Spaces:
Sleeping
Sleeping
File size: 41,912 Bytes
e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c 8fa7be2 e31495c | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 | # import os
# import base64
# from groq import Groq
# import streamlit as st
# class IELTSTask2Evaluator:
# def __init__(self):
# self.client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
# self.model = "openai/gpt-oss-20b"
# def evaluate_essay(self, essay_question, essay_content):
# score_prompt = """ Provide the scores for the following IELTS task 2 essay in terms of Cohesion & Coherence, Task Achievement, Lexical Resouces and Grammatical Range & Accuracy critera. The scores should be in IELTS framework. Each criterion should be scored between 1 to 9 and should be integer. E.g. 5.5 is not acceptable! For each criteria that you score also provide 3 different comments using the following band descriptors and by referncing the essay.
# IELTS Scoring band descriptor:
# Task Achievement: Score 9: • fully addresses all parts of the task
# • presents a fully developed position in answer to the question with relevant, fully extended and well supported ideas
# 8: • sufficiently addresses all parts of the task
# • presents a well-developed response to the question with relevant, extended and supported ideas
# 7: • addresses all parts of the task
# • presents a clear position throughout the response
# • presents, extends and supports main ideas, but there may be a tendency to over-generalise and/or supporting ideas may lack focus
# 6: • addresses all parts of the task although some parts may be more fully covered than others
# • presents a relevant position although the conclusions may become unclear or repetitive
# • presents relevant main ideas but some may be inadequately developed/unclear
# 5: • addresses the task only partially; the format may be inappropriate in places
# • expresses a position but the development is not always clear and there may be no conclusions drawn
# • presents some main ideas but these are limited and not sufficiently developed; there may be irrelevant detail
# 4: • responds to the task only in a minimal way or the answer is tangential; the format may be inappropriate
# • presents a position but this is unclear
# • presents some main ideas but these are difficult to identify and may be repetitive, irrelevant or not well supported
# 3: • does not adequately address any part of the task
# • does not express a clear position
# • presents few ideas, which are largely undeveloped or irrelevant
# 2: • barely responds to the task
# • does not express a position
# • may attempt to present one or two ideas but there is no development
# 1: • answer is completely unrelated to the task
# Cohesion and Coherence: Score 9: • uses cohesion in such a way that it attracts no attention
# • skilfully manages paragraphing
# Score 8: • sequences information and ideas logically
# • manages all aspects of cohesion well
# • uses paragraphing sufficiently and appropriately
# Score 7: • logically organises information and ideas; there is clear progression throughout
# • uses a range of cohesive devices appropriately although there may be some under-/over-use
# • presents a clear central topic within each paragraph
# Score 6: • arranges information and ideas coherently and there is a clear overall progression
# • uses cohesive devices effectively, but cohesion within and/or between sentences may be faulty or mechanical
# • may not always use referencing clearly or appropriately
# • uses paragraphing, but not always logically
# Score 5: • presents information with some organisation but there may be a lack of overall progression
# • makes inadequate, inaccurate or over-use of cohesive devices
# • may be repetitive because of lack of referencing and substitution
# • may not write in paragraphs, or paragraphing may be inadequate
# Score 4: • presents information and ideas but these are not arranged coherently and there is no clear progression in the response
# • uses some basic cohesive devices but these may be inaccurate or repetitive
# • may not write in paragraphs or their use may be confusing
# Score 3: • does not organise ideas logically
# • may use a very limited range of cohesive devices, and those used may not indicate a logical relationship between ideas
# Score 2: • has very little control of organisational features
# Score 1: • fails to communicate any message
# Lexical Resouce: Score 9: • uses a wide range of vocabulary with very natural and sophisticated control of lexical features; rare minor errors occur only as 'slips'
# Score 8: • uses a wide range of vocabulary fluently and flexibly to convey precise meanings
# • skilfully uses uncommon lexical items but there may be occasional inaccuracies in word choice and collocation
# • produces rare errors in spelling and/or word formation
# Score 7: • uses a sufficient range of vocabulary to allow some flexibility and precision
# • uses less common lexical items with some awareness of style and collocation
# • may produce occasional errors in word choice, spelling and/or word formation
# Score 6: • uses an adequate range of vocabulary for the task
# • attempts to use less common vocabulary but with some inaccuracy
# • makes some errors in spelling and/or word formation, but they do not impede communication
# Score 5: • uses a limited range of vocabulary, but this is minimally adequate for the task
# • may make noticeable errors in spelling and/or word formation that may cause some difficulty for the reader
# Score 4: • uses only basic vocabulary which may be used repetitively or which may be inappropriate for the task
# • has limited control of word formation and/or spelling; errors may cause strain for the reader
# Score 3: • uses only a very limited range of words and expressions with very limited control of word formation and/or spelling
# • errors may severely distort the message
# Score 2: • uses an extremely limited range of vocabulary; essentially no control of word formation and/or spelling
# Score 1: • can only use a few isolated words
# Grammatical Range and Accuracy: Score 9: • uses a wide range of structures with full flexibility and accuracy; rare minor errors occur only as 'slips'
# Score 8: • uses a wide range of structures
# • the majority of sentences are error-free
# • makes only very occasional errors or inappropriacies
# Score 7: • uses a variety of complex structures
# • produces frequent error-free sentences
# • has good control of grammar and punctuation but may make a few errors
# Score 6: • uses a mix of simple and complex sentence forms
# • makes some errors in grammar and punctuation but they rarely reduce communication
# Score 5: • uses only a limited range of structures
# • attempts complex sentences but these tend to be less accurate than simple sentences
# • may make frequent grammatical errors and punctuation may be faulty; errors can cause some difficulty for the reader
# Score 4: • uses only a very limited range of structures with only rare use of subordinate clauses
# • some structures are accurate but errors predominate, and punctuation is often faulty
# Score 3: • attempts sentence forms but errors in grammar and punctuation predominate and distort the meaning
# Score 2: • cannot use sentence forms except in memorised phrases
# Score 1: • cannot use sentence forms at all
# Essay Question: {}
# Essay: {}
# """
# return self._get_completion(score_prompt.format(essay_question, essay_content))
# def analyze_grammar(self, essay_content):
# gram_prompt = """ Provide a grammatical analysis of the following essay with respect to the content a B1 leanrner must know. Provide all the grammars used and their accuracy pecentage. E.g. "Simple Present: 70%". Also provide comments for inaccurate structures. Don't give me any exercises.
# Essay: {}
# """
# return self._get_completion(gram_prompt.format(essay_content))
# def analyze_vocabulary(self, essay_content):
# vocab_prompt = """ Provide the lexical errors and provide their correct forms. For each of the vocabulary related to the context of the essay that you think could be improved, give suggesions. Provide full sentence examples for these suggestions.
# Essay: {}
# """
# return self._get_completion(vocab_prompt.format(essay_content))
# def analyze_cohesion_coherence(self, essay_content):
# coh_coh_prompt = """ Evaluate the cohesion and coherence of essay based on the following aspects. DO NOT SCORE THEM:
# - paraphrasing ability
# - logical sequencing of ideas
# - use and accuracy of cohesive devices
# - existence of a clear central topic in each paragrpah
# - correct paragraphing
# Essay: {}
# """
# return self._get_completion(coh_coh_prompt.format(essay_content))
# def analyze_task_achievement(self, essay_question, essay_content):
# task_ach_prompt = """ Evaluate the Task Achievement factor of this IELTS essay based on the following question and essay. Do NOT provide scores. Just mention analysis and how it could be imporved.
# Question: {}
# Essay: {}
# """
# return self._get_completion(task_ach_prompt.format(essay_question, essay_content))
# def _get_completion(self, prompt):
# response = self.client.chat.completions.create(
# messages=[{"role": "user", "content": prompt}],
# model=self.model
# )
# return response.choices[0].message.content
# class IELTSTask2ExerciseGenerator:
# def __init__(self):
# self.client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
# self.model = "llama3-8b-8192"
# def generate_grammar_exercises(self, grammar_analysis, essay_content):
# gram_exer_prompt = """ Based on the content of the grammar analysis provided in JSON format, make 4 different exercise types and provide 10 exercises for each. All the items should be in the context of the essay. Avoid providing exercises that are exact replica of the candidates' mistakes.
# Grammar Analysis: {}
# Essay: {}
# """
# return self._get_completion(gram_exer_prompt.format(grammar_analysis, essay_content))
# def generate_vocabulary_exercises(self, vocab_analysis):
# vocab_exer_prompt = """ Based on the lexical errors, provide exercises in the same context of the essay. Avoid providing exercises that are exact replica of the candidates' mistakes.
# Lexical Errors: {}
# """
# return self._get_completion(vocab_exer_prompt.format(vocab_analysis))
# def _get_completion(self, prompt):
# response = self.client.chat.completions.create(
# messages=[{"role": "user", "content": prompt}],
# model=self.model
# )
# return response.choices[0].message.content
# class IELTSTask1Evaluator:
# def __init__(self):
# self.client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
# self.text_model = "llama3-8b-8192"
# self.vision_model = "llama-3.2-11b-vision-preview"
# def encode_image(self, image_path):
# with open(image_path, "rb") as image_file:
# return base64.b64encode(image_file.read()).decode('utf-8')
# def analyze_graph(self, image_path, question):
# """Analyzes the graph/chart provided for Task 1 considering the question"""
# base64_image = self.encode_image(image_path)
# response = self.client.chat.completions.create(
# messages=[
# {
# "role": "user",
# "content": [
# {
# "type": "text",
# "text": f"""Given this IELTS Task 1 question: {question}
# Please analyze the graph/chart and:
# 1. List the key features that need to be described based on the question requirements
# 2. Identify the main trends, patterns, or comparisons required by the question
# 3. Note any significant data points that should be highlighted
# 4. Specify what should be included in the overview
# 5. Indicate what details should be included in the body paragraphs
# Provide your analysis in a structured format that can be used to evaluate student responses."""
# },
# {
# "type": "image_url",
# "image_url": {
# "url": f"data:image/jpeg;base64,{base64_image}",
# },
# },
# ],
# }
# ],
# model=self.vision_model,
# )
# return response.choices[0].message.content
# def evaluate_task1_response(self, question, graph_analysis, written_response):
# score_prompt = """Provide the scores for the following IELTS Task 1 essay based on the graph analysis provided and the written response. Score in terms of Task Achievement, Coherence and Cohesion, Lexical Resource, and Grammatical Range & Accuracy criteria. The scores should be in IELTS framework. Each criterion should be scored between 1 to 9 and should be integer. E.g. 5.5 is not acceptable! For each criteria that you score, provide 3 different comments using the band descriptors and by referencing both the key features of the graph and how well they were described in the response.
# IELTS Task 1 Band Descriptors:
# Band 9:
# • Fully satisfies all requirements of the task
# • Clearly presents a fully developed response
# • Uses cohesion in such a way that it attracts no attention
# • Skilfully manages paragraphing
# • Uses a wide range of vocabulary with very natural and sophisticated control of lexical features; rare minor errors occur only as 'slips'
# • Uses a wide range of structures with full flexibility and accuracy; rare minor errors occur only as 'slips'
# Band 8:
# • Covers all requirements of the task sufficiently
# • Presents, highlights and illustrates key features/bullet points clearly and appropriately
# • Sequences information and ideas logically
# • Manages all aspects of cohesion well
# • Uses paragraphing sufficiently and appropriately
# • Uses a wide range of vocabulary fluently and flexibly to convey precise meanings
# • Skilfully uses uncommon lexical items but there may be occasional inaccuracies in word choice and collocation
# • Produces rare errors in spelling and/or word formation
# • Uses a wide range of structures
# • The majority of sentences are error-free
# • Makes only very occasional errors or inappropriacies
# Band 7:
# • Covers the requirements of the task
# • Presents a clear overview of main trends, differences or stages
# • Clearly presents and highlights key features/bullet points but could be more fully extended
# • Logically organises information and ideas; there is clear progression throughout
# • Uses a range of cohesive devices appropriately although there may be some under-/over-use
# • Uses a sufficient range of vocabulary to allow some flexibility and precision
# • Uses less common lexical items with some awareness of style and collocation
# • May produce occasional errors in word choice, spelling and/or word formation
# • Uses a variety of complex structures
# • Produces frequent error-free sentences
# • Has good control of grammar and punctuation but may make a few errors
# Band 6:
# • Addresses the requirements of the task
# • Presents an overview with information appropriately selected
# • Presents and adequately highlights key features/bullet points but details may be irrelevant, inappropriate or inaccurate
# • Arranges information and ideas coherently and there is a clear overall progression
# • Uses cohesive devices effectively, but cohesion within and/or between sentences may be faulty or mechanical
# • May not always use referencing clearly or appropriately
# • Uses an adequate range of vocabulary for the task
# • Attempts to use less common vocabulary but with some inaccuracy
# • Makes some errors in spelling and/or word formation, but they do not impede communication
# • Uses a mix of simple and complex sentence forms
# • Makes some errors in grammar and punctuation but they rarely reduce communication
# Band 5:
# • Generally addresses the task; the format may be inappropriate in places
# • Recounts detail mechanically with no clear overview; there may be no data to support the description
# • Presents, but inadequately covers, key features/bullet points; there may be a tendency to focus on details
# • Presents information with some organisation but there may be a lack of overall progression
# • Makes inadequate, inaccurate or over-use of cohesive devices
# • May be repetitive because of lack of referencing and substitution
# • Uses a limited range of vocabulary, but this is minimally adequate for the task
# • May make noticeable errors in spelling and/or word formation that may cause some difficulty for the reader
# • Uses only a limited range of structures
# • Attempts complex sentences but these tend to be less accurate than simple sentences
# • May make frequent grammatical errors and punctuation may be faulty; errors can cause some difficulty for the reader
# Band 4:
# • Attempts to address the task but does not cover all key features/bullet points; the format may be inappropriate
# • May confuse key features/bullet points with detail; parts may be unclear, irrelevant, repetitive or inaccurate
# • Presents information and ideas but these are not arranged coherently and there is no clear progression
# • Uses some basic cohesive devices but these may be inaccurate or repetitive
# • Uses only basic vocabulary which may be used repetitively or which may be inappropriate for the task
# • Has limited control of word formation and/or spelling; errors may cause strain for the reader
# • Uses only a very limited range of structures with only rare use of subordinate clauses
# • Some structures are accurate but errors predominate, and punctuation is often faulty
# Band 3:
# • Fails to address the task, which may have been completely misunderstood
# • Presents limited ideas which may be largely irrelevant/repetitive
# • Does not organise ideas logically
# • May use a very limited range of cohesive devices, and those used may not indicate a logical relationship between ideas
# • Uses only a very limited range of words and expressions with very limited control of word formation and/or spelling
# • Errors may severely distort the message
# • Attempts sentence forms but errors in grammar and punctuation predominate and distort the meaning
# Band 2:
# • Answer is barely related to the task
# • Has very little control of organisational features
# • Uses an extremely limited range of vocabulary; essentially no control of word formation and/or spelling
# • Cannot use sentence forms except in memorised phrases
# Band 1:
# • Answer is completely unrelated to the task
# • Fails to communicate any message
# • Can only use a few isolated words
# • Cannot use sentence forms at all
# Band 0:
# • Does not attend
# • Does not attempt the task in any way
# • Writes a totally memorised response
# Question: {}
# Graph Analysis: {}
# Written Response: {}
# """
# return self._get_completion(score_prompt.format(question, graph_analysis, written_response))
# def analyze_grammar(self, written_response):
# gram_prompt = """Provide a grammatical analysis of the following Task 1 response with respect to describing trends, comparisons, and data. Provide all the grammars used and their accuracy percentage. E.g. "Past tense: 70%". Also provide comments for inaccurate structures. Focus especially on:
# - Tense usage for trends
# - Comparative structures
# - Passive voice
# - Articles with data
# - Prepositions with trends
# Response: {}
# """
# return self._get_completion(gram_prompt.format(written_response))
# def analyze_vocabulary(self, written_response):
# vocab_prompt = """Analyze the vocabulary used in this Task 1 response, focusing on:
# - Language for describing trends
# - Comparison vocabulary
# - Data reporting vocabulary
# - Graph/chart-specific terminology
# Provide suggestions for improvement with examples in similar contexts.
# Response: {}
# """
# return self._get_completion(vocab_prompt.format(written_response))
# def analyze_task_achievement(self, question, graph_analysis, written_response):
# task_ach_prompt = """Compare the key features identified in the graph analysis with how they were covered in the written response. Evaluate:
# - Overview presence and quality
# - Key feature selection
# - Data accuracy
# - Trend description completeness
# Do NOT provide scores, only analysis and suggestions for improvement.
# Question: {}
# Graph Analysis: {}
# Written Response: {}
# """
# return self._get_completion(task_ach_prompt.format(question, graph_analysis, written_response))
# def analyze_cohesion_coherence(self, written_response, graph_analysis):
# coh_coh_prompt = """Evaluate the cohesion and coherence of essay based on the following aspects. DO NOT SCORE THEM:
# - paraphrasing ability
# - logical sequencing of ideas
# - use and accuracy of cohesive devices
# - existence of a clear central topic in each paragraph
# - correct paragraphing
# Graph Analysis: {}
# Response: {}
# """
# return self._get_completion(coh_coh_prompt.format(graph_analysis, written_response))
# def _get_completion(self, prompt):
# response = self.client.chat.completions.create(
# messages=[{"role": "user", "content": prompt}],
# model=self.text_model
# )
# return response.choices[0].message.content
# class IELTSTask1ExerciseGenerator:
# def __init__(self):
# self.client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
# self.model = "llama3-8b-8192"
# def generate_grammar_exercises(self, grammar_analysis, essay_content):
# gram_exer_prompt = """ Based on the content of the grammar analysis provided in JSON format, make 4 different exercise types and provide 10 exercises for each. All the items should be in the context of the essay. Avoid providing exercises that are exact replica of the candidates' mistakes.
# Grammar Analysis: {}
# Essay: {}
# """
# return self._get_completion(gram_exer_prompt.format(grammar_analysis, essay_content))
# def generate_graph_description_exercises(self, graph_analysis):
# exercise_prompt = """Based on the graph analysis provided, create exercises to practice:
# 1. Writing overviews (1 exercise)
# 2. Describing trends (1 exercise)
# 3. Comparing data points (1 exercises)
# 4. Selecting key features (1 exercises)
# Keep all exercises relevant to the graph context.
# Graph Analysis: {}
# """
# return self._get_completion(exercise_prompt.format(graph_analysis))
# def generate_vocabulary_exercises(self, vocab_analysis):
# vocab_prompt = """Create targeted vocabulary exercises for Task 1 writing based on the vocabulary analysis. Include:
# 1. Trend description vocabulary
# 2. Comparison language
# 3. Data reporting phrases
# 4. Graph-specific terminology
# Analysis: {}
# """
# return self._get_completion(vocab_prompt.format(vocab_analysis))
# def _get_completion(self, prompt):
# response = self.client.chat.completions.create(
# messages=[{"role": "user", "content": prompt}],
# model=self.model
# )
# return response.choices[0].message.content
# def llm_responder_t1(image_path, question, written_response):
# task1_evaluator = IELTSTask1Evaluator()
# task1_generator = IELTSTask1ExerciseGenerator()
# graph_analysis = task1_evaluator.analyze_graph(image_path)
# general_analysis = task1_evaluator.evaluate_essay(question, graph_analysis, written_response)
# ga = task1_evaluator.analyze_grammar(written_response)
# lr = task1_evaluator.analyze_vocabulary(written_response)
# ta = task1_evaluator.analyze_task_achievement(question, graph_analysis, written_response)
# ga_exercise = task1_generator.generate_grammar_exercises(ga, written_response)
# lr_exercise = task1_generator.generate_vocabulary_exercises(lr)
# return ga, lr, cc, ta, ga_exercise, lr_exercise
# def llm_responder_t2(question, written_response):
# task2_evaluator = IELTSTask2Evaluator()
# task2_generator = IELTSTask2ExerciseGenerator()
# general_analysis = task2_evaluator.evaluate_essay(essay_question, essay_content)
# ga = task2_evaluator.analyze_grammar(written_response)
# lr = task2_evaluator.analyze_vocabulary(written_response)
# ta = task2_evaluator.analyze_task_achievement(essay_question, essay_content)
# ga_exercise = task2_generator.generate_grammar_exercises(ga, essay_content)
# lr_exercise = task2_generator.generate_vocabulary_exercises(lr)
# return ga, lr, cc, ta, ga_exercise, lr_exercise
import os
import base64
from groq import Groq
# -------------------------------
# GLOBAL MODEL SETTINGS
# -------------------------------
TEXT_MODEL = "llama-3.1-70b-versatile"
FAST_MODEL = "llama3-8b-8192"
VISION_MODEL = "llama-3.2-11b-vision-preview"
# ================================================================
# =============== TASK 2 EVALUATOR ===========================
# ================================================================
class IELTSTask2Evaluator:
def __init__(self):
self.client = Groq(api_key=os.getenv("GROQ_API_KEY"))
self.model = TEXT_MODEL
# -------------------------------
# SCORE ESSAY
# -------------------------------
def evaluate_essay(self, essay_question, essay_content):
prompt = f"""
You are an IELTS examiner. Evaluate this Task 2 essay.
Strict rules:
- Score each criterion (TA, CC, LR, GRA) from **1 to 9**, only integers.
- Provide **3 examiner-style comments per criterion**.
- Base the evaluation strictly on IELTS Writing Task 2 band descriptors.
Essay Question: {essay_question}
Essay:
{essay_content}
"""
return self._get_completion(prompt)
# -------------------------------
# GRAMMAR ANALYSIS
# -------------------------------
def analyze_grammar(self, essay_content):
prompt = f"""
Provide a full grammar analysis for a B1–C1 learner.
Include:
- Grammar structures used
- Accuracy % (e.g., “Present Simple: 70%”)
- Explanations for inaccurate structures
Essay:
{essay_content}
"""
return self._get_completion(prompt)
# -------------------------------
# VOCABULARY ANALYSIS
# -------------------------------
def analyze_vocabulary(self, essay_content):
prompt = f"""
Provide a vocabulary analysis of the essay:
Include:
- Lexical errors + corrections
- Stronger alternatives for weak vocabulary
- Full sentence examples
Essay:
{essay_content}
"""
return self._get_completion(prompt)
# -------------------------------
# COHESION & COHERENCE
# -------------------------------
def analyze_cohesion_coherence(self, essay_content):
prompt = f"""
Evaluate cohesion & coherence (NO SCORES):
Criteria:
- Paraphrasing quality
- Logical sequencing
- Cohesive devices use
- Topic clarity per paragraph
- Paragraph structure quality
Essay:
{essay_content}
"""
return self._get_completion(prompt)
# -------------------------------
# TASK ACHIEVEMENT
# -------------------------------
def analyze_task_achievement(self, essay_question, essay_content):
prompt = f"""
Analyze Task Achievement for this Task 2 essay (NO SCORES):
Explain:
- Whether all parts of the question are addressed
- Idea development
- Position clarity
- Suggestions for improvement
Question: {essay_question}
Essay: {essay_content}
"""
return self._get_completion(prompt)
# -------------------------------
# INTERNAL CALL
# -------------------------------
def _get_completion(self, prompt):
response = self.client.chat.completions.create(
model=self.model,
messages=[{"role": "user", "content": prompt}]
)
return response.choices[0].message["content"]
# ================================================================
# =============== TASK 2 EXERCISE GENERATOR ==================
# ================================================================
class IELTSTask2ExerciseGenerator:
def __init__(self):
self.client = Groq(api_key=os.getenv("GROQ_API_KEY"))
self.model = FAST_MODEL
def generate_grammar_exercises(self, grammar_analysis, essay_content):
prompt = f"""
Create grammar exercises based on this grammar analysis.
Rules:
- 4 exercise types
- 10 items each
- All exercises must use the essay’s topic
- Do NOT copy student mistakes
Grammar Analysis:
{grammar_analysis}
Essay:
{essay_content}
"""
return self._get_completion(prompt)
def generate_vocabulary_exercises(self, vocab_analysis):
prompt = f"""
Create vocabulary practice exercises based on these lexical issues.
Include:
- Reformulation
- Synonyms
- Contextual rewriting
Vocabulary Analysis:
{vocab_analysis}
"""
return self._get_completion(prompt)
def _get_completion(self, prompt):
response = self.client.chat.completions.create(
model=self.model,
messages=[{"role": "user", "content": prompt}],
)
return response.choices[0].message["content"]
# ================================================================
# =============== TASK 1 EVALUATOR ===========================
# ================================================================
class IELTSTask1Evaluator:
def __init__(self):
self.client = Groq(api_key=os.getenv("GROQ_API_KEY"))
self.text_model = TEXT_MODEL
self.vision_model = VISION_MODEL
def encode_image(self, path):
with open(path, "rb") as f:
return base64.b64encode(f.read()).decode()
# -------------------------------
# GRAPH ANALYSIS (VISION)
# -------------------------------
def analyze_graph(self, image_path, question):
base64_img = self.encode_image(image_path)
response = self.client.chat.completions.create(
model=self.vision_model,
messages=[
{
"role": "user",
"content": [
{"type": "text",
"text": f"Analyze this IELTS Task 1 graph. Question: {question}"},
{"type": "image_url",
"image_url": {"url": f"data:image/jpeg;base64,{base64_img}"}}
]
}
]
)
return response.choices[0].message["content"]
# -------------------------------
# TASK 1 FULL EVALUATION
# -------------------------------
def evaluate_task1_response(self, question, graph_analysis, written_response):
prompt = f"""
Evaluate this IELTS Task 1 response.
Provide:
- Integer band scores (1–9) for TA, CC, LR, GRA
- 3 comments per criterion
- Compare student writing to the graph analysis
Question: {question}
Graph Analysis:
{graph_analysis}
Response:
{written_response}
"""
return self._get_completion(prompt)
# -------------------------------
# OTHER ANALYSES (Grammar, Vocabulary, TA, CC)
# -------------------------------
def analyze_grammar(self, text):
prompt = f"""
Analyze grammar for Task 1 response:
Focus:
- Tenses for trends
- Comparative structures
- Passive forms
- Prepositions for charts
- Numeric language
Response:
{text}
"""
return self._get_completion(prompt)
def analyze_vocabulary(self, text):
prompt = f"""
Analyze vocabulary for Task 1:
Include:
- Trend vocabulary
- Comparison vocabulary
- Chart terminology
- Better synonyms
Response:
{text}
"""
return self._get_completion(prompt)
def analyze_task_achievement(self, question, graph_analysis, text):
prompt = f"""
Evaluate Task Achievement (NO SCORES):
Compare:
- Key features vs graph analysis
- Overview quality
- Trend accuracy
- Detail selection
Question: {question}
Graph:
{graph_analysis}
Response:
{text}
"""
return self._get_completion(prompt)
def analyze_cohesion_coherence(self, text, graph_analysis):
prompt = f"""
Evaluate Cohesion & Coherence (NO SCORES):
Graph Reference:
{graph_analysis}
Response:
{text}
"""
return self._get_completion(prompt)
def _get_completion(self, prompt):
resp = self.client.chat.completions.create(
model=self.text_model,
messages=[{"role": "user", "content": prompt}]
)
return resp.choices[0].message["content"]
# ================================================================
# =============== TASK 1 EXERCISE GENERATOR ==================
# ================================================================
class IELTSTask1ExerciseGenerator:
def __init__(self):
self.client = Groq(api_key=os.getenv("GROQ_API_KEY"))
self.model = FAST_MODEL
def generate_grammar_exercises(self, grammar_analysis, essay_content):
prompt = f"""
Generate Task 1 grammar exercises:
- 4 exercise types
- 10 items each
- Based on grammar analysis
- Context must match essay topic
Grammar Analysis:
{grammar_analysis}
Essay:
{essay_content}
"""
return self._get_completion(prompt)
def generate_graph_description_exercises(self, graph_analysis):
prompt = f"""
Create Task 1 exercises:
1. Write an overview
2. Describe a trend
3. Compare two data points
4. Select key features
Graph Analysis:
{graph_analysis}
"""
return self._get_completion(prompt)
def generate_vocabulary_exercises(self, vocab_analysis):
prompt = f"""
Create Task 1 vocabulary exercises:
Include:
- Trend verbs
- Comparison vocabulary
- Chart-specific words
Vocabulary Analysis:
{vocab_analysis}
"""
return self._get_completion(prompt)
def _get_completion(self, prompt):
resp = self.client.chat.completions.create(
model=self.model,
messages=[{"role": "user", "content": prompt}],
)
return resp.choices[0].message["content"]
# ================================================================
# =============== T1 & T2 RESPONDER ============================
# ================================================================
def llm_responder_t1(image_path, question, written_response):
ev = IELTSTask1Evaluator()
ex = IELTSTask1ExerciseGenerator()
graph = ev.analyze_graph(image_path, question)
evaluation = ev.evaluate_task1_response(question, graph, written_response)
grammar = ev.analyze_grammar(written_response)
vocab = ev.analyze_vocabulary(written_response)
cohesion = ev.analyze_cohesion_coherence(written_response, graph)
task_ach = ev.analyze_task_achievement(question, graph, written_response)
grammar_ex = ex.generate_grammar_exercises(grammar, written_response)
vocab_ex = ex.generate_vocabulary_exercises(vocab)
return evaluation, grammar, vocab, cohesion, task_ach, grammar_ex, vocab_ex
def llm_responder_t2(question, written_response):
ev = IELTSTask2Evaluator()
ex = IELTSTask2ExerciseGenerator()
evaluation = ev.evaluate_essay(question, written_response)
grammar = ev.analyze_grammar(written_response)
vocab = ev.analyze_vocabulary(written_response)
cohesion = ev.analyze_cohesion_coherence(written_response)
task_ach = ev.analyze_task_achievement(question, written_response)
grammar_ex = ex.generate_grammar_exercises(grammar, written_response)
vocab_ex = ex.generate_vocabulary_exercises(vocab)
return evaluation, grammar, vocab, cohesion, task_ach, grammar_ex, vocab_ex
|