Spaces:
Running
Running
File size: 10,855 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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "5371a9bb",
"metadata": {},
"source": [
"# Tracing Walkthrough\n",
"\n",
"There are two recommended ways to trace your LangChains:\n",
"\n",
"1. Setting the `LANGCHAIN_TRACING` environment variable to \"true\".\n",
"1. Using a context manager with tracing_enabled() to trace a particular block of code.\n",
"\n",
"**Note** if the environment variable is set, all code will be traced, regardless of whether or not it's within the context manager."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "17c04cc6-c93d-4b6c-a033-e897577f4ed1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"os.environ[\"LANGCHAIN_TRACING\"] = \"true\"\n",
"\n",
"## Uncomment below if using hosted setup.\n",
"# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://langchain-api-gateway-57eoxz8z.uc.gateway.dev\" \n",
"\n",
"## Uncomment below if you want traces to be recorded to \"my_session\" instead of \"default\".\n",
"# os.environ[\"LANGCHAIN_SESSION\"] = \"my_session\" \n",
"\n",
"## Better to set this environment variable in the terminal\n",
"## Uncomment below if using hosted version. Replace \"my_api_key\" with your actual API Key.\n",
"# os.environ[\"LANGCHAIN_API_KEY\"] = \"my_api_key\" \n",
"\n",
"import langchain\n",
"from langchain.agents import Tool, initialize_agent, load_tools\n",
"from langchain.agents import AgentType\n",
"from langchain.callbacks import tracing_enabled\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1b62cd48",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Agent run with tracing. Ensure that OPENAI_API_KEY is set appropriately to run this example.\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"tools = load_tools([\"llm-math\"], llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "bfa16b79-aa4b-4d41-a067-70d1f593f667",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 2^.123243\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: 1.0891804557407723\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'1.0891804557407723'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")\n",
"\n",
"agent.run(\"What is 2 raised to .123243 power?\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4829eb1d",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 2 ^ .123243\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
"Final Answer: 1.0891804557407723\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'1.0891804557407723'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Agent run with tracing using a chat model\n",
"agent = initialize_agent(\n",
" tools, ChatOpenAI(temperature=0), agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")\n",
"\n",
"agent.run(\"What is 2 raised to .123243 power?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "76abfd82",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 2 ^ .123243\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
"Final Answer: 1.0891804557407723\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 5 ^ .123243\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.2193914912400514\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
"Final Answer: 1.2193914912400514\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
}
],
"source": [
"# Both of the agent runs will be traced because the environment variable is set\n",
"agent.run(\"What is 2 raised to .123243 power?\")\n",
"with tracing_enabled() as session:\n",
" agent.run(\"What is 5 raised to .123243 power?\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "fe833c33-033f-4806-be0c-cc3d147db13d",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 5 ^ .123243\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.2193914912400514\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
"Final Answer: 1.2193914912400514\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 2 ^ .123243\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
"Final Answer: 1.0891804557407723\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'1.0891804557407723'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Now, we unset the environment variable and use a context manager.\n",
"if \"LANGCHAIN_TRACING\" in os.environ:\n",
" del os.environ[\"LANGCHAIN_TRACING\"]\n",
"\n",
"# here, we are writing traces to \"my_test_session\"\n",
"with tracing_enabled(\"my_session\") as session:\n",
" assert session\n",
" agent.run(\"What is 5 raised to .123243 power?\") # this should be traced\n",
"\n",
"agent.run(\"What is 2 raised to .123243 power?\") # this should not be traced"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "b34105a4-be8e-46e4-8abe-01adba3ba727",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\n",
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 3^0.123\u001b[0m\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
"Action: Calculator\n",
"Action Input: 2^0.123\u001b[0m\u001b[32;1m\u001b[1;3mAny number raised to the power of 0 is 1, but I'm not sure about a decimal power.\n",
"Action: Calculator\n",
"Action Input: 1^.123\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.1446847956963533\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0889970153361064\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0\u001b[0m\n",
"Thought:\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'1.0'"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# The context manager is concurrency safe:\n",
"import asyncio \n",
"if \"LANGCHAIN_TRACING\" in os.environ:\n",
" del os.environ[\"LANGCHAIN_TRACING\"]\n",
" \n",
"questions = [f\"What is {i} raised to .123 power?\" for i in range(1,4)]\n",
"\n",
"# start a background task\n",
"task = asyncio.create_task(agent.arun(questions[0])) # this should not be traced\n",
"with tracing_enabled() as session:\n",
" assert session\n",
" tasks = [agent.arun(q) for q in questions[1:3]] # these should be traced\n",
" await asyncio.gather(*tasks)\n",
"\n",
"await task"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4e46c85b-2ac0-4661-abed-9c2bf3036820",
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|