Spaces:
Sleeping
Sleeping
File size: 29,290 Bytes
cfd3735 |
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 |
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "5436020b",
"metadata": {},
"source": [
"# Defining Custom Tools\n",
"\n",
"When constructing your own agent, you will need to provide it with a list of Tools that it can use. Besides the actual function that is called, the Tool consists of several components:\n",
"\n",
"- name (str), is required and must be unique within a set of tools provided to an agent\n",
"- description (str), is optional but recommended, as it is used by an agent to determine tool use\n",
"- return_direct (bool), defaults to False\n",
"- args_schema (Pydantic BaseModel), is optional but recommended, can be used to provide more information (e.g., few-shot examples) or validation for expected parameters.\n",
"\n",
"\n",
"There are two main ways to define a tool, we will cover both in the example below."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "1aaba18c",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Import things that are needed generically\n",
"from langchain import LLMMathChain, SerpAPIWrapper\n",
"from langchain.agents import AgentType, initialize_agent\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.tools import BaseTool, StructuredTool, Tool, tool"
]
},
{
"cell_type": "markdown",
"id": "8e2c3874",
"metadata": {},
"source": [
"Initialize the LLM to use for the agent."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "36ed392e",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"llm = ChatOpenAI(temperature=0)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "f8bc72c2",
"metadata": {},
"source": [
"## Completely New Tools - String Input and Output\n",
"\n",
"The simplest tools accept a single query string and return a string output. If your tool function requires multiple arguments, you might want to skip down to the `StructuredTool` section below.\n",
"\n",
"There are two ways to do this: either by using the Tool dataclass, or by subclassing the BaseTool class."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "b63fcc3b",
"metadata": {},
"source": [
"### Tool dataclass\n",
"\n",
"The 'Tool' dataclass wraps functions that accept a single string input and returns a string output."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "56ff7670",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/wfh/code/lc/lckg/langchain/chains/llm_math/base.py:50: UserWarning: Directly instantiating an LLMMathChain with an llm is deprecated. Please instantiate with llm_chain argument or using the from_llm class method.\n",
" warnings.warn(\n"
]
}
],
"source": [
"# Load the tool configs that are needed.\n",
"search = SerpAPIWrapper()\n",
"llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
"tools = [\n",
" Tool.from_function(\n",
" func=search.run,\n",
" name = \"Search\",\n",
" description=\"useful for when you need to answer questions about current events\"\n",
" # coroutine= ... <- you can specify an async method if desired as well\n",
" ),\n",
"]"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "e9b560f7",
"metadata": {},
"source": [
"You can also define a custom `args_schema`` to provide more information about inputs."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "631361e7",
"metadata": {},
"outputs": [],
"source": [
"from pydantic import BaseModel, Field\n",
"\n",
"class CalculatorInput(BaseModel):\n",
" question: str = Field()\n",
" \n",
"\n",
"tools.append(\n",
" Tool.from_function(\n",
" func=llm_math_chain.run,\n",
" name=\"Calculator\",\n",
" description=\"useful for when you need to answer questions about math\",\n",
" args_schema=CalculatorInput\n",
" # coroutine= ... <- you can specify an async method if desired as well\n",
" )\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "5b93047d",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Construct the agent. We will use the default agent type here.\n",
"# See documentation for a full list of options.\n",
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "6f96a891",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to find out Leo DiCaprio's girlfriend's name and her age\n",
"Action: Search\n",
"Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAfter rumours of a romance with Gigi Hadid, the Oscar winner has seemingly moved on. First being linked to the television personality in September 2022, it appears as if his \"age bracket\" has moved up. This follows his rumoured relationship with mere 19-year-old Eden Polani.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI still need to find out his current girlfriend's name and age\n",
"Action: Search\n",
"Action Input: \"Leo DiCaprio current girlfriend\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mJust Jared on Instagram: “Leonardo DiCaprio & girlfriend Camila Morrone couple up for a lunch date!\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mNow that I know his girlfriend's name is Camila Morrone, I need to find her current age\n",
"Action: Search\n",
"Action Input: \"Camila Morrone age\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m25 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mNow that I have her age, I need to calculate her age raised to the 0.43 power\n",
"Action: Calculator\n",
"Action Input: 25^(0.43)\u001b[0m\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"25^(0.43)\u001b[32;1m\u001b[1;3m```text\n",
"25**(0.43)\n",
"```\n",
"...numexpr.evaluate(\"25**(0.43)\")...\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m3.991298452658078\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.991298452658078\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer\n",
"Final Answer: Camila Morrone's current age raised to the 0.43 power is approximately 3.99.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Camila Morrone's current age raised to the 0.43 power is approximately 3.99.\""
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "6f12eaf0",
"metadata": {},
"source": [
"### Subclassing the BaseTool class\n",
"\n",
"You can also directly subclass `BaseTool`. This is useful if you want more control over the instance variables or if you want to propagate callbacks to nested chains or other tools."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c58a7c40",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from typing import Optional, Type\n",
"\n",
"from langchain.callbacks.manager import AsyncCallbackManagerForToolRun, CallbackManagerForToolRun\n",
"\n",
"class CustomSearchTool(BaseTool):\n",
" name = \"custom_search\"\n",
" description = \"useful for when you need to answer questions about current events\"\n",
"\n",
" def _run(self, query: str, run_manager: Optional[CallbackManagerForToolRun] = None) -> str:\n",
" \"\"\"Use the tool.\"\"\"\n",
" return search.run(query)\n",
" \n",
" async def _arun(self, query: str, run_manager: Optional[AsyncCallbackManagerForToolRun] = None) -> str:\n",
" \"\"\"Use the tool asynchronously.\"\"\"\n",
" raise NotImplementedError(\"custom_search does not support async\")\n",
" \n",
"class CustomCalculatorTool(BaseTool):\n",
" name = \"Calculator\"\n",
" description = \"useful for when you need to answer questions about math\"\n",
" args_schema: Type[BaseModel] = CalculatorInput\n",
"\n",
" def _run(self, query: str, run_manager: Optional[CallbackManagerForToolRun] = None) -> str:\n",
" \"\"\"Use the tool.\"\"\"\n",
" return llm_math_chain.run(query)\n",
" \n",
" async def _arun(self, query: str, run_manager: Optional[AsyncCallbackManagerForToolRun] = None) -> str:\n",
" \"\"\"Use the tool asynchronously.\"\"\"\n",
" raise NotImplementedError(\"Calculator does not support async\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "3318a46f",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"tools = [CustomSearchTool(), CustomCalculatorTool()]\n",
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "6a2cebbf",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to use custom_search to find out who Leo DiCaprio's girlfriend is, and then use the Calculator to raise her age to the 0.43 power.\n",
"Action: custom_search\n",
"Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAfter rumours of a romance with Gigi Hadid, the Oscar winner has seemingly moved on. First being linked to the television personality in September 2022, it appears as if his \"age bracket\" has moved up. This follows his rumoured relationship with mere 19-year-old Eden Polani.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI need to find out the current age of Eden Polani.\n",
"Action: custom_search\n",
"Action Input: \"Eden Polani age\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m19 years old\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mNow I can use the Calculator to raise her age to the 0.43 power.\n",
"Action: Calculator\n",
"Action Input: 19 ^ 0.43\u001b[0m\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"19 ^ 0.43\u001b[32;1m\u001b[1;3m```text\n",
"19 ** 0.43\n",
"```\n",
"...numexpr.evaluate(\"19 ** 0.43\")...\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m3.547023357958959\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.547023357958959\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
"Final Answer: 3.547023357958959\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'3.547023357958959'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
]
},
{
"cell_type": "markdown",
"id": "824eaf74",
"metadata": {},
"source": [
"## Using the `tool` decorator\n",
"\n",
"To make it easier to define custom tools, a `@tool` decorator is provided. This decorator can be used to quickly create a `Tool` from a simple function. The decorator uses the function name as the tool name by default, but this can be overridden by passing a string as the first argument. Additionally, the decorator will use the function's docstring as the tool's description."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "8f15307d",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.tools import tool\n",
"\n",
"@tool\n",
"def search_api(query: str) -> str:\n",
" \"\"\"Searches the API for the query.\"\"\"\n",
" return f\"Results for query {query}\"\n",
"\n",
"search_api"
]
},
{
"cell_type": "markdown",
"id": "cc6ee8c1",
"metadata": {},
"source": [
"You can also provide arguments like the tool name and whether to return directly."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "28cdf04d",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"@tool(\"search\", return_direct=True)\n",
"def search_api(query: str) -> str:\n",
" \"\"\"Searches the API for the query.\"\"\"\n",
" return \"Results\""
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "1085a4bd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Tool(name='search', description='search(query: str) -> str - Searches the API for the query.', args_schema=<class 'pydantic.main.SearchApi'>, return_direct=True, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x12748c4c0>, func=<function search_api at 0x16bd66310>, coroutine=None)"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"search_api"
]
},
{
"cell_type": "markdown",
"id": "de34a6a3",
"metadata": {},
"source": [
"You can also provide `args_schema` to provide more information about the argument"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "f3a5c106",
"metadata": {},
"outputs": [],
"source": [
"class SearchInput(BaseModel):\n",
" query: str = Field(description=\"should be a search query\")\n",
" \n",
"@tool(\"search\", return_direct=True, args_schema=SearchInput)\n",
"def search_api(query: str) -> str:\n",
" \"\"\"Searches the API for the query.\"\"\"\n",
" return \"Results\""
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "7914ba6b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Tool(name='search', description='search(query: str) -> str - Searches the API for the query.', args_schema=<class '__main__.SearchInput'>, return_direct=True, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x12748c4c0>, func=<function search_api at 0x16bcf0ee0>, coroutine=None)"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"search_api"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "61d2e80b",
"metadata": {},
"source": [
"## Custom Structured Tools\n",
"\n",
"If your functions require more structured arguments, you can use the `StructuredTool` class directly, or still subclass the `BaseTool` class."
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "5be41722",
"metadata": {},
"source": [
"### StructuredTool dataclass\n",
"\n",
"To dynamically generate a structured tool from a given function, the fastest way to get started is with `StructuredTool.from_function()`."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "3c070216",
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"from langchain.tools import StructuredTool\n",
"\n",
"def post_message(url: str, body: dict, parameters: Optional[dict] = None) -> str:\n",
" \"\"\"Sends a POST request to the given url with the given body and parameters.\"\"\"\n",
" result = requests.post(url, json=body, params=parameters)\n",
" return f\"Status: {result.status_code} - {result.text}\"\n",
"\n",
"tool = StructuredTool.from_function(post_message)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "fb0a38eb",
"metadata": {},
"source": [
"## Subclassing the BaseTool\n",
"\n",
"The BaseTool automatically infers the schema from the _run method's signature."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "7505c9c5",
"metadata": {},
"outputs": [],
"source": [
"from typing import Optional, Type\n",
"\n",
"from langchain.callbacks.manager import AsyncCallbackManagerForToolRun, CallbackManagerForToolRun\n",
" \n",
"class CustomSearchTool(BaseTool):\n",
" name = \"custom_search\"\n",
" description = \"useful for when you need to answer questions about current events\"\n",
"\n",
" def _run(self, query: str, engine: str = \"google\", gl: str = \"us\", hl: str = \"en\", run_manager: Optional[CallbackManagerForToolRun] = None) -> str:\n",
" \"\"\"Use the tool.\"\"\"\n",
" search_wrapper = SerpAPIWrapper(params={\"engine\": engine, \"gl\": gl, \"hl\": hl})\n",
" return search_wrapper.run(query)\n",
" \n",
" async def _arun(self, query: str, engine: str = \"google\", gl: str = \"us\", hl: str = \"en\", run_manager: Optional[AsyncCallbackManagerForToolRun] = None) -> str:\n",
" \"\"\"Use the tool asynchronously.\"\"\"\n",
" raise NotImplementedError(\"custom_search does not support async\")\n",
"\n",
"\n",
"\n",
"# You can provide a custom args schema to add descriptions or custom validation\n",
"\n",
"class SearchSchema(BaseModel):\n",
" query: str = Field(description=\"should be a search query\")\n",
" engine: str = Field(description=\"should be a search engine\")\n",
" gl: str = Field(description=\"should be a country code\")\n",
" hl: str = Field(description=\"should be a language code\")\n",
"\n",
"class CustomSearchTool(BaseTool):\n",
" name = \"custom_search\"\n",
" description = \"useful for when you need to answer questions about current events\"\n",
" args_schema: Type[SearchSchema] = SearchSchema\n",
"\n",
" def _run(self, query: str, engine: str = \"google\", gl: str = \"us\", hl: str = \"en\", run_manager: Optional[CallbackManagerForToolRun] = None) -> str:\n",
" \"\"\"Use the tool.\"\"\"\n",
" search_wrapper = SerpAPIWrapper(params={\"engine\": engine, \"gl\": gl, \"hl\": hl})\n",
" return search_wrapper.run(query)\n",
" \n",
" async def _arun(self, query: str, engine: str = \"google\", gl: str = \"us\", hl: str = \"en\", run_manager: Optional[AsyncCallbackManagerForToolRun] = None) -> str:\n",
" \"\"\"Use the tool asynchronously.\"\"\"\n",
" raise NotImplementedError(\"custom_search does not support async\")\n",
" \n",
" "
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "7d68b0ac",
"metadata": {},
"source": [
"## Using the decorator\n",
"\n",
"The `tool` decorator creates a structured tool automatically if the signature has multiple arguments."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "38d11416",
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"from langchain.tools import tool\n",
"\n",
"@tool\n",
"def post_message(url: str, body: dict, parameters: Optional[dict] = None) -> str:\n",
" \"\"\"Sends a POST request to the given url with the given body and parameters.\"\"\"\n",
" result = requests.post(url, json=body, params=parameters)\n",
" return f\"Status: {result.status_code} - {result.text}\""
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "1d0430d6",
"metadata": {},
"source": [
"## Modify existing tools\n",
"\n",
"Now, we show how to load existing tools and modify them directly. In the example below, we do something really simple and change the Search tool to have the name `Google Search`."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "79213f40",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import load_tools"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "e1067dcb",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "6c66ffe8",
"metadata": {},
"outputs": [],
"source": [
"tools[0].name = \"Google Search\""
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "f45b5bc3",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "565e2b9b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to find out Leo DiCaprio's girlfriend's name and her age.\n",
"Action: Google Search\n",
"Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAfter rumours of a romance with Gigi Hadid, the Oscar winner has seemingly moved on. First being linked to the television personality in September 2022, it appears as if his \"age bracket\" has moved up. This follows his rumoured relationship with mere 19-year-old Eden Polani.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI still need to find out his current girlfriend's name and her age.\n",
"Action: Google Search\n",
"Action Input: \"Leo DiCaprio current girlfriend age\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mLeonardo DiCaprio has been linked with 19-year-old model Eden Polani, continuing the rumour that he doesn't date any women over the age of ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI need to find out the age of Eden Polani.\n",
"Action: Calculator\n",
"Action Input: 19^(0.43)\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.547023357958959\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
"Final Answer: The age of Leo DiCaprio's girlfriend raised to the 0.43 power is approximately 3.55.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"The age of Leo DiCaprio's girlfriend raised to the 0.43 power is approximately 3.55.\""
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
]
},
{
"cell_type": "markdown",
"id": "376813ed",
"metadata": {},
"source": [
"## Defining the priorities among Tools\n",
"When you made a Custom tool, you may want the Agent to use the custom tool more than normal tools.\n",
"\n",
"For example, you made a custom tool, which gets information on music from your database. When a user wants information on songs, You want the Agent to use `the custom tool` more than the normal `Search tool`. But the Agent might prioritize a normal Search tool.\n",
"\n",
"This can be accomplished by adding a statement such as `Use this more than the normal search if the question is about Music, like 'who is the singer of yesterday?' or 'what is the most popular song in 2022?'` to the description.\n",
"\n",
"An example is below."
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "3450512e",
"metadata": {},
"outputs": [],
"source": [
"# Import things that are needed generically\n",
"from langchain.agents import initialize_agent, Tool\n",
"from langchain.agents import AgentType\n",
"from langchain.llms import OpenAI\n",
"from langchain import LLMMathChain, SerpAPIWrapper\n",
"search = SerpAPIWrapper()\n",
"tools = [\n",
" Tool(\n",
" name = \"Search\",\n",
" func=search.run,\n",
" description=\"useful for when you need to answer questions about current events\"\n",
" ),\n",
" Tool(\n",
" name=\"Music Search\",\n",
" func=lambda x: \"'All I Want For Christmas Is You' by Mariah Carey.\", #Mock Function\n",
" description=\"A Music search engine. Use this more than the normal search if the question is about Music, like 'who is the singer of yesterday?' or 'what is the most popular song in 2022?'\",\n",
" )\n",
"]\n",
"\n",
"agent = initialize_agent(tools, OpenAI(temperature=0), agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "4b9a7849",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I should use a music search engine to find the answer\n",
"Action: Music Search\n",
"Action Input: most famous song of christmas\u001b[0m\u001b[33;1m\u001b[1;3m'All I Want For Christmas Is You' by Mariah Carey.\u001b[0m\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 'All I Want For Christmas Is You' by Mariah Carey.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"'All I Want For Christmas Is You' by Mariah Carey.\""
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"what is the most famous song of christmas\")"
]
},
{
"cell_type": "markdown",
"id": "bc477d43",
"metadata": {},
"source": [
"## Using tools to return directly\n",
"Often, it can be desirable to have a tool output returned directly to the user, if it’s called. You can do this easily with LangChain by setting the return_direct flag for a tool to be True."
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "3bb6185f",
"metadata": {},
"outputs": [],
"source": [
"llm_math_chain = LLMMathChain(llm=llm)\n",
"tools = [\n",
" Tool(\n",
" name=\"Calculator\",\n",
" func=llm_math_chain.run,\n",
" description=\"useful for when you need to answer questions about math\",\n",
" return_direct=True\n",
" )\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "113ddb84",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "582439a6",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to calculate this\n",
"Action: Calculator\n",
"Action Input: 2**.12\u001b[0m\u001b[36;1m\u001b[1;3mAnswer: 1.086734862526058\u001b[0m\u001b[32;1m\u001b[1;3m\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Answer: 1.086734862526058'"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats 2**.12\")"
]
}
],
"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": "3.11.2"
},
"vscode": {
"interpreter": {
"hash": "e90c8aa204a57276aa905271aff2d11799d0acb3547adabc5892e639a5e45e34"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|