Spaces:
Sleeping
Sleeping
File size: 50,369 Bytes
eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 f7a1a4f eb87615 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "d312255a",
"metadata": {},
"source": [
" Project Structure\n",
"\n",
" tools.py – Provides auxiliary tools for the agent.\n",
" retriever.py – Implements retrieval functions to support knowledge access.\n",
" app.py – Integrates all components into a fully functional agent, which we’ll finalize in the last part of this unit."
]
},
{
"cell_type": "markdown",
"id": "fbbeaeb4",
"metadata": {},
"source": [
"### Building the Guestbook Tool"
]
},
{
"cell_type": "markdown",
"id": "5cd54389",
"metadata": {},
"source": [
"Step 1: Load and Prepare the Dataset"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "a36bf5b5",
"metadata": {},
"outputs": [],
"source": [
"from llama_index.core.schema import Document\n",
"import pandas as pd\n",
"#from huggingface_hub import hf_hub_download"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "62d4fbf9",
"metadata": {},
"outputs": [],
"source": [
"# Load the dataset\n",
"#guest_dataset = datasets.load_dataset(\"agents-course/unit3-invitees\", split=\"train\")\n",
"guest_dataset = pd.read_parquet(\"/home/cairo/code/alfred-agent-rag/data/train-00000-of-00001.parquet\")\n",
"\n",
"# Convert dataset entries into Document objects\n",
"docs = [\n",
" Document(\n",
" text=\"\\n\".join([\n",
" f\"Name: {guest_dataset['name'][i]}\",\n",
" f\"Relation: {guest_dataset['relation'][i]}\",\n",
" f\"Description: {guest_dataset['description'][i]}\",\n",
" f\"Email: {guest_dataset['email'][i]}\"\n",
" ]),\n",
" metadata={\"name\": guest_dataset['name'][i]}\n",
" )\n",
" for i in range(len(guest_dataset))\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "5e94a1f5",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.microsoft.datawrangler.viewer.v0+json": {
"columns": [
{
"name": "index",
"rawType": "int64",
"type": "integer"
},
{
"name": "name",
"rawType": "object",
"type": "string"
},
{
"name": "relation",
"rawType": "object",
"type": "string"
},
{
"name": "description",
"rawType": "object",
"type": "string"
},
{
"name": "email",
"rawType": "object",
"type": "string"
}
],
"conversionMethod": "pd.DataFrame",
"ref": "5b022186-8682-4d89-87c4-204710defe6d",
"rows": [
[
"0",
"Ada Lovelace",
"best friend",
"Lady Ada Lovelace is my best friend. She is an esteemed mathematician and friend. She is renowned for her pioneering work in mathematics and computing, often celebrated as the first computer programmer due to her work on Charles Babbage's Analytical Engine.",
"ada.lovelace@example.com"
],
[
"1",
"Dr. Nikola Tesla",
"old friend from university days",
"Dr. Nikola Tesla is an old friend from your university days. He's recently patented a new wireless energy transmission system and would be delighted to discuss it with you. Just remember he's passionate about pigeons, so that might make for good small talk.",
"nikola.tesla@gmail.com"
],
[
"2",
"Marie Curie",
"no relation",
"Marie Curie was a groundbreaking physicist and chemist, famous for her research on radioactivity.",
"marie.curie@example.com"
]
],
"shape": {
"columns": 4,
"rows": 3
}
},
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>name</th>\n",
" <th>relation</th>\n",
" <th>description</th>\n",
" <th>email</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ada Lovelace</td>\n",
" <td>best friend</td>\n",
" <td>Lady Ada Lovelace is my best friend. She is an...</td>\n",
" <td>ada.lovelace@example.com</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Dr. Nikola Tesla</td>\n",
" <td>old friend from university days</td>\n",
" <td>Dr. Nikola Tesla is an old friend from your un...</td>\n",
" <td>nikola.tesla@gmail.com</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Marie Curie</td>\n",
" <td>no relation</td>\n",
" <td>Marie Curie was a groundbreaking physicist and...</td>\n",
" <td>marie.curie@example.com</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" name relation \\\n",
"0 Ada Lovelace best friend \n",
"1 Dr. Nikola Tesla old friend from university days \n",
"2 Marie Curie no relation \n",
"\n",
" description email \n",
"0 Lady Ada Lovelace is my best friend. She is an... ada.lovelace@example.com \n",
"1 Dr. Nikola Tesla is an old friend from your un... nikola.tesla@gmail.com \n",
"2 Marie Curie was a groundbreaking physicist and... marie.curie@example.com "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"guest_dataset"
]
},
{
"cell_type": "markdown",
"id": "3354008a",
"metadata": {},
"source": [
"Step 2: Create the Retriever Tool\n",
"\n",
"Now, let’s create a custom tool that Alfred can use to search through our guest information."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "25f03ac1",
"metadata": {},
"outputs": [],
"source": [
"from llama_index.core.tools import FunctionTool\n",
"from llama_index.retrievers.bm25 import BM25Retriever\n",
"\n",
"bm25_retriever = BM25Retriever.from_defaults(nodes=docs)\n",
"\n",
"def get_guest_info_retriever(query: str) -> str:\n",
" \"\"\"Retrieves detailed information about gala guests based on their name or relation.\"\"\"\n",
" results = bm25_retriever.retrieve(query)\n",
" if results:\n",
" return \"\\n\\n\".join([doc.text for doc in results[:3]])\n",
" else:\n",
" return \"No matching guest information found.\"\n",
"\n",
"# Initialize the tool\n",
"guest_info_tool = FunctionTool.from_defaults(get_guest_info_retriever)"
]
},
{
"cell_type": "markdown",
"id": "5df9b39b",
"metadata": {},
"source": [
"Let’s understand this tool step-by-step.\n",
"\n",
"- The docstring helps the agent understand when and how to use this tool\n",
"- The type decorators define what parameters the tool expects (in this case, a search query)\n",
"- We’re using a BM25Retriever, which is a powerful text retrieval algorithm that doesn’t require embeddings\n",
"- The method processes the query and returns the most relevant guest information"
]
},
{
"cell_type": "markdown",
"id": "37217aaf",
"metadata": {},
"source": [
"Step 3: Integrate the Tool with Alfred"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "4a52e554",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "97f624e7ef9b4b0fb132bf0bce536477",
"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": [
"from huggingface_hub import login\n",
"\n",
"login()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "d1258afc",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Exception in callback Dispatcher.span.<locals>.wrapper.<locals>.handle_future_result(span_id='Workflow.run...-e3cd19dfc9c6', bound_args=<BoundArgumen...mory': None})>, instance=<llama_index....x76ae1634edb0>, context=<_contextvars...x76ae168519c0>)(<WorkflowHand...ompletions'\")>) at /home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py:274\n",
"handle: <Handle Dispatcher.span.<locals>.wrapper.<locals>.handle_future_result(span_id='Workflow.run...-e3cd19dfc9c6', bound_args=<BoundArgumen...mory': None})>, instance=<llama_index....x76ae1634edb0>, context=<_contextvars...x76ae168519c0>)(<WorkflowHand...ompletions'\")>) at /home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py:274>\n",
"Traceback (most recent call last):\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/context.py\", line 583, in _step_worker\n",
" new_ev = await instrumented_step(**kwargs)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py\", line 368, in async_wrapper\n",
" result = await func(*args, **kwargs)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/agent/workflow/multi_agent_workflow.py\", line 382, in run_agent_step\n",
" agent_output = await agent.take_step(\n",
" ^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/agent/workflow/react_agent.py\", line 101, in take_step\n",
" async for last_chat_response in response:\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/llms/huggingface_api/base.py\", line 429, in gen\n",
" async for chunk in await self._async_client.chat_completion(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py\", line 1032, in chat_completion\n",
" data = await self._inner_post(request_parameters, stream=stream)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py\", line 367, in _inner_post\n",
" raise error\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py\", line 353, in _inner_post\n",
" response.raise_for_status()\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/aiohttp/client_reqrep.py\", line 1093, in raise_for_status\n",
" raise ClientResponseError(\n",
"aiohttp.client_exceptions.ClientResponseError: 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'\n",
"\n",
"The above exception was the direct cause of the following exception:\n",
"\n",
"Traceback (most recent call last):\n",
" File \"/home/cairo/anaconda3/lib/python3.12/asyncio/events.py\", line 88, in _run\n",
" self._context.run(self._callback, *self._args)\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py\", line 286, in handle_future_result\n",
" raise exception\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/workflow.py\", line 394, in _run_workflow\n",
" raise exception_raised\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/context.py\", line 592, in _step_worker\n",
" raise WorkflowRuntimeError(\n",
"llama_index.core.workflow.errors.WorkflowRuntimeError: Error in step 'run_agent_step': 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'\n"
]
},
{
"ename": "WorkflowRuntimeError",
"evalue": "Error in step 'run_agent_step': 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mClientResponseError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/context.py:583\u001b[0m, in \u001b[0;36mContext._step_worker\u001b[0;34m(self, name, step, config, stepwise, verbose, checkpoint_callback, run_id, service_manager, dispatcher)\u001b[0m\n\u001b[1;32m 582\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 583\u001b[0m new_ev \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m instrumented_step(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 584\u001b[0m kwargs\u001b[38;5;241m.\u001b[39mclear()\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py:368\u001b[0m, in \u001b[0;36mDispatcher.span.<locals>.async_wrapper\u001b[0;34m(func, instance, args, kwargs)\u001b[0m\n\u001b[1;32m 367\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 368\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 369\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/agent/workflow/multi_agent_workflow.py:382\u001b[0m, in \u001b[0;36mAgentWorkflow.run_agent_step\u001b[0;34m(self, ctx, ev)\u001b[0m\n\u001b[1;32m 380\u001b[0m tools \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_tools(ev\u001b[38;5;241m.\u001b[39mcurrent_agent_name, user_msg_str \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 382\u001b[0m agent_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m agent\u001b[38;5;241m.\u001b[39mtake_step(\n\u001b[1;32m 383\u001b[0m ctx,\n\u001b[1;32m 384\u001b[0m ev\u001b[38;5;241m.\u001b[39minput,\n\u001b[1;32m 385\u001b[0m tools,\n\u001b[1;32m 386\u001b[0m memory,\n\u001b[1;32m 387\u001b[0m )\n\u001b[1;32m 389\u001b[0m ctx\u001b[38;5;241m.\u001b[39mwrite_event_to_stream(agent_output)\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/agent/workflow/react_agent.py:101\u001b[0m, in \u001b[0;36mReActAgent.take_step\u001b[0;34m(self, ctx, llm_input, tools, memory)\u001b[0m\n\u001b[1;32m 100\u001b[0m last_chat_response \u001b[38;5;241m=\u001b[39m ChatResponse(message\u001b[38;5;241m=\u001b[39mChatMessage())\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m last_chat_response \u001b[38;5;129;01min\u001b[39;00m response:\n\u001b[1;32m 102\u001b[0m raw \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 103\u001b[0m last_chat_response\u001b[38;5;241m.\u001b[39mraw\u001b[38;5;241m.\u001b[39mmodel_dump()\n\u001b[1;32m 104\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(last_chat_response\u001b[38;5;241m.\u001b[39mraw, BaseModel)\n\u001b[1;32m 105\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m last_chat_response\u001b[38;5;241m.\u001b[39mraw\n\u001b[1;32m 106\u001b[0m )\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/llms/huggingface_api/base.py:429\u001b[0m, in \u001b[0;36mHuggingFaceInferenceAPI.astream_chat.<locals>.gen\u001b[0;34m()\u001b[0m\n\u001b[1;32m 428\u001b[0m cur_index \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m\n\u001b[0;32m--> 429\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m chunk \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_async_client\u001b[38;5;241m.\u001b[39mchat_completion(\n\u001b[1;32m 430\u001b[0m messages\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_to_huggingface_messages(messages),\n\u001b[1;32m 431\u001b[0m stream\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 432\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs,\n\u001b[1;32m 433\u001b[0m ):\n\u001b[1;32m 434\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunk\u001b[38;5;241m.\u001b[39mchoices[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mfinish_reason \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py:1032\u001b[0m, in \u001b[0;36mAsyncInferenceClient.chat_completion\u001b[0;34m(self, messages, model, stream, frequency_penalty, logit_bias, logprobs, max_tokens, n, presence_penalty, response_format, seed, stop, stream_options, temperature, tool_choice, tool_prompt, tools, top_logprobs, top_p, extra_body)\u001b[0m\n\u001b[1;32m 1025\u001b[0m request_parameters \u001b[38;5;241m=\u001b[39m provider_helper\u001b[38;5;241m.\u001b[39mprepare_request(\n\u001b[1;32m 1026\u001b[0m inputs\u001b[38;5;241m=\u001b[39mmessages,\n\u001b[1;32m 1027\u001b[0m parameters\u001b[38;5;241m=\u001b[39mparameters,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1030\u001b[0m api_key\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtoken,\n\u001b[1;32m 1031\u001b[0m )\n\u001b[0;32m-> 1032\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_inner_post(request_parameters, stream\u001b[38;5;241m=\u001b[39mstream)\n\u001b[1;32m 1034\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py:367\u001b[0m, in \u001b[0;36mAsyncInferenceClient._inner_post\u001b[0;34m(self, request_parameters, stream)\u001b[0m\n\u001b[1;32m 366\u001b[0m \u001b[38;5;28;01mawait\u001b[39;00m session\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m--> 367\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m error\n\u001b[1;32m 368\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py:353\u001b[0m, in \u001b[0;36mAsyncInferenceClient._inner_post\u001b[0;34m(self, request_parameters, stream)\u001b[0m\n\u001b[1;32m 352\u001b[0m \u001b[38;5;28;01mpass\u001b[39;00m\n\u001b[0;32m--> 353\u001b[0m response\u001b[38;5;241m.\u001b[39mraise_for_status()\n\u001b[1;32m 354\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/aiohttp/client_reqrep.py:1093\u001b[0m, in \u001b[0;36mClientResponse.raise_for_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1092\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrelease()\n\u001b[0;32m-> 1093\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m ClientResponseError(\n\u001b[1;32m 1094\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequest_info,\n\u001b[1;32m 1095\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhistory,\n\u001b[1;32m 1096\u001b[0m status\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstatus,\n\u001b[1;32m 1097\u001b[0m message\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreason,\n\u001b[1;32m 1098\u001b[0m headers\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mheaders,\n\u001b[1;32m 1099\u001b[0m )\n",
"\u001b[0;31mClientResponseError\u001b[0m: 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'",
"\nThe above exception was the direct cause of the following exception:\n",
"\u001b[0;31mWorkflowRuntimeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[15], line 14\u001b[0m\n\u001b[1;32m 8\u001b[0m alfred \u001b[38;5;241m=\u001b[39m AgentWorkflow\u001b[38;5;241m.\u001b[39mfrom_tools_or_functions(\n\u001b[1;32m 9\u001b[0m [guest_info_tool],\n\u001b[1;32m 10\u001b[0m llm\u001b[38;5;241m=\u001b[39mllm,\n\u001b[1;32m 11\u001b[0m )\n\u001b[1;32m 13\u001b[0m \u001b[38;5;66;03m# Example query Alfred might receive during the gala\u001b[39;00m\n\u001b[0;32m---> 14\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m alfred\u001b[38;5;241m.\u001b[39mrun(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTell me about our guest named \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mLady Ada Lovelace\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 16\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m🎩 Alfred\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ms Response:\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 17\u001b[0m \u001b[38;5;28mprint\u001b[39m(response)\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/workflow.py:394\u001b[0m, in \u001b[0;36mWorkflow.run.<locals>._run_workflow\u001b[0;34m()\u001b[0m\n\u001b[1;32m 390\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m exception_raised:\n\u001b[1;32m 391\u001b[0m \u001b[38;5;66;03m# cancel the stream\u001b[39;00m\n\u001b[1;32m 392\u001b[0m ctx\u001b[38;5;241m.\u001b[39mwrite_event_to_stream(StopEvent())\n\u001b[0;32m--> 394\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exception_raised\n\u001b[1;32m 396\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m we_done:\n\u001b[1;32m 397\u001b[0m \u001b[38;5;66;03m# cancel the stream\u001b[39;00m\n\u001b[1;32m 398\u001b[0m ctx\u001b[38;5;241m.\u001b[39mwrite_event_to_stream(StopEvent())\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/context.py:592\u001b[0m, in \u001b[0;36mContext._step_worker\u001b[0;34m(self, name, step, config, stepwise, verbose, checkpoint_callback, run_id, service_manager, dispatcher)\u001b[0m\n\u001b[1;32m 590\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 591\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m config\u001b[38;5;241m.\u001b[39mretry_policy \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 592\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m WorkflowRuntimeError(\n\u001b[1;32m 593\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mError in step \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m!s}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 594\u001b[0m ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 596\u001b[0m delay \u001b[38;5;241m=\u001b[39m config\u001b[38;5;241m.\u001b[39mretry_policy\u001b[38;5;241m.\u001b[39mnext(\n\u001b[1;32m 597\u001b[0m retry_start_at \u001b[38;5;241m+\u001b[39m time\u001b[38;5;241m.\u001b[39mtime(), attempts, e\n\u001b[1;32m 598\u001b[0m )\n\u001b[1;32m 599\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m delay \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 600\u001b[0m \u001b[38;5;66;03m# We're done retrying\u001b[39;00m\n",
"\u001b[0;31mWorkflowRuntimeError\u001b[0m: Error in step 'run_agent_step': 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'"
]
}
],
"source": [
"from llama_index.core.agent.workflow import AgentWorkflow\n",
"from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n",
"\n",
"# Initialize the Hugging Face model\n",
"llm = HuggingFaceInferenceAPI(model_name=\"Qwen/Qwen2.5-Coder-32B-Instruct\")\n",
"\n",
"# Create Alfred, our gala agent, with the guest info tool\n",
"alfred = AgentWorkflow.from_tools_or_functions(\n",
" [guest_info_tool],\n",
" llm=llm,\n",
")\n",
"\n",
"# Example query Alfred might receive during the gala\n",
"response = await alfred.run(\"Tell me about our guest named 'Lady Ada Lovelace'.\")\n",
"\n",
"print(\"🎩 Alfred's Response:\")\n",
"print(response)"
]
},
{
"cell_type": "markdown",
"id": "8ce1210b",
"metadata": {},
"source": [
"What’s happening in this final step:\n",
"\n",
"- We initialize a Hugging Face model using the HuggingFaceInferenceAPI class\n",
"- We create our agent (Alfred) as a AgentWorkflow, including the tool we just created\n",
"- We ask Alfred to retrieve information about a guest named “Lady Ada Lovelace”"
]
},
{
"cell_type": "markdown",
"id": "a83f4bc6",
"metadata": {},
"source": [
"### Building and Integrating Tools for Your Agent"
]
},
{
"cell_type": "markdown",
"id": "6dee00aa",
"metadata": {},
"source": [
"Give Your Agent Access to the Web"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "adaac02f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"He served two terms as the president of Brazil from 2003 to 2010 and left office with an approval rating of 80%. Brazilian president-elect for the leftist Workers Party (PT) Luiz Inacio Lula da ...\n"
]
}
],
"source": [
"from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec\n",
"from llama_index.core.tools import FunctionTool\n",
"\n",
"# Initialize the DuckDuckGo search tool\n",
"tool_spec = DuckDuckGoSearchToolSpec()\n",
"\n",
"search_tool = FunctionTool.from_defaults(tool_spec.duckduckgo_full_search)\n",
"# Example usage\n",
"response = search_tool(\"Who's the current President of Brazil?\")\n",
"print(response.raw_output[-1]['body'])"
]
},
{
"cell_type": "markdown",
"id": "d43f238a",
"metadata": {},
"source": [
"Creating a Custom Tool for Weather Information to Schedule the Fireworks"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "1c59be40",
"metadata": {},
"outputs": [],
"source": [
"import random\n",
"from llama_index.core.tools import FunctionTool\n",
"\n",
"def get_weather_info(location: str) -> str:\n",
" \"\"\"Fetches dummy weather information for a given location.\"\"\"\n",
" # Dummy weather data\n",
" weather_conditions = [\n",
" {\"condition\": \"Rainy\", \"temp_c\": 15},\n",
" {\"condition\": \"Clear\", \"temp_c\": 25},\n",
" {\"condition\": \"Windy\", \"temp_c\": 20}\n",
" ]\n",
" # Randomly select a weather condition\n",
" data = random.choice(weather_conditions)\n",
" return f\"Weather in {location}: {data['condition']}, {data['temp_c']}°C\"\n",
"\n",
"# Initialize the tool\n",
"weather_info_tool = FunctionTool.from_defaults(get_weather_info)"
]
},
{
"cell_type": "markdown",
"id": "98b670b7",
"metadata": {},
"source": [
"Creating a Hub Stats Tool for Influential AI Builders"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "82ce0fa8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The most downloaded model by facebook is facebook/esmfold_v1 with 24,213,202 downloads.\n"
]
}
],
"source": [
"import random\n",
"from llama_index.core.tools import FunctionTool\n",
"from huggingface_hub import list_models\n",
"\n",
"def get_hub_stats(author: str) -> str:\n",
" \"\"\"Fetches the most downloaded model from a specific author on the Hugging Face Hub.\"\"\"\n",
" try:\n",
" # List models from the specified author, sorted by downloads\n",
" models = list(list_models(author=author, sort=\"downloads\", direction=-1, limit=1))\n",
"\n",
" if models:\n",
" model = models[0]\n",
" return f\"The most downloaded model by {author} is {model.id} with {model.downloads:,} downloads.\"\n",
" else:\n",
" return f\"No models found for author {author}.\"\n",
" except Exception as e:\n",
" return f\"Error fetching models for {author}: {str(e)}\"\n",
"\n",
"# Initialize the tool\n",
"hub_stats_tool = FunctionTool.from_defaults(get_hub_stats)\n",
"\n",
"# Example usage\n",
"print(hub_stats_tool(\"facebook\")) # Example: Get the most downloaded model by Facebook"
]
},
{
"cell_type": "markdown",
"id": "6722948c",
"metadata": {},
"source": [
"Integrating Tools with Alfred"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "cea842d2",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Exception in callback Dispatcher.span.<locals>.wrapper.<locals>.handle_future_result(span_id='Workflow.run...-55bd0ee16e6f', bound_args=<BoundArgumen...mory': None})>, instance=<llama_index....x76ae0f7cddf0>, context=<_contextvars...x76ae50734e40>)(<WorkflowHand...ompletions'\")>) at /home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py:274\n",
"handle: <Handle Dispatcher.span.<locals>.wrapper.<locals>.handle_future_result(span_id='Workflow.run...-55bd0ee16e6f', bound_args=<BoundArgumen...mory': None})>, instance=<llama_index....x76ae0f7cddf0>, context=<_contextvars...x76ae50734e40>)(<WorkflowHand...ompletions'\")>) at /home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py:274>\n",
"Traceback (most recent call last):\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/context.py\", line 583, in _step_worker\n",
" new_ev = await instrumented_step(**kwargs)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py\", line 368, in async_wrapper\n",
" result = await func(*args, **kwargs)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/agent/workflow/multi_agent_workflow.py\", line 382, in run_agent_step\n",
" agent_output = await agent.take_step(\n",
" ^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/agent/workflow/react_agent.py\", line 101, in take_step\n",
" async for last_chat_response in response:\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/llms/huggingface_api/base.py\", line 429, in gen\n",
" async for chunk in await self._async_client.chat_completion(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py\", line 1032, in chat_completion\n",
" data = await self._inner_post(request_parameters, stream=stream)\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py\", line 367, in _inner_post\n",
" raise error\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py\", line 353, in _inner_post\n",
" response.raise_for_status()\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/aiohttp/client_reqrep.py\", line 1093, in raise_for_status\n",
" raise ClientResponseError(\n",
"aiohttp.client_exceptions.ClientResponseError: 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'\n",
"\n",
"The above exception was the direct cause of the following exception:\n",
"\n",
"Traceback (most recent call last):\n",
" File \"/home/cairo/anaconda3/lib/python3.12/asyncio/events.py\", line 88, in _run\n",
" self._context.run(self._callback, *self._args)\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py\", line 286, in handle_future_result\n",
" raise exception\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/workflow.py\", line 394, in _run_workflow\n",
" raise exception_raised\n",
" File \"/home/cairo/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/context.py\", line 592, in _step_worker\n",
" raise WorkflowRuntimeError(\n",
"llama_index.core.workflow.errors.WorkflowRuntimeError: Error in step 'run_agent_step': 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'\n"
]
},
{
"ename": "WorkflowRuntimeError",
"evalue": "Error in step 'run_agent_step': 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mClientResponseError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/context.py:583\u001b[0m, in \u001b[0;36mContext._step_worker\u001b[0;34m(self, name, step, config, stepwise, verbose, checkpoint_callback, run_id, service_manager, dispatcher)\u001b[0m\n\u001b[1;32m 582\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 583\u001b[0m new_ev \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m instrumented_step(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 584\u001b[0m kwargs\u001b[38;5;241m.\u001b[39mclear()\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/instrumentation/dispatcher.py:368\u001b[0m, in \u001b[0;36mDispatcher.span.<locals>.async_wrapper\u001b[0;34m(func, instance, args, kwargs)\u001b[0m\n\u001b[1;32m 367\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 368\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 369\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/agent/workflow/multi_agent_workflow.py:382\u001b[0m, in \u001b[0;36mAgentWorkflow.run_agent_step\u001b[0;34m(self, ctx, ev)\u001b[0m\n\u001b[1;32m 380\u001b[0m tools \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_tools(ev\u001b[38;5;241m.\u001b[39mcurrent_agent_name, user_msg_str \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 382\u001b[0m agent_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m agent\u001b[38;5;241m.\u001b[39mtake_step(\n\u001b[1;32m 383\u001b[0m ctx,\n\u001b[1;32m 384\u001b[0m ev\u001b[38;5;241m.\u001b[39minput,\n\u001b[1;32m 385\u001b[0m tools,\n\u001b[1;32m 386\u001b[0m memory,\n\u001b[1;32m 387\u001b[0m )\n\u001b[1;32m 389\u001b[0m ctx\u001b[38;5;241m.\u001b[39mwrite_event_to_stream(agent_output)\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/agent/workflow/react_agent.py:101\u001b[0m, in \u001b[0;36mReActAgent.take_step\u001b[0;34m(self, ctx, llm_input, tools, memory)\u001b[0m\n\u001b[1;32m 100\u001b[0m last_chat_response \u001b[38;5;241m=\u001b[39m ChatResponse(message\u001b[38;5;241m=\u001b[39mChatMessage())\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m last_chat_response \u001b[38;5;129;01min\u001b[39;00m response:\n\u001b[1;32m 102\u001b[0m raw \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 103\u001b[0m last_chat_response\u001b[38;5;241m.\u001b[39mraw\u001b[38;5;241m.\u001b[39mmodel_dump()\n\u001b[1;32m 104\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(last_chat_response\u001b[38;5;241m.\u001b[39mraw, BaseModel)\n\u001b[1;32m 105\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m last_chat_response\u001b[38;5;241m.\u001b[39mraw\n\u001b[1;32m 106\u001b[0m )\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/llms/huggingface_api/base.py:429\u001b[0m, in \u001b[0;36mHuggingFaceInferenceAPI.astream_chat.<locals>.gen\u001b[0;34m()\u001b[0m\n\u001b[1;32m 428\u001b[0m cur_index \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m\n\u001b[0;32m--> 429\u001b[0m \u001b[38;5;28;01masync\u001b[39;00m \u001b[38;5;28;01mfor\u001b[39;00m chunk \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_async_client\u001b[38;5;241m.\u001b[39mchat_completion(\n\u001b[1;32m 430\u001b[0m messages\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_to_huggingface_messages(messages),\n\u001b[1;32m 431\u001b[0m stream\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 432\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs,\n\u001b[1;32m 433\u001b[0m ):\n\u001b[1;32m 434\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunk\u001b[38;5;241m.\u001b[39mchoices[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mfinish_reason \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py:1032\u001b[0m, in \u001b[0;36mAsyncInferenceClient.chat_completion\u001b[0;34m(self, messages, model, stream, frequency_penalty, logit_bias, logprobs, max_tokens, n, presence_penalty, response_format, seed, stop, stream_options, temperature, tool_choice, tool_prompt, tools, top_logprobs, top_p, extra_body)\u001b[0m\n\u001b[1;32m 1025\u001b[0m request_parameters \u001b[38;5;241m=\u001b[39m provider_helper\u001b[38;5;241m.\u001b[39mprepare_request(\n\u001b[1;32m 1026\u001b[0m inputs\u001b[38;5;241m=\u001b[39mmessages,\n\u001b[1;32m 1027\u001b[0m parameters\u001b[38;5;241m=\u001b[39mparameters,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1030\u001b[0m api_key\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtoken,\n\u001b[1;32m 1031\u001b[0m )\n\u001b[0;32m-> 1032\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_inner_post(request_parameters, stream\u001b[38;5;241m=\u001b[39mstream)\n\u001b[1;32m 1034\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py:367\u001b[0m, in \u001b[0;36mAsyncInferenceClient._inner_post\u001b[0;34m(self, request_parameters, stream)\u001b[0m\n\u001b[1;32m 366\u001b[0m \u001b[38;5;28;01mawait\u001b[39;00m session\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m--> 367\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m error\n\u001b[1;32m 368\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/huggingface_hub/inference/_generated/_async_client.py:353\u001b[0m, in \u001b[0;36mAsyncInferenceClient._inner_post\u001b[0;34m(self, request_parameters, stream)\u001b[0m\n\u001b[1;32m 352\u001b[0m \u001b[38;5;28;01mpass\u001b[39;00m\n\u001b[0;32m--> 353\u001b[0m response\u001b[38;5;241m.\u001b[39mraise_for_status()\n\u001b[1;32m 354\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream:\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/aiohttp/client_reqrep.py:1093\u001b[0m, in \u001b[0;36mClientResponse.raise_for_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1092\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrelease()\n\u001b[0;32m-> 1093\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m ClientResponseError(\n\u001b[1;32m 1094\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequest_info,\n\u001b[1;32m 1095\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhistory,\n\u001b[1;32m 1096\u001b[0m status\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstatus,\n\u001b[1;32m 1097\u001b[0m message\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreason,\n\u001b[1;32m 1098\u001b[0m headers\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mheaders,\n\u001b[1;32m 1099\u001b[0m )\n",
"\u001b[0;31mClientResponseError\u001b[0m: 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'",
"\nThe above exception was the direct cause of the following exception:\n",
"\u001b[0;31mWorkflowRuntimeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[21], line 13\u001b[0m\n\u001b[1;32m 7\u001b[0m alfred \u001b[38;5;241m=\u001b[39m AgentWorkflow\u001b[38;5;241m.\u001b[39mfrom_tools_or_functions(\n\u001b[1;32m 8\u001b[0m [search_tool, weather_info_tool, hub_stats_tool],\n\u001b[1;32m 9\u001b[0m llm\u001b[38;5;241m=\u001b[39mllm\n\u001b[1;32m 10\u001b[0m )\n\u001b[1;32m 12\u001b[0m \u001b[38;5;66;03m# Example query Alfred might receive during the gala\u001b[39;00m\n\u001b[0;32m---> 13\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mawait\u001b[39;00m alfred\u001b[38;5;241m.\u001b[39mrun(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWhat is Facebook and what\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ms their most popular model?\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m🎩 Alfred\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ms Response:\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 16\u001b[0m \u001b[38;5;28mprint\u001b[39m(response)\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/workflow.py:394\u001b[0m, in \u001b[0;36mWorkflow.run.<locals>._run_workflow\u001b[0;34m()\u001b[0m\n\u001b[1;32m 390\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m exception_raised:\n\u001b[1;32m 391\u001b[0m \u001b[38;5;66;03m# cancel the stream\u001b[39;00m\n\u001b[1;32m 392\u001b[0m ctx\u001b[38;5;241m.\u001b[39mwrite_event_to_stream(StopEvent())\n\u001b[0;32m--> 394\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m exception_raised\n\u001b[1;32m 396\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m we_done:\n\u001b[1;32m 397\u001b[0m \u001b[38;5;66;03m# cancel the stream\u001b[39;00m\n\u001b[1;32m 398\u001b[0m ctx\u001b[38;5;241m.\u001b[39mwrite_event_to_stream(StopEvent())\n",
"File \u001b[0;32m~/anaconda3/lib/python3.12/site-packages/llama_index/core/workflow/context.py:592\u001b[0m, in \u001b[0;36mContext._step_worker\u001b[0;34m(self, name, step, config, stepwise, verbose, checkpoint_callback, run_id, service_manager, dispatcher)\u001b[0m\n\u001b[1;32m 590\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 591\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m config\u001b[38;5;241m.\u001b[39mretry_policy \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 592\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m WorkflowRuntimeError(\n\u001b[1;32m 593\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mError in step \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m!s}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 594\u001b[0m ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 596\u001b[0m delay \u001b[38;5;241m=\u001b[39m config\u001b[38;5;241m.\u001b[39mretry_policy\u001b[38;5;241m.\u001b[39mnext(\n\u001b[1;32m 597\u001b[0m retry_start_at \u001b[38;5;241m+\u001b[39m time\u001b[38;5;241m.\u001b[39mtime(), attempts, e\n\u001b[1;32m 598\u001b[0m )\n\u001b[1;32m 599\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m delay \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 600\u001b[0m \u001b[38;5;66;03m# We're done retrying\u001b[39;00m\n",
"\u001b[0;31mWorkflowRuntimeError\u001b[0m: Error in step 'run_agent_step': 402, message='Payment Required', url='https://router.huggingface.co/hf-inference/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions'"
]
}
],
"source": [
"from llama_index.core.agent.workflow import AgentWorkflow\n",
"from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n",
"\n",
"# Initialize the Hugging Face model\n",
"llm = HuggingFaceInferenceAPI(model_name=\"Qwen/Qwen2.5-Coder-32B-Instruct\")\n",
"# Create Alfred with all the tools\n",
"alfred = AgentWorkflow.from_tools_or_functions(\n",
" [search_tool, weather_info_tool, hub_stats_tool],\n",
" llm=llm\n",
")\n",
"\n",
"# Example query Alfred might receive during the gala\n",
"response = await alfred.run(\"What is Facebook and what's their most popular model?\")\n",
"\n",
"print(\"🎩 Alfred's Response:\")\n",
"print(response)"
]
},
{
"cell_type": "markdown",
"id": "9d85b055",
"metadata": {},
"source": [
"Conclusion\n",
"\n",
"By integrating these tools, Alfred is now equipped to handle a variety of tasks, from web searches to weather updates and model statistics. This ensures he remains the most informed and engaging host at the gala."
]
},
{
"cell_type": "markdown",
"id": "eac6666b",
"metadata": {},
"source": [
"### Creating Your Gala Agent"
]
},
{
"cell_type": "markdown",
"id": "33897d2c",
"metadata": {},
"source": [
"https://huggingface.co/learn/agents-course/unit3/agentic-rag/agent?agents-frameworks=llama-index"
]
},
{
"cell_type": "markdown",
"id": "a9ba3df0",
"metadata": {},
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|