Spaces:
Sleeping
Sleeping
File size: 9,201 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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "984169ca",
"metadata": {},
"source": [
"# Question Answering Benchmarking: State of the Union Address\n",
"\n",
"Here we go over how to benchmark performance on a question answering task over a state of the union address.\n",
"\n",
"It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See [here](https://langchain.readthedocs.io/en/latest/tracing.html) for an explanation of what tracing is and how to set it up."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f127fb04",
"metadata": {},
"outputs": [],
"source": [
"# Comment this out if you are NOT using tracing\n",
"import os\n",
"os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
]
},
{
"cell_type": "markdown",
"id": "8a16b75d",
"metadata": {},
"source": [
"## Loading the data\n",
"First, let's load the data."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "5b2d5e98",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Found cached dataset json (/Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--question-answering-state-of-the-union-a7e5a3b2db4f440d/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/1 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from langchain.evaluation.loading import load_dataset\n",
"dataset = load_dataset(\"question-answering-state-of-the-union\")"
]
},
{
"cell_type": "markdown",
"id": "4ab6a716",
"metadata": {},
"source": [
"## Setting up a chain\n",
"Now we need to create some pipelines for doing question answering. Step one in that is creating an index over the data in question."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "c18680b5",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader(\"../../modules/state_of_the_union.txt\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "7f0de2b3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.indexes import VectorstoreIndexCreator"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "ef84ff99",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"vectorstore = VectorstoreIndexCreator().from_loaders([loader]).vectorstore"
]
},
{
"cell_type": "markdown",
"id": "f0b5d8f6",
"metadata": {},
"source": [
"Now we can create a question answering chain."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "8843cb0c",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import RetrievalQA\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "573719a0",
"metadata": {},
"outputs": [],
"source": [
"chain = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=vectorstore.as_retriever(), input_key=\"question\")"
]
},
{
"cell_type": "markdown",
"id": "37d669e9",
"metadata": {},
"source": [
"## Make a prediction\n",
"\n",
"First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "3089e409",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'question': 'What is the purpose of the NATO Alliance?',\n",
" 'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.',\n",
" 'result': ' The NATO Alliance was created to secure peace and stability in Europe after World War 2.'}"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain(dataset[0])"
]
},
{
"cell_type": "markdown",
"id": "d0c16cd7",
"metadata": {},
"source": [
"## Make many predictions\n",
"Now we can make predictions"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "24b4c66e",
"metadata": {},
"outputs": [],
"source": [
"predictions = chain.apply(dataset)"
]
},
{
"cell_type": "markdown",
"id": "49d969fb",
"metadata": {},
"source": [
"## Evaluate performance\n",
"Now we can evaluate the predictions. The first thing we can do is look at them by eye."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "1d583f03",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'question': 'What is the purpose of the NATO Alliance?',\n",
" 'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.',\n",
" 'result': ' The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.'}"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"predictions[0]"
]
},
{
"cell_type": "markdown",
"id": "4783344b",
"metadata": {},
"source": [
"Next, we can use a language model to score them programatically"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "d0a9341d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.evaluation.qa import QAEvalChain"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "1612dec1",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"eval_chain = QAEvalChain.from_llm(llm)\n",
"graded_outputs = eval_chain.evaluate(dataset, predictions, question_key=\"question\", prediction_key=\"result\")"
]
},
{
"cell_type": "markdown",
"id": "79587806",
"metadata": {},
"source": [
"We can add in the graded output to the `predictions` dict and then get a count of the grades."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "2a689df5",
"metadata": {},
"outputs": [],
"source": [
"for i, prediction in enumerate(predictions):\n",
" prediction['grade'] = graded_outputs[i]['text']"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "27b61215",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Counter({' CORRECT': 7, ' INCORRECT': 4})"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from collections import Counter\n",
"Counter([pred['grade'] for pred in predictions])"
]
},
{
"cell_type": "markdown",
"id": "12fe30f4",
"metadata": {},
"source": [
"We can also filter the datapoints to the incorrect examples and look at them."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "47c692a1",
"metadata": {},
"outputs": [],
"source": [
"incorrect = [pred for pred in predictions if pred['grade'] == \" INCORRECT\"]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "0ef976c1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'question': 'What is the U.S. Department of Justice doing to combat the crimes of Russian oligarchs?',\n",
" 'answer': 'The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.',\n",
" 'result': ' The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and is naming a chief prosecutor for pandemic fraud.',\n",
" 'grade': ' INCORRECT'}"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"incorrect[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7710401a",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|