File size: 32,540 Bytes
bb9389b 409acf6 82014e8 409acf6 0c259a6 bb9389b 409acf6 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "883e3354-1538-4f98-bf42-67552215bba3",
"metadata": {
"id": "883e3354-1538-4f98-bf42-67552215bba3"
},
"source": [
"# Setup"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b45bd52f-03e9-419f-8110-1013ff45fb1b",
"metadata": {
"tags": [],
"id": "b45bd52f-03e9-419f-8110-1013ff45fb1b"
},
"outputs": [],
"source": [
"from huggingface_hub import InferenceClient, login"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dc9f0411-8bf2-4a20-a6ea-331a2a486b8e",
"metadata": {
"tags": [],
"id": "dc9f0411-8bf2-4a20-a6ea-331a2a486b8e",
"outputId": "cb57d6e8-7d61-49ca-ec60-05594a7d5842",
"colab": {
"referenced_widgets": [
"515c96c357454fdc9a38ecc995ff1b3d"
]
}
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "515c96c357454fdc9a38ecc995ff1b3d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"login()"
]
},
{
"cell_type": "markdown",
"id": "4c254d6f-f3a1-49c1-815e-36e41e75ca25",
"metadata": {
"id": "4c254d6f-f3a1-49c1-815e-36e41e75ca25"
},
"source": [
"<div class=\"alert alert-danger\" role=\"alert\" style=\"display: flex; align-items: center;\">\n",
" <div style=\"text-align: center; padding-right: 10px;\">\n",
" <i class=\"fa fa-exclamation-triangle fa-2x\"></i>\n",
" </div>\n",
" <div style=\"display: flex; align-items: center; margin-top: 4px;\"> <!-- Added margin-top to lower the text -->\n",
" <strong>Warning: You will need to point to a model/deployment that is running.</strong>\n",
" </div>\n",
"</div>\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "84e6cb89-30d3-4ef5-8063-07783798e045",
"metadata": {
"id": "84e6cb89-30d3-4ef5-8063-07783798e045"
},
"outputs": [],
"source": [
"MODEL = \"CohereForAI/c4ai-command-r-plus\"\n",
"client = InferenceClient(MODEL)"
]
},
{
"cell_type": "markdown",
"id": "f5fe63f8-dea2-4c61-b6ce-29f173e4c4eb",
"metadata": {
"id": "f5fe63f8-dea2-4c61-b6ce-29f173e4c4eb"
},
"source": [
"# Translation\n",
"Our goal is to explore translation between English and Arabic and how prompt engineering can impact it. There has been [some work](https://arxiv.org/pdf/2308.01391), but we didn't find as much as we were hoping, especially for open source models.\n",
"\n",
"We have created a dataset across 6 domains and want to compare each method by having human rankers. We also have human translations to ground these rankings."
]
},
{
"cell_type": "markdown",
"id": "c5bee77b-da1c-43b3-ab14-d15e871f7502",
"metadata": {
"id": "c5bee77b-da1c-43b3-ab14-d15e871f7502"
},
"source": [
"## Baseline\n",
"\n",
"For our baseline we will translate with a simple system prompt and instruction."
]
},
{
"cell_type": "markdown",
"id": "a98b9b67-e68b-43b2-b8e9-0ed1cf85591f",
"metadata": {
"id": "a98b9b67-e68b-43b2-b8e9-0ed1cf85591f"
},
"source": [
"### System Prompt\n",
"This is a pretty basic system prompt. We give a role, and an assumed understanding. We also push for goals like \"highly motivated and detail-oriented\".\n",
"\n",
"> You are a skilled translator with extensive experience in English to Arabic translations. You possess a deep understanding of the linguistic, cultural, and contextual nuances essential for accurate and effective translation between these languages. Highly motivated and detail-oriented, you are committed to delivering translations that maintain the integrity and intent of the original text. Your role is crucial in ensuring clear and precise communication in our multilingual system."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "032c86d2-868e-4fa6-b03e-58f1c41434cc",
"metadata": {
"tags": [],
"id": "032c86d2-868e-4fa6-b03e-58f1c41434cc"
},
"outputs": [],
"source": [
"system_prompt = \"\"\"You are a skilled translator with extensive experience in English and Arabic translations. You possess a deep understanding of the linguistic, cultural, and contextual nuances essential for accurate and effective translation between these languages. Highly motivated and detail-oriented, you are committed to delivering translations that maintain the integrity and intent of the original text. Your role is crucial in ensuring clear and precise communication in our multilingual system.\"\"\""
]
},
{
"cell_type": "markdown",
"id": "803ddeba-03de-4f13-95d1-5fb097058cf2",
"metadata": {
"id": "803ddeba-03de-4f13-95d1-5fb097058cf2"
},
"source": [
"### Instruction\n",
"> Translate this from arabic to english: {translation_input}.\n",
">\n",
"> Translation:\n",
"\n",
"We will use a simple instruction to get a translation."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b7f1722c-c484-4e22-a025-53f95943fc76",
"metadata": {
"id": "b7f1722c-c484-4e22-a025-53f95943fc76"
},
"outputs": [],
"source": [
"def baseline_chat_completion(system_prompt, translation_input):\n",
" \"\"\"\n",
" Generates a completion for a chat conversation using a specified system prompt and a user input.\n",
" \"\"\"\n",
" messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": f\"Translate this from english to arabic: {translation_input}.\\nTranslation: \",\n",
" },\n",
" ]\n",
" return client.chat_completion(messages, max_tokens=10_000)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "96a0ba0b-be47-4eb0-bbc2-c82b0ea1b72e",
"metadata": {
"tags": [],
"id": "96a0ba0b-be47-4eb0-bbc2-c82b0ea1b72e"
},
"outputs": [],
"source": [
"translation_input = \"Float like a butterfly sting like a bee – his hands can’t hit what his eyes can’t see.\"\n",
"response = baseline_chat_completion(\n",
" system_prompt,\n",
" translation_input,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "2bca574c-461d-4822-b0dd-b12a3b9846b3",
"metadata": {
"id": "2bca574c-461d-4822-b0dd-b12a3b9846b3"
},
"source": [
"### Token Cost\n",
"Here we can see that the cost is quite cheap, only 92 tokens!"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4e305b1e-56e0-44da-8c17-496cbcc35fad",
"metadata": {
"tags": [],
"id": "4e305b1e-56e0-44da-8c17-496cbcc35fad",
"outputId": "a97a8a75-e2e6-4ac3-e7ac-db674a1f46c9"
},
"outputs": [
{
"data": {
"text/plain": [
"120"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"response.usage.prompt_tokens"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ef24fe6b-d801-4f3e-95ad-cb7f67247bc3",
"metadata": {
"tags": [],
"id": "ef24fe6b-d801-4f3e-95ad-cb7f67247bc3",
"outputId": "0d7417e1-b648-40aa-eba7-5f1b0dc962b3"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"يطير كالفراشة ويلسع كالنحلة - لا يمكن ليديه أن تصيبا ما لا تستطيع عيناه رؤيته.\n"
]
}
],
"source": [
"print(response.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"id": "3a9cdf02-d590-4bcf-a7a8-e6b7817ba715",
"metadata": {
"id": "3a9cdf02-d590-4bcf-a7a8-e6b7817ba715"
},
"source": [
"## Manual Purpose Driven Translation\n",
"\n",
"[Optimizing Machine Translation through Prompt Engineering](https://arxiv.org/pdf/2308.01391) has done some good exploratory work in examining how prompt engineering can impact translation. They were working between Japanese and English and showed that translations influenced by prompts tailored to **specific purposes** and **target audiences** generally adhered more closely to the translation specifications, suggesting that such prompted translations could be more culturally and contextually appropriate than standard machine translations.\n",
"\n",
"### Prompt\n",
"One of the approaches in the paper was to include the purpose and target audience specification. This was motivated by the author’s experience as a professional translator, leading to the conclusion that these two parameters are essential even in everyday translation work. You can find the prompt below adapted for Arabic to English:\n",
"\n",
"> Translate the following English [source text] into Arabic. Please fulfill the following conditions when translating. \n",
"> Purpose of the translation: `<Manual description>` \n",
"> Target audience: `<Manual description>` \n",
"> [source text] `{translation_input}` \n",
"> [translated text]\n",
"\n",
"You can see that we need to provide the Purpose and the Target Audience for each translation. This makes sense as we will be able to steer our model appropriately, but the drawback is that we need to do this for each subject. In the real world this likely won't scale and is rather tedious.\n",
"\n",
"Lets go ahead and create these for each of our datasets."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4714f6a2-fd0b-48ee-80bc-860f40ee2baa",
"metadata": {
"tags": [],
"id": "4714f6a2-fd0b-48ee-80bc-860f40ee2baa"
},
"outputs": [],
"source": [
"dataset_to_purpose_target = {\n",
" \"ELRC-24ss\": {\n",
" \"purpose\": \"Enhancing understanding and knowledge about COVID-19 and health-related topics.\",\n",
" \"audience\": \"Individuals seeking reliable and comprehensible information about COVID-19 and related health topics.\",\n",
" },\n",
" \"GNOME-25ss\": {\n",
" \"purpose\": \"Facilitating localization and translation of GNOME software.\",\n",
" \"audience\": \"Translators and developers working on GNOME projects.\"\n",
" },\n",
" \"HPLT-25ss\": {\n",
" \"purpose\": \"Providing multilingual data for high-performance language technologies.\",\n",
" \"audience\": \"Researchers and developers working on multilingual NLP applications.\"\n",
" },\n",
" \"OpenSubtitles-25ss\": {\n",
" \"purpose\": \"Creating parallel corpora from movie and TV subtitles.\",\n",
" \"audience\": \"Researchers and developers in NLP and machine translation. And Movies and TV Shows translators\"\n",
" },\n",
" \"TED2020-25ss\": {\n",
" \"purpose\": \"Generating multilingual sentence embeddings using TED transcripts.\",\n",
" \"audience\": \"Researchers and developers working on multilingual sentence embeddings.\"\n",
" },\n",
" \"UNPC-24ss\": {\n",
" \"purpose\": \"Offering a parallel corpus of United Nations documents for linguistic research.\",\n",
" \"audience\": \"Researchers and linguists studying multilingual and legal texts.\"\n",
" }\n",
"}\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f865e9f8-7c63-4e72-b539-0d5916eda44f",
"metadata": {
"id": "f865e9f8-7c63-4e72-b539-0d5916eda44f"
},
"outputs": [],
"source": [
"def purpose_driven_chat_completion(system_prompt, translation_input, dataset):\n",
" \"\"\"\n",
" Generates a completion for a chat conversation using a specified system prompt and a user input.\n",
" \"\"\"\n",
"\n",
" prompt = f\"\"\"Translate the following English [source text] into Arabic. Please fulfill the following conditions when translating.\n",
"Purpose of the translation: {dataset_to_purpose_target[dataset]['purpose']}\n",
"Target audience: {dataset_to_purpose_target[dataset]['audience']}\n",
"[source text] `{translation_input}`\n",
"[translated text] \"\"\"\n",
"\n",
" messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": prompt,\n",
" },\n",
" ]\n",
" return client.chat_completion(messages, max_tokens=10_000)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4115515d-cbcd-405a-b2e0-a805880a40c4",
"metadata": {
"tags": [],
"id": "4115515d-cbcd-405a-b2e0-a805880a40c4"
},
"outputs": [],
"source": [
"translation_input = \"We have observed that when groups of stakeholders work to define … visions, this leads to debate over whether to emphasize ecosystem health or human well-being … Whether the priority is ecosystems or people greatly influences stakeholders' assessment of desirable ecological and social states.\"\n",
"response = purpose_driven_chat_completion(system_prompt, translation_input, \"ELRC-24ss\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6296d255-d11d-4df7-aa0e-1226ef3d963a",
"metadata": {
"tags": [],
"id": "6296d255-d11d-4df7-aa0e-1226ef3d963a",
"outputId": "45282f39-18ef-4dc0-f708-1113ca1769ce"
},
"outputs": [
{
"data": {
"text/plain": [
"208"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"response.usage.prompt_tokens"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1f1c6dd0-11bf-4b88-9029-8bce1e7bcb1c",
"metadata": {
"tags": [],
"id": "1f1c6dd0-11bf-4b88-9029-8bce1e7bcb1c",
"outputId": "a12fc058-249f-4493-eb3e-f021c12651dc"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\"لقد لاحظنا أنه عندما تعمل مجموعات أصحاب المصلحة على تحديد ... الرؤى، فإن هذا يؤدي إلى نقاش حول ما إذا كان ينبغي التركيز على صحة النظام البيئي أو رفاهية الإنسان ... إن معرفة ما إذا كانت الأولوية للنظم البيئية أو للبشر تؤثر بشكل كبير على تقييم أصحاب المصلحة للحالات البيئية والاجتماعية المرغوبة.\"\n"
]
}
],
"source": [
"print(response.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"id": "898a909e-88a2-4efb-99ed-64ceee317037",
"metadata": {
"id": "898a909e-88a2-4efb-99ed-64ceee317037"
},
"source": [
"## Automatic Purpose Driven Structured Generation Translation\n",
"\n",
"Manual Purpose Driven Translation is a great step in the right direction, but its challenging to scale. Instead of having the user submit these purposes and target audiences, what if we use a model to do that? The easiest way to get this input in a format that is convenient is going to be by using [structured generation](https://huggingface.co/blog/evaluation-structured-outputs) to get a json. We can easily do this in InferenceClient easily just by using [tools](https://huggingface.co/docs/huggingface_hub/en/package_reference/inference_client#huggingface_hub.InferenceClient.chat_completion.tools)"
]
},
{
"cell_type": "markdown",
"id": "8aca3847-7f3d-43d3-8e80-0c7e2282073b",
"metadata": {
"id": "8aca3847-7f3d-43d3-8e80-0c7e2282073b"
},
"source": [
"## Instruction"
]
},
{
"cell_type": "markdown",
"id": "2f5deb21-18fb-4c5b-9045-c7fe5e751c05",
"metadata": {
"id": "2f5deb21-18fb-4c5b-9045-c7fe5e751c05"
},
"source": [
"Its usually helpful if we tell the LLM what we want to create when we prompt it. I have found using the tags like `<source text>` can be really useful to denote what you are specifying.\n",
"\n",
"> I want to translate the following \\<source text\\> from English into Arabic. But first I want to create a json that includes the following: \n",
"{\"intent\": \"\", \"subject\": \"\", \"assumptions relating to content\": \"\", \"purpose\": \"\", \"target audience\": \"\"}. \n",
"Can you fill this out and be specific to how this can help you translate in the next step? No need to translate yet! \n",
"\\<source text\\> \n",
"\\</source text\\> "
]
},
{
"cell_type": "markdown",
"id": "55f02988-1c63-4f03-a5a6-ca86c83b3c17",
"metadata": {
"id": "55f02988-1c63-4f03-a5a6-ca86c83b3c17"
},
"source": [
"## Tool Definition"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "affe3668-aa37-47b5-be37-a0bd5dabab56",
"metadata": {
"tags": [],
"id": "affe3668-aa37-47b5-be37-a0bd5dabab56"
},
"outputs": [],
"source": [
"translation_tools = [\n",
" {\n",
" \"type\": \"function\",\n",
" \"function\": {\n",
" \"name\": \"get_translation_audience_purpose\",\n",
" \"description\": \"Get the background of a text to assist in translation\",\n",
" \"parameters\": {\n",
" \"type\": \"object\",\n",
" \"properties\": {\n",
" \"subject\": {\n",
" \"type\": \"string\",\n",
" \"description\": \"The topic or central theme that the text revolves around.\",\n",
" },\n",
" \"assumptions relating to the content\": {\n",
" \"type\": \"string\",\n",
" \"description\": \"Write out any assumptions relating to the text.\",\n",
" },\n",
" \"purpose\": {\n",
" \"type\": \"string\",\n",
" \"description\": \"Why the text was written\",\n",
" },\n",
" \"audience\": {\n",
" \"type\": \"string\",\n",
" \"description\": \"The inferred audience that the text is written for.\",\n",
" },\n",
" },\n",
" \"required\": [\n",
" \"subject\",\n",
" \"assumptions relating to the content\",\n",
" \"purpose\",\n",
" \"audience\",\n",
" ],\n",
" },\n",
" },\n",
" }\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b6436ce6-03af-4206-a283-0c2ecd17bd88",
"metadata": {
"id": "b6436ce6-03af-4206-a283-0c2ecd17bd88"
},
"outputs": [],
"source": [
"def tool_call_chat_completion(system_prompt, translation_input, tools):\n",
" \"\"\"\n",
" Generates a completion for a chat conversation using a specified system prompt and a user input.\n",
" \"\"\"\n",
"\n",
" prompt = f\"\"\"I want to translate the following <source text> from English into Arabic. But first I want to create a json that includes the following:\n",
"{{\"subject\": \"\", \"assumptions relating to content\": \"\", \"purpose\": \"\", \"target audience\": \"\"}}.\n",
"Can you fill this out and be specific to how this can help you translate in the next step? No need to translate yet!\n",
"<source text>\n",
"{translation_input}\n",
"</source text>\n",
"\"\"\"\n",
" messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": prompt,\n",
" },\n",
" ]\n",
" return client.chat_completion(messages, max_tokens=10_000, tools=tools, tool_choice='get_translation_audience_purpose')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a731b2c0-54a3-4b8e-83f6-1663c759cf79",
"metadata": {
"tags": [],
"id": "a731b2c0-54a3-4b8e-83f6-1663c759cf79"
},
"outputs": [],
"source": [
"translation_input = \"We have observed that when groups of stakeholders work to define … visions, this leads to debate over whether to emphasize ecosystem health or human well-being … Whether the priority is ecosystems or people greatly influences stakeholders' assessment of desirable ecological and social states.\"\n",
"response = tool_call_chat_completion(system_prompt, translation_input, translation_tools)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "07e0f133-f6e1-4bc6-969c-da9d36bfba2f",
"metadata": {
"tags": [],
"id": "07e0f133-f6e1-4bc6-969c-da9d36bfba2f",
"outputId": "82e2506a-7336-4909-b8e4-fc52f671c511"
},
"outputs": [
{
"data": {
"text/plain": [
"454"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"function_call_tokens = response.usage.prompt_tokens\n",
"function_call_tokens"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "02be1827-7137-463f-a026-0b26dec6f552",
"metadata": {
"tags": [],
"id": "02be1827-7137-463f-a026-0b26dec6f552",
"outputId": "60cd7be7-b6ac-412b-e0bc-3b8d3088f2b2"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'assumptions relating to the content': 'The text assumes that the readers '\n",
" 'understand the concept of stakeholder '\n",
" 'groups and their potential differing '\n",
" 'priorities regarding environmental '\n",
" 'and social issues.',\n",
" 'audience': 'The target audience for this text is likely individuals or '\n",
" 'organizations involved in sustainability, ecology, or social '\n",
" 'welfare fields, as well as stakeholders with an interest in '\n",
" 'these areas.',\n",
" 'purpose': 'The purpose of this text is to highlight the observations made '\n",
" 'about the debates that arise when stakeholder groups define their '\n",
" 'visions, specifically regarding the priority between ecosystem '\n",
" 'health and human well-being, and how this priority influences '\n",
" 'their assessment of desired ecological and social outcomes.',\n",
" 'subject': 'Debates on Prioritizing Ecosystem vs. Human Well-being by '\n",
" 'Stakeholder Groups'}\n"
]
}
],
"source": [
"from pprint import pprint\n",
"description_json = response.choices[0].message.tool_calls[0].function.arguments\n",
"pprint(description_json)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7575bd09-2d20-49ae-bb10-162a0e469f16",
"metadata": {
"id": "7575bd09-2d20-49ae-bb10-162a0e469f16"
},
"outputs": [],
"source": [
"def automatic_purpose_driven_chat_completion(system_prompt, translation_input, description_json):\n",
" \"\"\"\n",
" Generates a completion for a chat conversation using a specified system prompt and a user input.\n",
" \"\"\"\n",
"\n",
" prompt = f\"\"\"Given the following descriptive json translate <source text> from English to Arabic\n",
"{description_json}\n",
"<source text>\n",
"{translation_input}\n",
"</source text>\n",
"Translation:\n",
"\"\"\"\n",
" messages = [\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": prompt,\n",
" },\n",
" ]\n",
" return client.chat_completion(messages, max_tokens=10_000)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "32bccca0-c866-4006-84d1-d5b783b73689",
"metadata": {
"tags": [],
"id": "32bccca0-c866-4006-84d1-d5b783b73689"
},
"outputs": [],
"source": [
"response = automatic_purpose_driven_chat_completion(system_prompt, translation_input, description_json)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b0867efb-39ea-4f9a-b073-2a84261f3821",
"metadata": {
"tags": [],
"id": "b0867efb-39ea-4f9a-b073-2a84261f3821",
"outputId": "485ece36-c47e-4d1d-cf50-bbe1a9960776"
},
"outputs": [
{
"data": {
"text/plain": [
"311"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"automatic_purpose_driven_tokens = response.usage.prompt_tokens\n",
"automatic_purpose_driven_tokens"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "462ca84c-9ffd-4924-880d-e06b724caf02",
"metadata": {
"tags": [],
"id": "462ca84c-9ffd-4924-880d-e06b724caf02",
"outputId": "bf026405-eb15-4a28-8357-d99e174967e7"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Here is the translated text from English to Arabic:\n",
"\n",
"{\"افتراضات متعلقة بالمحتوى\": \"يفترض النص أن القراء يفهمون مفهوم مجموعات أصحاب المصلحة وأولوياتهم المختلفة المحتملة فيما يتعلق بالقضايا البيئية والاجتماعية.\", \"الجمهور\": \"الجمهور المستهدف لهذا النص هو على الأرجح أفراد أو منظمات تعمل في مجالات الاستدامة أو الإيكولوجيا أو الرعاية الاجتماعية، بالإضافة إلى أصحاب المصلحة المهتمين بهذه المجالات.\", \"الغرض\": \"الغرض من هذا النص هو تسليط الضوء على الملاحظات التي أبديت حول النقاشات التي تنشأ عندما تحدد مجموعات أصحاب المصلحة رؤيتها، خاصة فيما يتعلق بالأولوية بين صحة النظام البيئي ورفاهية الإنسان، وكيف تؤثر هذه الأولوية على تقييمها للنتائج الإيكولوجية والاجتماعية المرجوة.\", \"الموضوع\": \"النقاشات حول أولويات النظام البيئي مقابل رفاهية الإنسان من قبل مجموعات أصحاب المصلحة\": \"لقد لاحظنا أنه عندما تعمل مجموعات أصحاب المصلحة على تحديد الرؤى، فإن ذلك يؤدي إلى نقاش حول ما إذا كان ينبغي التركيز على صحة النظام البيئي أو رفاهية الإنسان... إن أولوية النظم البيئية أو البشر تؤثر بشكل كبير على تقييم أصحاب المصلحة للوضع الاجتماعي والإيكولوجي المرغوب.\"}\n"
]
}
],
"source": [
"print(response.choices[0].message.content)"
]
},
{
"cell_type": "markdown",
"id": "1ec3b20b-8393-4fda-a51d-cf67984cc166",
"metadata": {
"id": "1ec3b20b-8393-4fda-a51d-cf67984cc166"
},
"source": [
"# Push to the hub"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6fc55725-216f-45dd-9c6d-dae77e16d606",
"metadata": {
"tags": [],
"id": "6fc55725-216f-45dd-9c6d-dae77e16d606",
"outputId": "d3b9b994-e3af-4f05-88b4-3b29778d1dc7"
},
"outputs": [
{
"data": {
"text/plain": [
"CommitInfo(commit_url='https://huggingface.co/arabic-translation-prompt-engineering/atpe-notebooks/commit/d112cc49a99a72106b75c3eae9be453264fb488d', commit_message='Upload baseline.ipynb with huggingface_hub', commit_description='', oid='d112cc49a99a72106b75c3eae9be453264fb488d', pr_url=None, pr_revision=None, pr_num=None)"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from huggingface_hub import HfApi\n",
"\n",
"api = HfApi()\n",
"api.upload_file(\n",
" path_or_fileobj=\"baseline.ipynb\",\n",
" path_in_repo=\"baseline.ipynb\",\n",
" repo_id=\"arabic-translation-prompt-engineering/atpe-notebooks\",\n",
" repo_type=\"model\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6f21f4cf-1872-4934-bb91-8aef311ed729",
"metadata": {
"id": "6f21f4cf-1872-4934-bb91-8aef311ed729"
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.9"
},
"colab": {
"provenance": []
}
},
"nbformat": 4,
"nbformat_minor": 5
} |