File size: 33,693 Bytes
a392ebe |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"from langchain_pinecone import PineconeVectorStore\n",
"from langchain_google_genai import GoogleGenerativeAIEmbeddings\n",
"from langchain_google_genai import ChatGoogleGenerativeAI\n",
"from langchain.chains import RetrievalQA\n",
"from langchain.document_loaders import PyPDFLoader\n",
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"from langchain_openai import OpenAIEmbeddings\n",
"# from sentence_transformers import SentenceTransformer\n",
"from langchain_google_genai import GoogleGenerativeAIEmbeddings\n",
"\n",
"from langchain_google_genai import ChatGoogleGenerativeAI\n",
"from langchain_pinecone import PineconeVectorStore\n",
"from langchain.chains.question_answering import load_qa_chain\n",
"from langchain import PromptTemplate\n",
"from uuid import uuid4\n",
"from langchain_core.documents import Document\n",
"import getpass\n",
"import os\n",
"import google.generativeai as genai\n",
"from langchain.document_loaders import PyPDFLoader"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Importing the documents needs to be loaded in Vector Database\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"base_dir = os.getcwd()\n",
"file_name = \"Reliance.pdf\"\n",
"file_path = os.path.join(base_dir,file_name )\n",
"\n",
"def create_chunks(doc_to_chunk):\n",
" text_splitter = RecursiveCharacterTextSplitter(\n",
" chunk_size=500,\n",
" chunk_overlap=100,\n",
" length_function=len\n",
" )\n",
" return text_splitter.split_documents(doc_to_chunk)\n",
"\n",
"def load_pdf(path):\n",
" loader = PyPDFLoader(path)\n",
" return loader.load()\n",
"\n",
"def load_chunk_file(path):\n",
" doc = load_pdf(path)\n",
" return create_chunks(doc)\n",
"\n",
"chunks = load_chunk_file(file_path)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Loading the document into Vector Database"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['0c2ac5d0-8ee3-4b7e-8846-2918154f1eb8',\n",
" 'aa5fc10a-7127-4f21-889f-28f4416f476b',\n",
" '1642ce19-52a7-47ba-b9f5-571427234765',\n",
" 'ab61277d-6c32-4c2b-9f16-462e1d91920b',\n",
" 'df66c977-49f0-4f0c-b15d-399bae4cd22f',\n",
" '2a7a3525-6032-4c9d-8841-8ae7ebf56850',\n",
" 'b43a8564-a85b-4119-b58d-575e45a42165',\n",
" '30ab4aba-7d2c-47b4-834c-59bc92f9ed74',\n",
" '623f618b-a7f2-4095-b115-8b410ea9eb9e',\n",
" 'c2ea7159-4de7-448e-aa69-1e9accff1850',\n",
" '5869be42-c13a-4370-bc3b-2007d09cb7bc',\n",
" 'e00749b7-b2a5-42f1-a16e-d6ed85849c91',\n",
" '3673b32b-14b0-479d-8791-12f22bd90ff8',\n",
" '919227ed-2b17-4b9c-a7d8-1de38c14d626',\n",
" 'e9af81a2-0753-4788-993d-b59cc2cada2c',\n",
" '872a0391-ad12-4eb5-baa5-fe6fe8ee659b',\n",
" '744cf651-e62d-4739-9531-a0dc8e4f1f07',\n",
" '645c60da-b40a-453a-b18f-4c06d314e221',\n",
" 'b4f052a5-475c-43ab-8252-b28793ccd5c4',\n",
" 'c40aea8d-d4a2-4af4-9054-97613d23e4a0',\n",
" 'ea57becd-f898-47bb-9ca5-9fe15cb20454',\n",
" 'd6b72ea5-eb18-47c0-8662-d4d211dfd10b',\n",
" '83cea095-1704-46b1-85bd-79888fdf7d86',\n",
" '189bdbb1-a31a-4e66-b5e8-59b1b4655398',\n",
" 'a34b2aed-81a9-4326-9ccb-1e3fcf3873a9',\n",
" '00180119-f5cf-41de-84b7-610b701383bf',\n",
" '53f9ecc4-679c-47f8-9627-f2f886ef42de',\n",
" 'be45dc55-d9ff-470c-9393-6cf96dc73c32',\n",
" '63d75c0b-020e-4f72-9cae-3f2e4e82b228',\n",
" 'c59b133d-c867-45be-963b-cb8f5df49802',\n",
" 'bdf3cd50-4d60-4395-95a4-cde7a5e32f81',\n",
" '29de5ec1-9910-45bd-8e1e-df565254ef73',\n",
" '92a57d8c-84d2-4c73-9b40-682ed42e3998',\n",
" '9954113f-64d7-4077-9097-1a64f2e6f096',\n",
" 'eced5907-1ec7-45c2-9f1f-036c4fb78d6c',\n",
" '2405c386-79f3-4337-8c40-db8b84bfedc2',\n",
" '144fde6f-710b-4e1b-ac2f-6f3af969375a',\n",
" '4929fd1e-f559-479b-974e-250a2bf2ac56',\n",
" 'a4671288-21f3-4210-adcc-82daba519c62',\n",
" '33219ac4-e102-4fdd-b453-8d911b6a0814',\n",
" '4945640d-595c-46b8-87dc-87182501d9bf',\n",
" '0f85529e-11e6-4120-b50c-7054b817d3aa',\n",
" 'af1e1941-2904-40f5-aabe-ae1f7901bc5a',\n",
" '3cca1def-8a18-4267-b04d-23fceab5faed',\n",
" '9a53a228-f505-46db-95cd-dba9f40663bf',\n",
" '0a5d4944-1a01-40f4-b557-330ed2e8a18a',\n",
" 'cd161a04-1ce2-406d-a43b-ea7efea0370c',\n",
" '4eddd6ce-b482-4466-9465-cda8c7c67d29',\n",
" '584a0ea1-20cd-46cb-b127-970449862997',\n",
" '4edbba63-e967-4864-be57-c1e195128021',\n",
" 'ed281465-721c-470a-8ae7-21cfcb8af944',\n",
" '143f581d-b09b-4afc-8d9c-eadb1c98e7bb',\n",
" 'ec300ec2-5e3a-49fb-a109-00ff9386fd51',\n",
" 'b233a907-d9b6-4d42-94cc-19013ca2ee22',\n",
" '96f478ba-d59c-4cec-b69b-f8153819c64b',\n",
" 'dee19024-32c4-437c-814f-65435855bc7d',\n",
" '35efa2fe-bfec-41b0-af06-c1421b618dfb',\n",
" 'a7f09dd4-0808-431f-9962-7781cec5d768',\n",
" '7dd9eb93-154f-49af-97cf-3acb30fe39f1',\n",
" 'ffb9ef79-92e3-4c24-b70d-717f9bb486ab',\n",
" 'd4d0fc60-eece-4cde-aebd-2d2eacb1a175',\n",
" '89a3c27b-332f-4598-b662-88460ebfea84',\n",
" '8b853629-e6a8-482c-9d6a-8100c8e11be1',\n",
" 'a16cbe9e-78a5-4998-9022-43941f5651ef',\n",
" '43198ea2-2cb6-41f9-968e-71aef1aa3092',\n",
" '201e741d-a2da-4f1c-bc0e-413cc264e15f',\n",
" '122b9da9-d278-4858-859f-a343d989c755',\n",
" 'e62610e0-fce8-484a-bb3f-c0acba538a20',\n",
" 'e33ce6e0-fa91-4ea2-895a-c5dfc57dda15',\n",
" '2feabd6a-0a10-4567-a00d-a175165795b7',\n",
" 'e2f71af2-c2f9-4949-825b-e9da02d33f56',\n",
" '51959195-4c81-4b4b-a928-91ae25c32cb7',\n",
" '40cbbbaa-0241-4ec7-8672-d9b4eec0b5e3',\n",
" 'e06501b9-6e70-4b46-a206-2d1bdbf8323a',\n",
" '09624885-5fd8-46e8-a984-5415088a2652',\n",
" 'ef2e77e7-a139-4d15-9415-c010cc348a58',\n",
" 'e0fde1e5-907b-4fd4-b7b4-76996ad804af',\n",
" '66658ffb-4311-4de6-8391-c58aa0539449',\n",
" '84bd7262-d5df-4b18-ae3f-0d16cfc9a305',\n",
" 'b6a1b8ca-d1b8-43ff-b58c-c3bd051cd6d1',\n",
" '4800b8ed-2d70-4251-a6b2-f3423c6179a0',\n",
" 'aecb53ac-b605-408f-896f-1969586ec320',\n",
" '6e67366e-95da-4cae-8efa-59f8a72de036',\n",
" '2b15f99a-f5db-4501-ada1-13b5e3608e7a',\n",
" 'cccc222d-79b9-48e0-b1ec-204e98eb57e3',\n",
" 'f56aeeb8-f883-4bf8-b7ba-5d7fa5c210cb',\n",
" '2aaa5c36-d138-48b3-bc79-5462a0b1d9f0',\n",
" '9bc822df-5102-4600-becc-344ac58ff8f1',\n",
" '485a6eeb-f603-4d68-88e5-17cb88385eee',\n",
" '9e3b0eb4-067c-4895-97e6-a4940e30c6e5',\n",
" 'd9ec6744-d756-4c70-8b22-a5d0ea1bc7f9',\n",
" '8dac6d17-163a-4186-bf2e-13c8a9d2c68b',\n",
" '6afeca7a-019f-44ed-99bc-4faaec6cea9d',\n",
" 'f22359e9-7fb8-465e-90da-9c31b2bc7044',\n",
" '10aefd98-f3cd-4a30-8153-ce4be52baa2e',\n",
" '444d3318-4b08-45f7-8706-26493b2ddd52',\n",
" '8247b43f-1ceb-45c3-95fa-96e33ce3f0ae',\n",
" '1dbd882d-fe93-4e43-b101-a2170b560645',\n",
" '661945bd-82da-4221-bd8c-189b28b8dd3c',\n",
" '0b406988-2b45-4c48-bfab-b6174b46cdbc',\n",
" 'fbd11f62-3d13-409b-9faa-887a305d6024',\n",
" '3d618eb3-d955-41eb-b0e8-e653b4955e4b',\n",
" 'b8ef62cf-2182-43cd-8035-d49efe89fc53',\n",
" '34b81bfe-4a05-40d2-b97f-1e760a4f9470',\n",
" '24e1dc11-8d7e-49ce-a68e-29424199f219',\n",
" '24ee8198-f1be-462c-a62b-bf50daa46456',\n",
" 'c7c11b34-7df2-477f-86ac-33499992c4c3',\n",
" 'bae84011-8d52-4eea-ade4-7e55fd9b6834',\n",
" '733a2c66-5857-4d0a-96fa-c14682d6ebfe',\n",
" '5ee5902e-e091-4295-b101-cf1550a474c0',\n",
" '417946bf-4757-499a-b6c9-1ff5c80e137f',\n",
" '4f7eeca1-5cab-42f8-a5cc-d42646c05692',\n",
" '1fcbfff3-c90a-403f-8253-9646b874fdae',\n",
" 'dde8af51-308b-44cc-923f-a0f14c7fc82c',\n",
" 'bd1410b3-a00d-40ae-99c1-232838ec2ca3',\n",
" '63f4b459-156c-4a26-97a5-f34f098b0b6a',\n",
" 'c3b75842-5879-4ff8-904d-045fe7918db6',\n",
" 'acdda0ae-50d7-4e6b-afda-7442052af76e',\n",
" 'de80e5c5-2dea-463b-85b5-2a43389b103b',\n",
" '0a1f41f7-b34c-47ad-9e11-1d01aad61f06',\n",
" '592a5b78-2901-4343-96c0-ed1cd08c218a',\n",
" '26e3415c-5919-4734-9236-018d5ae772e2']"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Import the necessary modules\n",
"from langchain_pinecone import PineconeVectorStore\n",
"from langchain_core.documents import Document\n",
"from langchain_google_genai import GoogleGenerativeAIEmbeddings\n",
"from dotenv import load_dotenv\n",
"import os\n",
"from pinecone import Pinecone, ServerlessSpec\n",
"load_dotenv()\n",
"\n",
"# Initialize the Pinecone vector store\n",
"index_name = \"test-index\"\n",
"pc = Pinecone(\n",
" api_key=os.environ[\"PINECONE_API_KEY\"]) \n",
"if index_name not in pc.list_indexes().names():\n",
" pc.create_index(\n",
" name=index_name,\n",
" dimension=768,\n",
" metric='cosine', \n",
" spec=ServerlessSpec(\n",
" cloud='aws', # Specify your preferred cloud provider\n",
" region='us-east-1' # Specify your preferred region\n",
" )\n",
" )\n",
"\n",
"embeddings = GoogleGenerativeAIEmbeddings(model=\"models/embedding-001\", google_api_key=os.environ[\"GOOGLE_API_KEY\"])\n",
"vectorstore = PineconeVectorStore(index_name=index_name, embedding=embeddings)\n",
"uuids = [str(uuid4()) for _ in range(len(chunks))]\n",
"vectorstore.add_documents(documents=chunks, ids=uuids)\n",
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create questions for the performance evaluation of RAG"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'llama_index.embeddings.gemini'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[8], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mllama_index\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mllms\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgemini\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Gemini\n\u001b[1;32m----> 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mllama_index\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01membeddings\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgemini\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m GeminiEmbeddings\n",
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'llama_index.embeddings.gemini'"
]
}
],
"source": [
"from llama_index.llms.gemini import Gemini\n",
"from llama_index.embeddings.gemini import GeminiEmbeddings\n"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Unexpected exception formatting exception. Falling back to standard exception\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Traceback (most recent call last):\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\IPython\\core\\interactiveshell.py\", line 3508, in run_code\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Temp\\ipykernel_38684\\3905429830.py\", line 3, in <module>\n",
" resp = Gemini(Model = \"gemini-1.5-flash\").complete(\"Write a poem about a magic backpack\")\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\llms\\gemini\\base.py\", line 147, in __init__\n",
" model_meta = genai.get_model(model)\n",
" ^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\google\\generativeai\\models.py\", line 55, in get_model\n",
" elif name.startswith(\"tunedModels/\"):\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\google\\generativeai\\types\\model_types.py\", line 357, in make_model_name\n",
"TypeError: Invalid input type. Expected one of the following types: `str`, `Model`, or `TunedModel`.\n",
"\n",
"During handling of the above exception, another exception occurred:\n",
"\n",
"Traceback (most recent call last):\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\IPython\\core\\interactiveshell.py\", line 2105, in showtraceback\n",
" stb = self.InteractiveTB.structured_traceback(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\IPython\\core\\ultratb.py\", line 1396, in structured_traceback\n",
" return FormattedTB.structured_traceback(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\IPython\\core\\ultratb.py\", line 1287, in structured_traceback\n",
" return VerboseTB.structured_traceback(\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\IPython\\core\\ultratb.py\", line 1140, in structured_traceback\n",
" formatted_exception = self.format_exception_as_a_whole(etype, evalue, etb, number_of_lines_of_context,\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\IPython\\core\\ultratb.py\", line 1055, in format_exception_as_a_whole\n",
" frames.append(self.format_record(record))\n",
" ^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\IPython\\core\\ultratb.py\", line 955, in format_record\n",
" frame_info.lines, Colors, self.has_colors, lvals\n",
" ^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\IPython\\core\\ultratb.py\", line 778, in lines\n",
" return self._sd.lines\n",
" ^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\stack_data\\utils.py\", line 145, in cached_property_wrapper\n",
" value = obj.__dict__[self.func.__name__] = self.func(obj)\n",
" ^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\stack_data\\core.py\", line 734, in lines\n",
" pieces = self.included_pieces\n",
" ^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\stack_data\\utils.py\", line 145, in cached_property_wrapper\n",
" value = obj.__dict__[self.func.__name__] = self.func(obj)\n",
" ^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\stack_data\\core.py\", line 681, in included_pieces\n",
" pos = scope_pieces.index(self.executing_piece)\n",
" ^^^^^^^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\stack_data\\utils.py\", line 145, in cached_property_wrapper\n",
" value = obj.__dict__[self.func.__name__] = self.func(obj)\n",
" ^^^^^^^^^^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\stack_data\\core.py\", line 660, in executing_piece\n",
" return only(\n",
" ^^^^^\n",
" File \"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\executing\\executing.py\", line 116, in only\n",
" raise NotOneValueFound('Expected one value, found 0')\n",
"executing.executing.NotOneValueFound: Expected one value, found 0\n"
]
}
],
"source": [
"from dotenv import load_dotenv\n",
"load_dotenv()\n",
"resp = Gemini(Model = \"gemini-1.5-flash\").complete(\"Write a poem about a magic backpack\")\n",
"print(resp)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"GOOGLE_API_KEY = os.environ[\"GOOGLE_API_KEY\"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"questions = [\n",
" \"What is the company's registered office address?\",\n",
" \"What is the phone number of the company?\",\n",
" \"When was the company established?\",\n",
" \"Who is the regulatory authority for the company?\",\n",
" \"What is the website of the company?\",\n",
" \"What is the CIN (Corporate Identification Number) of the company?\",\n",
" \"Who is the CEO of the company?\",\n",
" \"What is the company's market capitalization?\",\n",
" \"What are the major products or services offered by the company?\",\n",
" \"What is the company's financial performance in the last fiscal year?\"\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ In Context Relevance, input source will be set to __record__.main_input or `Select.RecordInput` .\n",
"✅ In Context Relevance, input statement will be set to __record__.app.query.rets.source_nodes[:].node.text .\n",
"✅ In Answer Relevance, input prompt will be set to __record__.main_input or `Select.RecordInput` .\n",
"✅ In Answer Relevance, input context will be set to __record__.main_output or `Select.RecordOutput` .\n",
"✅ In Context Relevance, input prompt will be set to __record__.main_input or `Select.RecordInput` .\n",
"✅ In Context Relevance, input context will be set to __record__.app.query.rets.source_nodes[:].node.text .\n"
]
}
],
"source": [
"from trulens_eval.feedback.provider.langchain import Langchain\n",
"from trulens_eval.feedback.provider.hugs import Huggingface\n",
"from trulens_eval import Feedback\n",
"from trulens_eval import TruLlama\n",
"context_selection = TruLlama.select_source_nodes().node.text\n",
"provider = Huggingface()\n",
"import numpy as np\n",
"huggingface_provider = Huggingface()\n",
"# Define a groundedness feedback function\n",
"f_groundedness = (\n",
" Feedback(huggingface_provider.groundedness_measure_with_nli,\n",
" name=\"Context Relevance\")\n",
" .on_input()\n",
" .on(context_selection)\n",
" .aggregate(np.mean)\n",
")\n",
"# Question/answer relevance between overall question and answer.\n",
"f_answer_relevance = Feedback(\n",
" huggingface_provider.context_relevance,\n",
" name=\"Answer Relevance\"\n",
").on_input_output()\n",
"\n",
"# Context relevance between question and each context chunk.\n",
"f_context_relevance = (\n",
" Feedback(huggingface_provider.context_relevance,\n",
" name=\"Context Relevance\")\n",
" .on_input()\n",
" .on(context_selection)\n",
" .aggregate(np.mean)\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"from trulens_eval.feedback.provider.hugs import Huggingface\n",
"huggingface_provider = Huggingface()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"def generate_answer(query, vector_store, template):\n",
" # Use LangChain's RetrievalQA to query the vector store and generate the answer\n",
" qa_chain = RetrievalQA.from_chain_type(\n",
" llm=ChatGoogleGenerativeAI(model=\"gemini-1.5-flash\"),\n",
" chain_type=\"stuff\",\n",
" retriever=vector_store.as_retriever(search_type=\"similarity\")\n",
" )\n",
"\n",
" # Format the prompt with the retrieved context and the query\n",
" prompt = template.format(context=\"{context}\", question=query)\n",
" \n",
" # Generate the answer by running the chain with the combined prompt\n",
" answer = qa_chain.run(query=query) # Pass 'input' as keyword argument with the formatted prompt\n",
" return answer"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"generate_answer(\n",
" \"How do you create your AI portfolio?\")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"ename": "ValidationError",
"evalue": "2 validation errors for TruLlama\napp.is-instance[BaseQueryEngine]\n Input should be an instance of BaseQueryEngine [type=is_instance_of, input_value=<function generate_answer at 0x0000019D4B98EFC0>, input_type=function]\n For further information visit https://errors.pydantic.dev/2.8/v/is_instance_of\napp.is-instance[BaseChatEngine]\n Input should be an instance of BaseChatEngine [type=is_instance_of, input_value=<function generate_answer at 0x0000019D4B98EFC0>, input_type=function]\n For further information visit https://errors.pydantic.dev/2.8/v/is_instance_of",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mValidationError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[15], line 3\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtrulens_eval\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m TruLlama\n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtrulens_eval\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m FeedbackMode\n\u001b[1;32m----> 3\u001b[0m tru_recorder \u001b[38;5;241m=\u001b[39m \u001b[43mTruLlama\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43mgenerate_answer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43mapp_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mApp_1\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m 6\u001b[0m \u001b[43m \u001b[49m\u001b[43mfeedbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\n\u001b[0;32m 7\u001b[0m \u001b[43m \u001b[49m\u001b[43mf_groundedness\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 8\u001b[0m \u001b[43m \u001b[49m\u001b[43mf_answer_relevance\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9\u001b[0m \u001b[43m \u001b[49m\u001b[43mf_context_relevance\u001b[49m\n\u001b[0;32m 10\u001b[0m \u001b[43m \u001b[49m\u001b[43m]\u001b[49m\n\u001b[0;32m 11\u001b[0m \u001b[43m)\u001b[49m\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\trulens_eval\\tru_llama.py:314\u001b[0m, in \u001b[0;36mTruLlama.__init__\u001b[1;34m(self, app, **kwargs)\u001b[0m\n\u001b[0;32m 311\u001b[0m kwargs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mroot_class\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m Class\u001b[38;5;241m.\u001b[39mof_object(app) \u001b[38;5;66;03m# TODO: make class property\u001b[39;00m\n\u001b[0;32m 312\u001b[0m kwargs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124minstrument\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m LlamaInstrument(app\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m)\n\u001b[1;32m--> 314\u001b[0m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\trulens_eval\\app.py:564\u001b[0m, in \u001b[0;36mApp.__init__\u001b[1;34m(self, tru, feedbacks, **kwargs)\u001b[0m\n\u001b[0;32m 559\u001b[0m kwargs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mfeedbacks\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m feedbacks\n\u001b[0;32m 560\u001b[0m kwargs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mrecording_contexts\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m contextvars\u001b[38;5;241m.\u001b[39mContextVar(\n\u001b[0;32m 561\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrecording_contexts\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 562\u001b[0m )\n\u001b[1;32m--> 564\u001b[0m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 566\u001b[0m app \u001b[38;5;241m=\u001b[39m kwargs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mapp\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[0;32m 567\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapp \u001b[38;5;241m=\u001b[39m app\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\trulens_eval\\schema\\app.py:97\u001b[0m, in \u001b[0;36mAppDefinition.__init__\u001b[1;34m(self, app_id, tags, metadata, feedback_mode, app_extra_json, **kwargs)\u001b[0m\n\u001b[0;32m 94\u001b[0m kwargs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m {}\n\u001b[0;32m 95\u001b[0m kwargs[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mapp_extra_json\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m app_extra_json \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mdict\u001b[39m()\n\u001b[1;32m---> 97\u001b[0m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 99\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m app_id \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 100\u001b[0m app_id \u001b[38;5;241m=\u001b[39m obj_id_of_obj(obj\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_dump(), prefix\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mapp\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\trulens_eval\\utils\\pyschema.py:686\u001b[0m, in \u001b[0;36mWithClassInfo.__init__\u001b[1;34m(self, class_info, obj, cls, *args, **kwargs)\u001b[0m\n\u001b[0;32m 682\u001b[0m class_info \u001b[38;5;241m=\u001b[39m Class\u001b[38;5;241m.\u001b[39mof_class(\u001b[38;5;28mcls\u001b[39m, with_bases\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m 684\u001b[0m kwargs[CLASS_INFO] \u001b[38;5;241m=\u001b[39m class_info\n\u001b[1;32m--> 686\u001b[0m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\pydantic\\main.py:193\u001b[0m, in \u001b[0;36mBaseModel.__init__\u001b[1;34m(self, **data)\u001b[0m\n\u001b[0;32m 191\u001b[0m \u001b[38;5;66;03m# `__tracebackhide__` tells pytest and some other tools to omit this function from tracebacks\u001b[39;00m\n\u001b[0;32m 192\u001b[0m __tracebackhide__ \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m--> 193\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__pydantic_validator__\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalidate_python\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mself_instance\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m)\u001b[49m\n",
"\u001b[1;31mValidationError\u001b[0m: 2 validation errors for TruLlama\napp.is-instance[BaseQueryEngine]\n Input should be an instance of BaseQueryEngine [type=is_instance_of, input_value=<function generate_answer at 0x0000019D4B98EFC0>, input_type=function]\n For further information visit https://errors.pydantic.dev/2.8/v/is_instance_of\napp.is-instance[BaseChatEngine]\n Input should be an instance of BaseChatEngine [type=is_instance_of, input_value=<function generate_answer at 0x0000019D4B98EFC0>, input_type=function]\n For further information visit https://errors.pydantic.dev/2.8/v/is_instance_of"
]
}
],
"source": [
"from trulens_eval import TruLlama\n",
"from trulens_eval import FeedbackMode\n",
"tru_recorder = TruLlama(\n",
" generate_answer,\n",
" app_id=\"App_1\",\n",
" feedbacks=[\n",
" f_groundedness,\n",
" f_answer_relevance,\n",
" f_context_relevance\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|