File size: 11,493 Bytes
6be64b3 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Capture LangSmith data in a Pandas DataFrame"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import pandas as pd\n",
"from langsmith import Client"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# Initialize the client\n",
"client = Client(\n",
" api_key=os.getenv(\"LANGCHAIN_API_KEY\"),\n",
" api_url=os.getenv(\"LANGCHAIN_ENDPOINT\")\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Retrieve trace runs\n",
"project_name = \"AirBnB RAG Evaluation\"\n",
"traces = client.list_runs(project_name=project_name)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# Convert trace data to DataFrame\n",
"trace_data = []\n",
"\n",
"for trace in traces:\n",
" trace_data.append({\n",
" 'trace_id': trace.id,\n",
" 'start_time': trace.start_time,\n",
" 'end_time': trace.end_time,\n",
" 'status': trace.status,\n",
" 'input': trace.inputs,\n",
" 'output': trace.outputs\n",
" })"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(trace_data)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"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>trace_id</th>\n",
" <th>start_time</th>\n",
" <th>end_time</th>\n",
" <th>status</th>\n",
" <th>input</th>\n",
" <th>output</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>717ef090-359f-41c4-84b3-08bec6251185</td>\n",
" <td>2024-06-25 14:02:53.067707</td>\n",
" <td>2024-06-25 14:02:54.842210</td>\n",
" <td>success</td>\n",
" <td>{'messages': [{'lc': 1, 'type': 'constructor',...</td>\n",
" <td>{'llm_output': {'model_name': 'llama3-70b-8192...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>97f1d6b5-17fa-4ebe-8438-2eabb33e6c12</td>\n",
" <td>2024-06-25 14:02:53.064911</td>\n",
" <td>2024-06-25 14:02:53.066843</td>\n",
" <td>success</td>\n",
" <td>{'context': [{'page_content': 'December 31, 20...</td>\n",
" <td>{'output': {'messages': [{'content': '<|begin_...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>78165b64-3961-4b28-8d66-ca17763ff7df</td>\n",
" <td>2024-06-25 14:02:53.063469</td>\n",
" <td>2024-06-25 14:02:53.066525</td>\n",
" <td>success</td>\n",
" <td>{'context': [{'page_content': 'December 31, 20...</td>\n",
" <td>{'output': [{'page_content': 'December 31, 202...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>6ba40755-4a55-4d8c-a824-7e8f855444cc</td>\n",
" <td>2024-06-25 14:02:53.062807</td>\n",
" <td>2024-06-25 14:02:54.844401</td>\n",
" <td>success</td>\n",
" <td>{'context': [{'page_content': 'December 31, 20...</td>\n",
" <td>{'output': {'content': '[BEGIN_SUMMARY]\n",
"The to...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>3bcafa07-7bdd-48e0-a55a-47b3f8ee32c7</td>\n",
" <td>2024-06-25 14:02:53.060709</td>\n",
" <td>2024-06-25 14:02:54.845145</td>\n",
" <td>success</td>\n",
" <td>{'context': [{'page_content': 'December 31, 20...</td>\n",
" <td>{'response': {'content': '[BEGIN_SUMMARY]\n",
"The ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>555</th>\n",
" <td>1013e849-793d-46da-aeea-2a8c3eaa08d4</td>\n",
" <td>2024-06-20 19:35:54.492314</td>\n",
" <td>2024-06-20 19:35:54.498540</td>\n",
" <td>success</td>\n",
" <td>{'question': 'What is Airbnb's 'Description of...</td>\n",
" <td>{'output': 'What is Airbnb's 'Description of B...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>556</th>\n",
" <td>88e7c281-436f-4cfd-9056-5e6954d2462c</td>\n",
" <td>2024-06-20 19:35:54.491579</td>\n",
" <td>2024-06-20 19:35:54.498051</td>\n",
" <td>success</td>\n",
" <td>{'question': 'What is Airbnb's 'Description of...</td>\n",
" <td>{'output': 'What is Airbnb's 'Description of B...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>557</th>\n",
" <td>7ea55086-6ed9-4930-8ba4-0df7a406c8b8</td>\n",
" <td>2024-06-20 19:35:54.490744</td>\n",
" <td>2024-06-20 19:35:55.556579</td>\n",
" <td>success</td>\n",
" <td>{'question': 'What is Airbnb's 'Description of...</td>\n",
" <td>{'output': [{'page_content': 'Table of Content...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>558</th>\n",
" <td>288e39cf-71e6-4574-bf48-8f902ec7a12f</td>\n",
" <td>2024-06-20 19:35:54.489031</td>\n",
" <td>2024-06-20 19:35:55.557354</td>\n",
" <td>success</td>\n",
" <td>{'question': 'What is Airbnb's 'Description of...</td>\n",
" <td>{'context': [{'page_content': 'Table of Conten...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>559</th>\n",
" <td>073e10ba-0a34-4338-9ff0-a7c00584e6bb</td>\n",
" <td>2024-06-20 19:35:54.441022</td>\n",
" <td>2024-06-20 19:35:56.962382</td>\n",
" <td>success</td>\n",
" <td>{'question': 'What is Airbnb's 'Description of...</td>\n",
" <td>{'response': {'content': 'Airbnb's 'Descriptio...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>560 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" trace_id start_time \\\n",
"0 717ef090-359f-41c4-84b3-08bec6251185 2024-06-25 14:02:53.067707 \n",
"1 97f1d6b5-17fa-4ebe-8438-2eabb33e6c12 2024-06-25 14:02:53.064911 \n",
"2 78165b64-3961-4b28-8d66-ca17763ff7df 2024-06-25 14:02:53.063469 \n",
"3 6ba40755-4a55-4d8c-a824-7e8f855444cc 2024-06-25 14:02:53.062807 \n",
"4 3bcafa07-7bdd-48e0-a55a-47b3f8ee32c7 2024-06-25 14:02:53.060709 \n",
".. ... ... \n",
"555 1013e849-793d-46da-aeea-2a8c3eaa08d4 2024-06-20 19:35:54.492314 \n",
"556 88e7c281-436f-4cfd-9056-5e6954d2462c 2024-06-20 19:35:54.491579 \n",
"557 7ea55086-6ed9-4930-8ba4-0df7a406c8b8 2024-06-20 19:35:54.490744 \n",
"558 288e39cf-71e6-4574-bf48-8f902ec7a12f 2024-06-20 19:35:54.489031 \n",
"559 073e10ba-0a34-4338-9ff0-a7c00584e6bb 2024-06-20 19:35:54.441022 \n",
"\n",
" end_time status \\\n",
"0 2024-06-25 14:02:54.842210 success \n",
"1 2024-06-25 14:02:53.066843 success \n",
"2 2024-06-25 14:02:53.066525 success \n",
"3 2024-06-25 14:02:54.844401 success \n",
"4 2024-06-25 14:02:54.845145 success \n",
".. ... ... \n",
"555 2024-06-20 19:35:54.498540 success \n",
"556 2024-06-20 19:35:54.498051 success \n",
"557 2024-06-20 19:35:55.556579 success \n",
"558 2024-06-20 19:35:55.557354 success \n",
"559 2024-06-20 19:35:56.962382 success \n",
"\n",
" input \\\n",
"0 {'messages': [{'lc': 1, 'type': 'constructor',... \n",
"1 {'context': [{'page_content': 'December 31, 20... \n",
"2 {'context': [{'page_content': 'December 31, 20... \n",
"3 {'context': [{'page_content': 'December 31, 20... \n",
"4 {'context': [{'page_content': 'December 31, 20... \n",
".. ... \n",
"555 {'question': 'What is Airbnb's 'Description of... \n",
"556 {'question': 'What is Airbnb's 'Description of... \n",
"557 {'question': 'What is Airbnb's 'Description of... \n",
"558 {'question': 'What is Airbnb's 'Description of... \n",
"559 {'question': 'What is Airbnb's 'Description of... \n",
"\n",
" output \n",
"0 {'llm_output': {'model_name': 'llama3-70b-8192... \n",
"1 {'output': {'messages': [{'content': '<|begin_... \n",
"2 {'output': [{'page_content': 'December 31, 202... \n",
"3 {'output': {'content': '[BEGIN_SUMMARY]\n",
"The to... \n",
"4 {'response': {'content': '[BEGIN_SUMMARY]\n",
"The ... \n",
".. ... \n",
"555 {'output': 'What is Airbnb's 'Description of B... \n",
"556 {'output': 'What is Airbnb's 'Description of B... \n",
"557 {'output': [{'page_content': 'Table of Content... \n",
"558 {'context': [{'page_content': 'Table of Conten... \n",
"559 {'response': {'content': 'Airbnb's 'Descriptio... \n",
"\n",
"[560 rows x 6 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Save to CSV or display DataFrame\n",
"df.to_csv('trace_runs.csv', index=False)\n",
"display(df)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.11.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|