File size: 27,689 Bytes
7612318 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"import streamlit as st\n",
"import os\n",
"import pandas as pd\n",
"import random\n",
"from os.path import join\n",
"from datetime import datetime\n",
"# from src import decorate_with_code, show_response, get_from_user\n",
"from dotenv import load_dotenv\n",
"from langchain_groq.chat_models import ChatGroq\n",
"from langchain_mistralai import ChatMistralAI\n",
"from langchain_google_genai import GoogleGenerativeAI,GoogleGenerativeAIEmbeddings\n",
"from huggingface_hub import HfApi\n",
"load_dotenv()\n",
"\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>prompt</th>\n",
" <th>Desired Answer</th>\n",
" <th>Category</th>\n",
" <th>llama3_answer_1721726247</th>\n",
" <th>llama3_score_1721726247</th>\n",
" <th>mixtral_answer_1721726407</th>\n",
" <th>mixtral_score_1721726407</th>\n",
" <th>gemma_answer_1721726499</th>\n",
" <th>gemma_score_1721726499</th>\n",
" <th>Codestral Mamba_answer_1721759526</th>\n",
" <th>Codestral Mamba_score_1721759526</th>\n",
" <th>Codestral_answer_1721759762</th>\n",
" <th>Codestral_score_1721759762</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Which month has the highest average PM2.5 in 2...</td>\n",
" <td>January</td>\n",
" <td>NaN</td>\n",
" <td>The month with the highest average PM2.5 in 20...</td>\n",
" <td>True</td>\n",
" <td>The month with the highest average PM2.5 in 20...</td>\n",
" <td>True</td>\n",
" <td>The highest average PM2.5 in 2023 for Mumbai w...</td>\n",
" <td>True</td>\n",
" <td>content='To find the month with the highest av...</td>\n",
" <td>True</td>\n",
" <td>The month with the highest average PM2.5 in 20...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Which month generally has the highest pollution?</td>\n",
" <td>November</td>\n",
" <td>NaN</td>\n",
" <td>The month with the highest pollution is 11 wit...</td>\n",
" <td>True</td>\n",
" <td>The month with the highest pollution (on avera...</td>\n",
" <td>True</td>\n",
" <td>The month with the highest average PM2.5 is No...</td>\n",
" <td>True</td>\n",
" <td>content='To find out which month generally has...</td>\n",
" <td>False</td>\n",
" <td>The month with the highest pollution is Novemb...</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" prompt Desired Answer \\\n",
"0 Which month has the highest average PM2.5 in 2... January \n",
"1 Which month generally has the highest pollution? November \n",
"\n",
" Category llama3_answer_1721726247 \\\n",
"0 NaN The month with the highest average PM2.5 in 20... \n",
"1 NaN The month with the highest pollution is 11 wit... \n",
"\n",
" llama3_score_1721726247 mixtral_answer_1721726407 \\\n",
"0 True The month with the highest average PM2.5 in 20... \n",
"1 True The month with the highest pollution (on avera... \n",
"\n",
" mixtral_score_1721726407 gemma_answer_1721726499 \\\n",
"0 True The highest average PM2.5 in 2023 for Mumbai w... \n",
"1 True The month with the highest average PM2.5 is No... \n",
"\n",
" gemma_score_1721726499 Codestral Mamba_answer_1721759526 \\\n",
"0 True content='To find the month with the highest av... \n",
"1 True content='To find out which month generally has... \n",
"\n",
" Codestral Mamba_score_1721759526 \\\n",
"0 True \n",
"1 False \n",
"\n",
" Codestral_answer_1721759762 \\\n",
"0 The month with the highest average PM2.5 in 20... \n",
"1 The month with the highest pollution is Novemb... \n",
"\n",
" Codestral_score_1721759762 \n",
"0 True \n",
"1 True "
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prompts = pd.read_csv(\"prompts.csv\")\n",
"prompts.head(2)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Date datetime64[ns]\n",
"City object\n",
"AQI float64\n",
"Pollutant object\n",
"Air Quality object\n",
"Based on number of monitoring stations float64\n",
"State object\n",
"Date_City object\n",
"dtype: object\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Date</th>\n",
" <th>City</th>\n",
" <th>AQI</th>\n",
" <th>Pollutant</th>\n",
" <th>Air Quality</th>\n",
" <th>Based on number of monitoring stations</th>\n",
" <th>State</th>\n",
" <th>Date_City</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2016-01-01</td>\n",
" <td>Agartala</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" <td>NaN</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2016-01-01</td>\n",
" <td>Agra</td>\n",
" <td>417.0</td>\n",
" <td>PM\\n2.5</td>\n",
" <td>Severe</td>\n",
" <td>1.0</td>\n",
" <td>Uttar Pradesh</td>\n",
" <td>2016-01-01_Agra</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Date City AQI Pollutant Air Quality \\\n",
"0 2016-01-01 Agartala NaN None None \n",
"1 2016-01-01 Agra 417.0 PM\\n2.5 Severe \n",
"\n",
" Based on number of monitoring stations State Date_City \n",
"0 NaN None None \n",
"1 1.0 Uttar Pradesh 2016-01-01_Agra "
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = pd.read_parquet(\"AQI_data.parquet\")\n",
"print(data.dtypes)\n",
"data.head(2)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"def get_full_prompt(question):\n",
" return f\"\"\"You are a data scientist who is good with tools such as pandas, numpy and matplotlib. You are also an expert in air quality. You\n",
"can access daily AQI `data` and you have to complete a code provided by me based on my question. `data` is a pandas DataFrame and has the following columns and data types:\n",
"\n",
"Date: date, Date of the `AQI` data\n",
"City: string, Name of the city where the `AQI` was recorded\n",
"State: string, Name of the state where `City` is located\n",
"AQI: float, AQI value\n",
"Air Quality: string, Air quality category from [\"Satisfactory\", \"Moderate\", \"Good\", \"Poor\", \"Very Poor\", \"Severe\"] based on `AQI` value\n",
"\n",
"Now, my question is: \"{question}\"\n",
"\n",
"Complete the code below to answer my question:\n",
"\n",
"```python\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"data = pd.read_parquet(\"AQI_data.parquet\")\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"You are a data scientist who is good with tools such as pandas, numpy and matplotlib. You are also an expert in air quality. You\n",
"can access daily AQI `data` and you have to complete a code provided by me based on my question. `data` is a pandas DataFrame and has the following columns and data types:\n",
"\n",
"Date: date, Date of the `AQI` data\n",
"City: string, Name of the city where the `AQI` was recorded\n",
"State: string, Name of the state where `City` is located\n",
"AQI: float, AQI value\n",
"Air Quality: string, Air quality category from [\"Satisfactory\", \"Moderate\", \"Good\", \"Poor\", \"Very Poor\", \"Severe\"] based on `AQI` value\n",
"\n",
"Now, my question is: \"Which month has the highest average PM2.5 in 2023 for Mumbai?\"\n",
"\n",
"Complete the code below to answer my question:\n",
"\n",
"```python\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"data = pd.read_parquet(\"AQI_data.parquet\")\n"
]
}
],
"source": [
"print(get_full_prompt(prompts.prompt[0]))"
]
},
{
"cell_type": "code",
"execution_count": 74,
"metadata": {},
"outputs": [],
"source": [
"def get_gemini_response(prompt, model):\n",
" return GoogleGenerativeAI(model=model, google_api_key=os.environ.get(\"GOOGLE_API_KEY\"), temperature=0).invoke(prompt)\n",
"\n",
"def get_groq_response(prompt, model):\n",
" return ChatGroq(model=model, api_key=os.environ.get(\"GROQ_API_KEY\"), temperature=0).invoke(prompt).content\n",
"\n",
"llms = {\"gemini-pro\": lambda prompt: get_gemini_response(prompt, \"gemini-pro\"), \"groq_gemma-7b-it\": lambda prompt: get_groq_response(prompt, \"gemma-7b-it\"), \"groq_llama-3.2-90b-text-preview\": lambda prompt: get_groq_response(prompt, \"llama-3.2-90b-text-preview\")}"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('Which month generally has the highest pollution?', 'November')"
]
},
"execution_count": 75,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"i = 1\n",
"prompts.prompt[i], prompts['Desired Answer'][i]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"llm = \"groq_llama-3.2-90b-text-preview\"\n",
"full_prompt = get_full_prompt(\"Which city has the highest AQI value consistently over the years?\")\n",
"answer = llms[llm](full_prompt)"
]
},
{
"cell_type": "code",
"execution_count": 83,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"You are a data scientist who is good with tools such as pandas, numpy and matplotlib. You are also an expert in air quality. You\n",
"can access daily AQI `data` and you have to complete a code provided by me based on my question. `data` is a pandas DataFrame and has the following columns and data types:\n",
"\n",
"Date: date, Date of the `AQI` data\n",
"City: string, Name of the city where the `AQI` was recorded\n",
"State: string, Name of the state where `City` is located\n",
"AQI: float, AQI value\n",
"Air Quality: string, Air quality category from [\"Satisfactory\", \"Moderate\", \"Good\", \"Poor\", \"Very Poor\", \"Severe\"] based on `AQI` value\n",
"\n",
"Now, my question is: \"Which city has the highest AQI value consistently over the years?\"\n",
"\n",
"Complete the code below to answer my question:\n",
"\n",
"```python\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"data = pd.read_parquet(\"AQI_data.parquet\")\n",
"####################################################################################################\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# Load the data\n",
"data = pd.read_parquet(\"AQI_data.parquet\")\n",
"\n",
"# Convert 'Date' column to datetime and extract the year\n",
"data['Date'] = pd.to_datetime(data['Date'])\n",
"data['Year'] = data['Date'].dt.year\n",
"\n",
"# Group by 'City' and 'Year', and calculate the average AQI value\n",
"avg_aqi = data.groupby(['City', 'Year'])['AQI'].mean().reset_index()\n",
"\n",
"# Group by 'City' and calculate the average AQI value over the years\n",
"avg_aqi_over_years = avg_aqi.groupby('City')['AQI'].mean().reset_index()\n",
"\n",
"# Find the city with the highest average AQI value\n",
"city_with_highest_aqi = avg_aqi_over_years.loc[avg_aqi_over_years['AQI'].idxmax()]\n",
"\n",
"print(f\"The city with the highest AQI value consistently over the years is {city_with_highest_aqi['City']} with an average AQI value of {city_with_highest_aqi['AQI']:.2f}\")\n",
"\n",
"# Plot the top 10 cities with the highest average AQI values\n",
"top_10_cities = avg_aqi_over_years.nlargest(10, 'AQI')\n",
"plt.figure(figsize=(10, 6))\n",
"plt.bar(top_10_cities['City'], top_10_cities['AQI'])\n",
"plt.xlabel('City')\n",
"plt.ylabel('Average AQI Value')\n",
"plt.title('Top 10 Cities with the Highest Average AQI Values')\n",
"plt.xticks(rotation=90)\n",
"plt.tight_layout()\n",
"plt.show()\n",
"\n",
"####################################################################################################\n",
"The city with the highest AQI value consistently over the years is Jharsuguda with an average AQI value of 282.00\n"
]
}
],
"source": [
"import re\n",
"code = re.search(r\"```python\\n(.*)```\", answer, re.DOTALL).group(1)\n",
"print(full_prompt)\n",
"print(\"#\" * 100)\n",
"print(code)\n",
"print(\"#\" * 100)\n",
"exec(code)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# import streamlit as st\n",
"# import os\n",
"# import pandas as pd\n",
"# import random\n",
"# from os.path import join\n",
"# from datetime import datetime\n",
"# from src import decorate_with_code, show_response, get_from_user\n",
"# from dotenv import load_dotenv\n",
"# from langchain_groq.chat_models import ChatGroq\n",
"# from langchain_mistralai import ChatMistralAI\n",
"# from huggingface_hub import HfApi\n",
"# st.set_page_config(layout=\"wide\")\n",
"\n",
"# ### Extract data.zip\n",
"# if not os.path.exists(\"data/1\"):\n",
"# os.system(\"unzip data.zip\")\n",
"\n",
"# # Load environment variables : Groq and Hugging Face API keys\n",
"# load_dotenv()\n",
"# Groq_Token = os.environ[\"GROQ_API_KEY\"]\n",
"# CODESTRAL_API_KEY = os.environ[\"CODESTRAL_API_KEY\"]\n",
"# hf_token = os.environ[\"HF_TOKEN\"]\n",
"# models = {\"llama3\":\"llama3-70b-8192\",\"mixtral\": \"mixtral-8x7b-32768\", \"llama2\": \"llama2-70b-4096\", \"gemma\": \"gemma-7b-it\"}\n",
"# groq_models = {\"llama3-70b\": \"llama3-70b-8192\", \"mixtral\": \"mixtral-8x7b-32768\", \"gemma-7b\": \"gemma-7b-it\",\"llama3.1-70b\":\"llama-3.1-70b-versatile\",\"llama3-8b\":\"llama3-8b-8192\",\"llama3.1-8b\":\"llama-3.1-8b-instant\",\"gemma-9b\":\"gemma2-9b-it\"}\n",
"# mistral_models = {\"Codestral Mamba\" : \"open-codestral-mamba\", \"Codestral\" : \"codestral-latest\",\"Mistral 7B\":\"open-mistral-7b\"}\n",
"# groq_model_list = list(groq_models.keys())\n",
"# mistral_model_list = list(mistral_models.keys())\n",
"\n",
"# self_path = os.path.dirname(os.path.abspath(__file__))\n",
"\n",
"\n",
"# def generate_template(prompt):\n",
"# df_check = pd.read_csv(\"Data.csv\")\n",
"# df_check[\"Timestamp\"] = pd.to_datetime(df_check[\"Timestamp\"])\n",
"# df_check = df_check.head(5)\n",
"\n",
"# new_line = \"\\n\"\n",
"\n",
"# template = f\"\"\"```python\n",
"# import pandas as pd\n",
"# import matplotlib.pyplot as plt\n",
"\n",
"# df = pd.read_csv(\"Data.csv\")\n",
"# df[\"Timestamp\"] = pd.to_datetime(df[\"Timestamp\"])\n",
"\n",
"# # df.dtypes\n",
"# {new_line.join(map(lambda x: '# '+x, str(df_check.dtypes).split(new_line)))}\n",
"\n",
"# # {prompt.strip()}\n",
"# # <your code here>\n",
"\n",
"# #answer = \n",
"# ```\n",
"# \"\"\"\n",
"# return template\n",
"\n",
"\n",
"# def generate_query(template):\n",
" \n",
"# query = f\"\"\"I have a pandas dataframe data of PM2.5.\n",
"# * The columns are 'Timestamp', 'station', 'PM2.5', 'address', 'city', 'latitude', 'longitude', and 'state'.\n",
"# * Frequency of Data is Daily.\n",
"# * `Pollution` generally means `PM2.5`.\n",
"# * PM2.5 guidelines: India: 60, WHO: 15.\n",
"# * Store the final answer in a global variable `answer`.\n",
"# * Always report the unit of the data. Example: `The average PM2.5 is 45.67 µg/m³`\n",
"\n",
"# Complete the following code.\n",
"\n",
"# {template}\n",
"# \"\"\"\n",
"# return query\n",
"\n",
"\n",
"# def process_query(query, llm):\n",
"# global answer\n",
"# template = generate_template(query)\n",
"# query = generate_query(template)\n",
"# global code\n",
"# global error\n",
"# try:\n",
"# answer = llm.invoke(query)\n",
"# error = ''\n",
"# code = f\"\"\"\n",
"# {template.split(\"```python\")[1].split(\"```\")[0]}\n",
"# {answer.content.split(\"```python\")[1].split(\"```\")[0]}\n",
"# \"\"\"\n",
"# # update variable `answer` when code is executed\n",
"# exec(code,globals())\n",
"# except Exception as e:\n",
"# error = e\n",
"# code = ''\n",
"# answer = f\"Error: {e}\"\n",
"# print(answer)\n",
"\n",
"\n",
"# # Using HTML and CSS to center the title\n",
"# st.write(\n",
"# \"\"\"\n",
"# <style>\n",
"# .title {\n",
"# text-align: center;\n",
"# color: #17becf;\n",
"# }\n",
"# </style>\n",
"# \"\"\",\n",
"# unsafe_allow_html=True,\n",
"# )\n",
"\n",
"\n",
"\n",
"\n",
"# # Display images and text in three columns with specified ratios\n",
"# col1, col2, col3 = st.sidebar.columns((1.0, 2, 1.0)) \n",
"# with col2:\n",
"# st.markdown(\"<h1 class='title'>Airchat</h1>\", unsafe_allow_html=True)\n",
" \n",
" \n",
"# model_name = st.sidebar.selectbox(\"Select LLM:\", groq_model_list + mistral_model_list)\n",
"\n",
"# questions = ['Custom Prompt']\n",
"# with open(join(self_path, \"questions.txt\")) as f:\n",
"# questions += f.read().split(\"\\n\")\n",
"\n",
"# waiting_lines = (\"Thinking...\", \"Just a moment...\", \"Let me think...\", \"Working on it...\", \"Processing...\", \"Hold on...\", \"One moment...\", \"On it...\")\n",
"\n",
"\n",
"\n",
"# # Initialize chat history\n",
"# if \"responses\" not in st.session_state:\n",
"# st.session_state.responses = []\n",
" \n",
"\n",
"# # Display chat responses from history on app rerun\n",
"# print(\"#\"*10)\n",
"# for response_id, response in enumerate(st.session_state.responses):\n",
"# status = show_response(st, response)\n",
"# if response[\"role\"] == \"assistant\":\n",
"# # feedback_key = f\"feedback_{int(response_id/2)}\"\n",
"# print(\"response_id\", response_id)\n",
" \n",
"# error = response[\"error\"]\n",
"# output = response[\"content\"]\n",
"# last_prompt = response[\"last_prompt\"]\n",
"# code = response[\"gen_code\"]\n",
"# evaluation = response[\"evaluation\"]\n",
" \n",
" \n",
" \n",
"# print(\"#\"*10)\n",
"\n",
"# show = True\n",
"# prompt = st.sidebar.selectbox(\"Select a Prompt:\", questions, key=\"prompt_key\")\n",
"# if prompt == 'Custom Prompt':\n",
"# show = False\n",
"# # React to user input\n",
"# prompt = st.chat_input(\"Ask me anything about air quality!\", key=1000)\n",
"# if prompt :\n",
"# show = True\n",
"# else:\n",
"# # placeholder for chat input\n",
"# st.chat_input(\"Select 'Select a Prompt' -> 'Custom Prompt' in the sidebar to ask your own questions.\", key=1000, disabled=True)\n",
"\n",
"# if \"last_prompt\" in st.session_state:\n",
"# last_prompt = st.session_state[\"last_prompt\"]\n",
"# last_model_name = st.session_state[\"last_model_name\"]\n",
"# if (prompt == last_prompt) and (model_name == last_model_name):\n",
"# show = False\n",
"\n",
"# if prompt:\n",
"# st.sidebar.info(\"Select 'Custom Prompt' to ask your own questions.\")\n",
"\n",
"# if show:\n",
"# # Add user input to chat history\n",
"# user_response = get_from_user(prompt)\n",
"# st.session_state.responses.append(user_response)\n",
"\n",
"# # select random waiting line\n",
"# with st.spinner(random.choice(waiting_lines)):\n",
"# ran = False\n",
"# for i in range(1):\n",
"# print(f\"Attempt {i+1}\")\n",
"# if model_name in groq_models:\n",
"# model_folder = \"Groq_\" + groq_models[model_name]\n",
"# llm = ChatGroq(model=groq_models[model_name], api_key=Groq_Token, temperature=0)\n",
"# else:\n",
"# model_folder = \"MistralAI_\" + mistral_models[model_name]\n",
"# llm = ChatMistralAI(model=mistral_models[model_name], api_key=CODESTRAL_API_KEY, temperature=0)\n",
"# print(llm)\n",
"# # llm = ChatGroq(model=models[model_name], api_key=os.getenv(\"GROQ_API\"), temperature=0)\n",
"\n",
"# df_check = pd.read_csv(\"Data.csv\")\n",
"# df_check[\"Timestamp\"] = pd.to_datetime(df_check[\"Timestamp\"])\n",
"# df_check = df_check.head(5)\n",
"\n",
"# new_line = \"\\n\"\n",
"\n",
"# parameters = {\"font.size\": 12,\"figure.dpi\": 600}\n",
"\n",
"# process_query(prompt, llm)\n",
" \n",
" \n",
"# # Read the questions from Questions.txt and find the index of the question if there is a match\n",
"# with open(join(\"questions.txt\")) as f:\n",
"# questions = f.read().split(\"\\n\")\n",
"# try:\n",
"# index = questions.index(prompt)\n",
"# index = index + 1\n",
"# except:\n",
"# index = None \n",
"# print(\"Index\",index)\n",
"# if type(index) == int:\n",
"# # Open folder data/index/llm_name and compare with evaluation.txt\n",
"# with open(join(\"data\", str(index), model_folder, \"evaluation.txt\")) as f:\n",
"# evaluation = f.read().strip()\n",
"# with open(join(\"data\", str(index), \"ground_truth\", \"answer.txt\")) as f:\n",
"# ground_truth = f.read().strip()\n",
"# else:\n",
"# evaluation = \"DK\"\n",
"# ground_truth = None \n",
"# response = {\"role\": \"assistant\", \"content\": answer, \"gen_code\": code, \"ex_code\": code, \"last_prompt\": prompt, \"error\": error,\"evaluation\": evaluation,\"ground_truth\": ground_truth}\n",
"\n",
"# if ran:\n",
"# break\n",
" \n",
"# # Append agent response to chat history\n",
"# st.session_state.responses.append(response)\n",
" \n",
"# st.session_state['last_prompt'] = prompt\n",
"# st.session_state['last_model_name'] = model_name\n",
"# st.rerun()\n",
" \n",
" \n",
"\n",
"# # Display contact details with message\n",
"# st.sidebar.markdown(\"<hr>\", unsafe_allow_html=True)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "zeel_py310",
"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": "3.10.15"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|