Spaces:
Running
Running
File size: 11,571 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 |
{
"cells": [
{
"cell_type": "markdown",
"id": "69e35d6f",
"metadata": {},
"source": [
"# How to customize conversational memory\n",
"\n",
"This notebook walks through a few ways to customize conversational memory."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "0f964494",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.chains import ConversationChain\n",
"from langchain.memory import ConversationBufferMemory\n",
"\n",
"\n",
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "fe3cd3e9",
"metadata": {},
"source": [
"## AI Prefix\n",
"\n",
"The first way to do so is by changing the AI prefix in the conversation summary. By default, this is set to \"AI\", but you can set this to be anything you want. Note that if you change this, you should also change the prompt used in the chain to reflect this naming change. Let's walk through an example of that in the example below."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "d0e66d87",
"metadata": {},
"outputs": [],
"source": [
"# Here it is by default set to \"AI\"\n",
"conversation = ConversationChain(\n",
" llm=llm, \n",
" verbose=True, \n",
" memory=ConversationBufferMemory()\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "f8fa6999",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi there!\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Hi there! It's nice to meet you. How can I help you today?\""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"Hi there!\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "de213386",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi there!\n",
"AI: Hi there! It's nice to meet you. How can I help you today?\n",
"Human: What's the weather?\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' The current weather is sunny and warm with a temperature of 75 degrees Fahrenheit. The forecast for the next few days is sunny with temperatures in the mid-70s.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"What's the weather?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "585949eb",
"metadata": {},
"outputs": [],
"source": [
"# Now we can override it and set it to \"AI Assistant\"\n",
"from langchain.prompts.prompt import PromptTemplate\n",
"\n",
"template = \"\"\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"{history}\n",
"Human: {input}\n",
"AI Assistant:\"\"\"\n",
"PROMPT = PromptTemplate(\n",
" input_variables=[\"history\", \"input\"], template=template\n",
")\n",
"conversation = ConversationChain(\n",
" prompt=PROMPT,\n",
" llm=llm, \n",
" verbose=True, \n",
" memory=ConversationBufferMemory(ai_prefix=\"AI Assistant\")\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "1bb9bc53",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi there!\n",
"AI Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Hi there! It's nice to meet you. How can I help you today?\""
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"Hi there!\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "d9241923",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi there!\n",
"AI Assistant: Hi there! It's nice to meet you. How can I help you today?\n",
"Human: What's the weather?\n",
"AI Assistant:\u001b[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' The current weather is sunny and warm with a temperature of 75 degrees Fahrenheit. The forecast for the rest of the day is sunny with a high of 78 degrees and a low of 65 degrees.'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"What's the weather?\")"
]
},
{
"cell_type": "markdown",
"id": "0517ccf8",
"metadata": {},
"source": [
"## Human Prefix\n",
"\n",
"The next way to do so is by changing the Human prefix in the conversation summary. By default, this is set to \"Human\", but you can set this to be anything you want. Note that if you change this, you should also change the prompt used in the chain to reflect this naming change. Let's walk through an example of that in the example below."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "6357a461",
"metadata": {},
"outputs": [],
"source": [
"# Now we can override it and set it to \"Friend\"\n",
"from langchain.prompts.prompt import PromptTemplate\n",
"\n",
"template = \"\"\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"{history}\n",
"Friend: {input}\n",
"AI:\"\"\"\n",
"PROMPT = PromptTemplate(\n",
" input_variables=[\"history\", \"input\"], template=template\n",
")\n",
"conversation = ConversationChain(\n",
" prompt=PROMPT,\n",
" llm=llm, \n",
" verbose=True, \n",
" memory=ConversationBufferMemory(human_prefix=\"Friend\")\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "969b6f54",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Friend: Hi there!\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Hi there! It's nice to meet you. How can I help you today?\""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"Hi there!\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d5ea82bb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Friend: Hi there!\n",
"AI: Hi there! It's nice to meet you. How can I help you today?\n",
"Friend: What's the weather?\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' The weather right now is sunny and warm with a temperature of 75 degrees Fahrenheit. The forecast for the rest of the day is mostly sunny with a high of 82 degrees.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"What's the weather?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ce7f79ab",
"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
}
|