Spaces:
Runtime error
Runtime error
File size: 11,530 Bytes
acc4ffe |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "ba5f8741",
"metadata": {},
"source": [
"# Custom Agent\n",
"\n",
"This notebook goes through how to create your own custom agent.\n",
"\n",
"An agent consists of three parts:\n",
" \n",
" - Tools: The tools the agent has available to use.\n",
" - LLMChain: The LLMChain that produces the text that is parsed in a certain way to determine which action to take.\n",
" - The agent class itself: this parses the output of the LLMChain to determin which action to take.\n",
" \n",
" \n",
"In this notebook we walk through two types of custom agents. The first type shows how to create a custom LLMChain, but still use an existing agent class to parse the output. The second shows how to create a custom agent class."
]
},
{
"cell_type": "markdown",
"id": "6064f080",
"metadata": {},
"source": [
"### Custom LLMChain\n",
"\n",
"The first way to create a custom agent is to use an existing Agent class, but use a custom LLMChain. This is the simplest way to create a custom Agent. It is highly reccomended that you work with the `ZeroShotAgent`, as at the moment that is by far the most generalizable one. \n",
"\n",
"Most of the work in creating the custom LLMChain comes down to the prompt. Because we are using an existing agent class to parse the output, it is very important that the prompt say to produce text in that format. Additionally, we currently require an `agent_scratchpad` input variable to put notes on previous actions and observations. This should almost always be the final part of the prompt. However, besides those instructions, you can customize the prompt as you wish.\n",
"\n",
"To ensure that the prompt contains the appropriate instructions, we will utilize a helper method on that class. The helper method for the `ZeroShotAgent` takes the following arguments:\n",
"\n",
"- tools: List of tools the agent will have access to, used to format the prompt.\n",
"- prefix: String to put before the list of tools.\n",
"- suffix: String to put after the list of tools.\n",
"- input_variables: List of input variables the final prompt will expect.\n",
"\n",
"For this exercise, we will give our agent access to Google Search, and we will customize it in that we will have it answer as a pirate."
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "9af9734e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
"from langchain import OpenAI, SerpAPIWrapper, LLMChain"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "becda2a1",
"metadata": {},
"outputs": [],
"source": [
"search = SerpAPIWrapper()\n",
"tools = [\n",
" Tool(\n",
" name = \"Search\",\n",
" func=search.run,\n",
" description=\"useful for when you need to answer questions about current events\"\n",
" )\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "339b1bb8",
"metadata": {},
"outputs": [],
"source": [
"prefix = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\"\"\"\n",
"suffix = \"\"\"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\n",
"\n",
"Question: {input}\n",
"{agent_scratchpad}\"\"\"\n",
"\n",
"prompt = ZeroShotAgent.create_prompt(\n",
" tools, \n",
" prefix=prefix, \n",
" suffix=suffix, \n",
" input_variables=[\"input\", \"agent_scratchpad\"]\n",
")"
]
},
{
"cell_type": "markdown",
"id": "59db7b58",
"metadata": {},
"source": [
"In case we are curious, we can now take a look at the final prompt template to see what it looks like when its all put together."
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "e21d2098",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
"\n",
"Search: useful for when you need to answer questions about current events\n",
"\n",
"Use the following format:\n",
"\n",
"Question: the input question you must answer\n",
"Thought: you should always think about what to do\n",
"Action: the action to take, should be one of [Search]\n",
"Action Input: the input to the action\n",
"Observation: the result of the action\n",
"... (this Thought/Action/Action Input/Observation can repeat N times)\n",
"Thought: I now know the final answer\n",
"Final Answer: the final answer to the original input question\n",
"\n",
"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\n",
"\n",
"Question: {input}\n",
"{agent_scratchpad}\n"
]
}
],
"source": [
"print(prompt.template)"
]
},
{
"cell_type": "markdown",
"id": "5e028e6d",
"metadata": {},
"source": [
"Note that we are able to feed agents a self-defined prompt template, i.e. not restricted to the prompt generated by the `create_prompt` function, assuming it meets the agent's requirements. \n",
"\n",
"For example, for `ZeroShotAgent`, we will need to ensure that it meets the following requirements. There should a string starting with \"Action:\" and a following string starting with \"Action Input:\", and both should be separated by a newline.\n"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "9b1cc2a2",
"metadata": {},
"outputs": [],
"source": [
"llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "e4f5092f",
"metadata": {},
"outputs": [],
"source": [
"tool_names = [tool.name for tool in tools]\n",
"agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "490604e9",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "653b1617",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find out the population of Canada\n",
"Action: Search\n",
"Action Input: Population of Canada 2023\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,610,447 as of Saturday, February 18, 2023, based on Worldometer elaboration of the latest United Nations data. Canada 2020 population is estimated at 37,742,154 people at mid year according to UN data.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Arrr, Canada be havin' 38,610,447 scallywags livin' there as of 2023!\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Arrr, Canada be havin' 38,610,447 scallywags livin' there as of 2023!\""
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"How many people live in canada as of 2023?\")"
]
},
{
"cell_type": "markdown",
"id": "040eb343",
"metadata": {},
"source": [
"### Multiple inputs\n",
"Agents can also work with prompts that require multiple inputs."
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "43dbfa2f",
"metadata": {},
"outputs": [],
"source": [
"prefix = \"\"\"Answer the following questions as best you can. You have access to the following tools:\"\"\"\n",
"suffix = \"\"\"When answering, you MUST speak in the following language: {language}.\n",
"\n",
"Question: {input}\n",
"{agent_scratchpad}\"\"\"\n",
"\n",
"prompt = ZeroShotAgent.create_prompt(\n",
" tools, \n",
" prefix=prefix, \n",
" suffix=suffix, \n",
" input_variables=[\"input\", \"language\", \"agent_scratchpad\"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "0f087313",
"metadata": {},
"outputs": [],
"source": [
"llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "92c75a10",
"metadata": {},
"outputs": [],
"source": [
"agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "ac5b83bf",
"metadata": {},
"outputs": [],
"source": [
"agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "c960e4ff",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to find out the population of Canada in 2023.\n",
"Action: Search\n",
"Action Input: Population of Canada in 2023\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,610,447 as of Saturday, February 18, 2023, based on Worldometer elaboration of the latest United Nations data. Canada 2020 population is estimated at 37,742,154 people at mid year according to UN data.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: La popolazione del Canada nel 2023 è stimata in 38.610.447 persone.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'La popolazione del Canada nel 2023 è stimata in 38.610.447 persone.'"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(input=\"How many people live in canada as of 2023?\", language=\"italian\")"
]
},
{
"cell_type": "markdown",
"id": "90171b2b",
"metadata": {},
"source": [
"### Custom Agent Class\n",
"\n",
"Coming soon."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "adefb4c2",
"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"
},
"vscode": {
"interpreter": {
"hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|