging. However, to further improve, the agent could consider adding a brief sentence or phrase to emphasize their expertise in the field of Data and AI, such as \"As a Data and AI Practitioner, I can provide insights on the patent process in my area of specialization.\" This would help to reinforce their credibility and expertise while maintaining the response\\'s overall length.')"
]
},
"execution_count": 181,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"evaluate(reply,\"do you hold a patent?\",messages[:1])"
]
},
{
"cell_type": "code",
"execution_count": 182,
"id": "2cf1d9c2",
"metadata": {},
"outputs": [],
"source": [
"def rerun(reply,message,history,feedback):\n",
"\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(\n",
" model = \"gpt-4o-mini\",\n",
" messages = messages\n",
" )\n",
" response.choices[0].message.content"
]
},
{
"cell_type": "code",
"execution_count": 191,
"id": "0f714a8a",
"metadata": {},
"outputs": [],
"source": [
"def chat(message, history):\n",
" if \"patent\" not in message:\n",
" system = system_prompt + \"\\n\\n Everything in the reply needs to be in pig latin.It is mandatory that you respond and only 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(\n",
" model=\"gpt-4o-mini\",\n",
" messages = messages\n",
" )\n",
"\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.reply)\n",
" reply = rerun(reply, message, history, evaluation.feedback)\n",
" return reply"
]
},
{
"cell_type": "code",
"execution_count": 192,
"id": "3bcbca87",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"* Running on local URL: http://127.0.0.1:7877\n",
"* To create a public link, set `share=True` in `launch()`.\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7877/\" 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": 192,
"metadata": {},
"output_type": "execute_result"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Passed evaluation - returning reply\n"
]
}
],
"source": [
"gr.ChatInterface(chat, type=\"messages\").launch()"
]
}
],
"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": 5
}
|