Spaces:
Runtime error
Runtime error
File size: 20,692 Bytes
acc4ffe |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "bf038596",
"metadata": {},
"source": [
"# Example Selectors\n",
"If you have a large number of examples, you may need to select which ones to include in the prompt. The ExampleSelector is the class responsible for doing so. The base interface is defined as below.\n",
"\n",
"```python\n",
"class BaseExampleSelector(ABC):\n",
" \"\"\"Interface for selecting examples to include in prompts.\"\"\"\n",
"\n",
" @abstractmethod\n",
" def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:\n",
" \"\"\"Select which examples to use based on the inputs.\"\"\"\n",
"\n",
"```\n",
"\n",
"The only method it needs to expose is a `select_examples` method. This takes in the input variables and then returns a list of examples. It is up to each specific implementation as to how those examples are selected. Let's take a look at some below."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "8244ff60",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import FewShotPromptTemplate"
]
},
{
"cell_type": "markdown",
"id": "861a4d1f",
"metadata": {},
"source": [
"## LengthBased ExampleSelector\n",
"\n",
"This ExampleSelector selects which examples to use based on length. This is useful when you are worried about constructing a prompt that will go over the length of the context window. For longer inputs, it will select fewer examples to include, while for shorter inputs it will select more.\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "7c469c95",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate\n",
"from langchain.prompts.example_selector import LengthBasedExampleSelector"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "0ec6d950",
"metadata": {},
"outputs": [],
"source": [
"# These are a lot of examples of a pretend task of creating antonyms.\n",
"examples = [\n",
" {\"input\": \"happy\", \"output\": \"sad\"},\n",
" {\"input\": \"tall\", \"output\": \"short\"},\n",
" {\"input\": \"energetic\", \"output\": \"lethargic\"},\n",
" {\"input\": \"sunny\", \"output\": \"gloomy\"},\n",
" {\"input\": \"windy\", \"output\": \"calm\"},\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "207e55f7",
"metadata": {},
"outputs": [],
"source": [
"example_prompt = PromptTemplate(\n",
" input_variables=[\"input\", \"output\"],\n",
" template=\"Input: {input}\\nOutput: {output}\",\n",
")\n",
"example_selector = LengthBasedExampleSelector(\n",
" # These are the examples it has available to choose from.\n",
" examples=examples, \n",
" # This is the PromptTemplate being used to format the examples.\n",
" example_prompt=example_prompt, \n",
" # This is the maximum length that the formatted examples should be.\n",
" # Length is measured by the get_text_length function below.\n",
" max_length=25,\n",
" # This is the function used to get the length of a string, which is used\n",
" # to determine which examples to include. It is commented out because\n",
" # it is provided as a default value if none is specified.\n",
" # get_text_length: Callable[[str], int] = lambda x: len(re.split(\"\\n| \", x))\n",
")\n",
"dynamic_prompt = FewShotPromptTemplate(\n",
" # We provide an ExampleSelector instead of examples.\n",
" example_selector=example_selector,\n",
" example_prompt=example_prompt,\n",
" prefix=\"Give the antonym of every input\",\n",
" suffix=\"Input: {adjective}\\nOutput:\", \n",
" input_variables=[\"adjective\"],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "d00b4385",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the antonym of every input\n",
"\n",
"Input: happy\n",
"Output: sad\n",
"\n",
"Input: tall\n",
"Output: short\n",
"\n",
"Input: energetic\n",
"Output: lethargic\n",
"\n",
"Input: sunny\n",
"Output: gloomy\n",
"\n",
"Input: windy\n",
"Output: calm\n",
"\n",
"Input: big\n",
"Output:\n"
]
}
],
"source": [
"# An example with small input, so it selects all examples.\n",
"print(dynamic_prompt.format(adjective=\"big\"))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "878bcde9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the antonym of every input\n",
"\n",
"Input: happy\n",
"Output: sad\n",
"\n",
"Input: big and huge and massive and large and gigantic and tall and much much much much much bigger than everything else\n",
"Output:\n"
]
}
],
"source": [
"# An example with long input, so it selects only one example.\n",
"long_string = \"big and huge and massive and large and gigantic and tall and much much much much much bigger than everything else\"\n",
"print(dynamic_prompt.format(adjective=long_string))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e4bebcd9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the antonym of every input\n",
"\n",
"Input: happy\n",
"Output: sad\n",
"\n",
"Input: tall\n",
"Output: short\n",
"\n",
"Input: energetic\n",
"Output: lethargic\n",
"\n",
"Input: sunny\n",
"Output: gloomy\n",
"\n",
"Input: windy\n",
"Output: calm\n",
"\n",
"Input: big\n",
"Output: small\n",
"\n",
"Input: enthusiastic\n",
"Output:\n"
]
}
],
"source": [
"# You can add an example to an example selector as well.\n",
"new_example = {\"input\": \"big\", \"output\": \"small\"}\n",
"dynamic_prompt.example_selector.add_example(new_example)\n",
"print(dynamic_prompt.format(adjective=\"enthusiastic\"))"
]
},
{
"cell_type": "markdown",
"id": "2d007b0a",
"metadata": {},
"source": [
"## Similarity ExampleSelector\n",
"\n",
"The SemanticSimilarityExampleSelector selects examples based on which examples are most similar to the inputs. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs.\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "241bfe80",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts.example_selector import SemanticSimilarityExampleSelector\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.embeddings import OpenAIEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "50d0a701",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"example_selector = SemanticSimilarityExampleSelector.from_examples(\n",
" # This is the list of examples available to select from.\n",
" examples, \n",
" # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
" OpenAIEmbeddings(), \n",
" # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
" Chroma, \n",
" # This is the number of examples to produce.\n",
" k=1\n",
")\n",
"similar_prompt = FewShotPromptTemplate(\n",
" # We provide an ExampleSelector instead of examples.\n",
" example_selector=example_selector,\n",
" example_prompt=example_prompt,\n",
" prefix=\"Give the antonym of every input\",\n",
" suffix=\"Input: {adjective}\\nOutput:\", \n",
" input_variables=[\"adjective\"],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "4c8fdf45",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the antonym of every input\n",
"\n",
"Input: happy\n",
"Output: sad\n",
"\n",
"Input: worried\n",
"Output:\n"
]
}
],
"source": [
"# Input is a feeling, so should select the happy/sad example\n",
"print(similar_prompt.format(adjective=\"worried\"))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "829af21a",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the antonym of every input\n",
"\n",
"Input: happy\n",
"Output: sad\n",
"\n",
"Input: fat\n",
"Output:\n"
]
}
],
"source": [
"# Input is a measurement, so should select the tall/short example\n",
"print(similar_prompt.format(adjective=\"fat\"))"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "3c16fe23",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the antonym of every input\n",
"\n",
"Input: happy\n",
"Output: sad\n",
"\n",
"Input: joyful\n",
"Output:\n"
]
}
],
"source": [
"# You can add new examples to the SemanticSimilarityExampleSelector as well\n",
"similar_prompt.example_selector.add_example({\"input\": \"enthusiastic\", \"output\": \"apathetic\"})\n",
"print(similar_prompt.format(adjective=\"joyful\"))"
]
},
{
"cell_type": "markdown",
"id": "bc35afd0",
"metadata": {},
"source": [
"## Maximal Marginal Relevance ExampleSelector\n",
"\n",
"The MaxMarginalRelevanceExampleSelector selects examples based on a combination of which examples are most similar to the inputs, while also optimizing for diversity. It does this by finding the examples with the embeddings that have the greatest cosine similarity with the inputs, and then iteratively adding them while penalizing them for closeness to already selected examples.\n"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "ac95c968",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts.example_selector import MaxMarginalRelevanceExampleSelector\n",
"from langchain.vectorstores import FAISS"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "db579bea",
"metadata": {},
"outputs": [],
"source": [
"example_selector = MaxMarginalRelevanceExampleSelector.from_examples(\n",
" # This is the list of examples available to select from.\n",
" examples, \n",
" # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
" OpenAIEmbeddings(), \n",
" # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
" FAISS, \n",
" # This is the number of examples to produce.\n",
" k=2\n",
")\n",
"mmr_prompt = FewShotPromptTemplate(\n",
" # We provide an ExampleSelector instead of examples.\n",
" example_selector=example_selector,\n",
" example_prompt=example_prompt,\n",
" prefix=\"Give the antonym of every input\",\n",
" suffix=\"Input: {adjective}\\nOutput:\", \n",
" input_variables=[\"adjective\"],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "cd76e344",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the antonym of every input\n",
"\n",
"Input: happy\n",
"Output: sad\n",
"\n",
"Input: windy\n",
"Output: calm\n",
"\n",
"Input: worried\n",
"Output:\n"
]
}
],
"source": [
"# Input is a feeling, so should select the happy/sad example as the first one\n",
"print(mmr_prompt.format(adjective=\"worried\"))"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "cf82956b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the antonym of every input\n",
"\n",
"Input: enthusiastic\n",
"Output: apathetic\n",
"\n",
"Input: worried\n",
"Output:\n"
]
}
],
"source": [
"# Let's compare this to what we would just get if we went solely off of similarity\n",
"similar_prompt.example_selector.k = 2\n",
"print(similar_prompt.format(adjective=\"worried\"))"
]
},
{
"cell_type": "markdown",
"id": "4aaeed2f",
"metadata": {},
"source": [
"## NGram Overlap ExampleSelector\n",
"\n",
"The NGramOverlapExampleSelector selects and orders examples based on which examples are most similar to the input, according to an ngram overlap score. The ngram overlap score is a float between 0.0 and 1.0, inclusive. \n",
"\n",
"The selector allows for a threshold score to be set. Examples with an ngram overlap score less than or equal to the threshold are excluded. The threshold is set to -1.0, by default, so will not exclude any examples, only reorder them. Setting the threshold to 0.0 will exclude examples that have no ngram overlaps with the input.\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9cbc0acc",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate\n",
"from langchain.prompts.example_selector.ngram_overlap import NGramOverlapExampleSelector"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "4f318f4b",
"metadata": {},
"outputs": [],
"source": [
"# These are examples of a fictional translation task.\n",
"examples = [\n",
" {\"input\": \"See Spot run.\", \"output\": \"Ver correr a Spot.\"},\n",
" {\"input\": \"My dog barks.\", \"output\": \"Mi perro ladra.\"},\n",
" {\"input\": \"Spot can run.\", \"output\": \"Spot puede correr.\"},\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "bf75e0fe",
"metadata": {},
"outputs": [],
"source": [
"example_prompt = PromptTemplate(\n",
" input_variables=[\"input\", \"output\"],\n",
" template=\"Input: {input}\\nOutput: {output}\",\n",
")\n",
"example_selector = NGramOverlapExampleSelector(\n",
" # These are the examples it has available to choose from.\n",
" examples=examples, \n",
" # This is the PromptTemplate being used to format the examples.\n",
" example_prompt=example_prompt, \n",
" # This is the threshold, at which selector stops.\n",
" # It is set to -1.0 by default.\n",
" threshold=-1.0,\n",
" # For negative threshold:\n",
" # Selector sorts examples by ngram overlap score, and excludes none.\n",
" # For threshold greater than 1.0:\n",
" # Selector excludes all examples, and returns an empty list.\n",
" # For threshold equal to 0.0:\n",
" # Selector sorts examples by ngram overlap score,\n",
" # and excludes those with no ngram overlap with input.\n",
")\n",
"dynamic_prompt = FewShotPromptTemplate(\n",
" # We provide an ExampleSelector instead of examples.\n",
" example_selector=example_selector,\n",
" example_prompt=example_prompt,\n",
" prefix=\"Give the Spanish translation of every input\",\n",
" suffix=\"Input: {sentence}\\nOutput:\", \n",
" input_variables=[\"sentence\"],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "83fb218a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the Spanish translation of every input\n",
"\n",
"Input: Spot can run.\n",
"Output: Spot puede correr.\n",
"\n",
"Input: See Spot run.\n",
"Output: Ver correr a Spot.\n",
"\n",
"Input: My dog barks.\n",
"Output: Mi perro ladra.\n",
"\n",
"Input: Spot can run fast.\n",
"Output:\n"
]
}
],
"source": [
"# An example input with large ngram overlap with \"Spot can run.\"\n",
"# and no overlap with \"My dog barks.\"\n",
"print(dynamic_prompt.format(sentence=\"Spot can run fast.\"))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "485f5307",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the Spanish translation of every input\n",
"\n",
"Input: Spot can run.\n",
"Output: Spot puede correr.\n",
"\n",
"Input: See Spot run.\n",
"Output: Ver correr a Spot.\n",
"\n",
"Input: Spot plays fetch.\n",
"Output: Spot juega a buscar.\n",
"\n",
"Input: My dog barks.\n",
"Output: Mi perro ladra.\n",
"\n",
"Input: Spot can run fast.\n",
"Output:\n"
]
}
],
"source": [
"# You can add examples to NGramOverlapExampleSelector as well.\n",
"new_example = {\"input\": \"Spot plays fetch.\", \"output\": \"Spot juega a buscar.\"}\n",
"\n",
"example_selector.add_example(new_example)\n",
"print(dynamic_prompt.format(sentence=\"Spot can run fast.\"))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "606ce697",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the Spanish translation of every input\n",
"\n",
"Input: Spot can run.\n",
"Output: Spot puede correr.\n",
"\n",
"Input: See Spot run.\n",
"Output: Ver correr a Spot.\n",
"\n",
"Input: Spot plays fetch.\n",
"Output: Spot juega a buscar.\n",
"\n",
"Input: Spot can run fast.\n",
"Output:\n"
]
}
],
"source": [
"# You can set a threshold at which examples are excluded.\n",
"# For example, setting threshold equal to 0.0\n",
"# excludes examples with no ngram overlaps with input.\n",
"# Since \"My dog barks.\" has no ngram overlaps with \"Spot can run fast.\"\n",
"# it is excluded.\n",
"example_selector.threshold=0.0\n",
"print(dynamic_prompt.format(sentence=\"Spot can run fast.\"))"
]
},
{
"cell_type": "code",
"execution_count": 87,
"id": "7f8d72f7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the Spanish translation of every input\n",
"\n",
"Input: Spot can run.\n",
"Output: Spot puede correr.\n",
"\n",
"Input: Spot plays fetch.\n",
"Output: Spot juega a buscar.\n",
"\n",
"Input: Spot can play fetch.\n",
"Output:\n"
]
}
],
"source": [
"# Setting small nonzero threshold\n",
"example_selector.threshold=0.09\n",
"print(dynamic_prompt.format(sentence=\"Spot can play fetch.\"))"
]
},
{
"cell_type": "code",
"execution_count": 88,
"id": "09633aa8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Give the Spanish translation of every input\n",
"\n",
"Input: Spot can play fetch.\n",
"Output:\n"
]
}
],
"source": [
"# Setting threshold greater than 1.0\n",
"example_selector.threshold=1.0+1e-9\n",
"print(dynamic_prompt.format(sentence=\"Spot can play fetch.\"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "39f30097",
"metadata": {},
"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": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|