Spaces:
Running
Running
File size: 14,022 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 |
{
"cells": [
{
"cell_type": "markdown",
"id": "18ada398-dce6-4049-9b56-fc0ede63da9c",
"metadata": {},
"source": [
"# Vectorstore Agent\n",
"\n",
"This notebook showcases an agent designed to retrieve information from one or more vectorstores, either with or without sources."
]
},
{
"cell_type": "markdown",
"id": "eecb683b-3a46-4b9d-81a3-7caefbfec1a1",
"metadata": {},
"source": [
"## Create the Vectorstores"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9bfd0ed8-a5eb-443e-8e92-90be8cabb0a7",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain import OpenAI, VectorDBQA\n",
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "345bb078-4ec1-4e3a-827b-cd238c49054d",
"metadata": {
"tags": []
},
"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": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"state_of_union_store = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5f50eb82-e1a5-4252-8306-8ec1b478d9b4",
"metadata": {
"tags": []
},
"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": [
"from langchain.document_loaders import WebBaseLoader\n",
"loader = WebBaseLoader(\"https://beta.ruff.rs/docs/faq/\")\n",
"docs = loader.load()\n",
"ruff_texts = text_splitter.split_documents(docs)\n",
"ruff_store = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")"
]
},
{
"cell_type": "markdown",
"id": "f4814175-964d-42f1-aa9d-22801ce1e912",
"metadata": {},
"source": [
"## Initialize Toolkit and Agent\n",
"\n",
"First, we'll create an agent with a single vectorstore."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5b3b3206",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import (\n",
" create_vectorstore_agent,\n",
" VectorStoreToolkit,\n",
" VectorStoreInfo,\n",
")\n",
"vectorstore_info = VectorStoreInfo(\n",
" name=\"state_of_union_address\",\n",
" description=\"the most recent state of the Union adress\",\n",
" vectorstore=state_of_union_store\n",
")\n",
"toolkit = VectorStoreToolkit(vectorstore_info=vectorstore_info)\n",
"agent_executor = create_vectorstore_agent(\n",
" llm=llm,\n",
" toolkit=toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "8a38ad10",
"metadata": {},
"source": [
"## Examples"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "3f2f455c",
"metadata": {},
"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 find the answer in the state of the union address\n",
"Action: state_of_union_address\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "d61e1e63",
"metadata": {},
"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 the state_of_union_address_with_sources tool to answer this question.\n",
"Action: state_of_union_address_with_sources\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m{\"answer\": \" Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\\n\", \"sources\": \"../../state_of_the_union.txt\"}\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\""
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address? List the source.\")"
]
},
{
"cell_type": "markdown",
"id": "7ca07707",
"metadata": {},
"source": [
"## Multiple Vectorstores\n",
"We can also easily use this initialize an agent with multiple vectorstores and use the agent to route between them. To do this. This agent is optimized for routing, so it is a different toolkit and initializer."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c3209fd3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import (\n",
" create_vectorstore_router_agent,\n",
" VectorStoreRouterToolkit,\n",
" VectorStoreInfo,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "815c4f39-308d-4949-b992-1361036e6e09",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"ruff_vectorstore_info = VectorStoreInfo(\n",
" name=\"ruff\",\n",
" description=\"Information about the Ruff python linting library\",\n",
" vectorstore=ruff_store\n",
")\n",
"router_toolkit = VectorStoreRouterToolkit(\n",
" vectorstores=[vectorstore_info, ruff_vectorstore_info],\n",
" llm=llm\n",
")\n",
"agent_executor = create_vectorstore_router_agent(\n",
" llm=llm,\n",
" toolkit=router_toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "71680984-edaf-4a63-90f5-94edbd263550",
"metadata": {},
"source": [
"## Examples"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "3cd1bf3e-e3df-4e69-bbe1-71c64b1af947",
"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 the state_of_union_address tool to answer this question.\n",
"Action: state_of_union_address\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "c5998b8d",
"metadata": {},
"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 find out what tool ruff uses to run over Jupyter Notebooks\n",
"Action: ruff\n",
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks?\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "744e9b51-fbd9-4778-b594-ea957d0f3467",
"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 find out what tool ruff uses and if the president mentioned it in the state of the union.\n",
"Action: ruff\n",
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out if the president mentioned nbQA in the state of the union.\n",
"Action: state_of_union_address\n",
"Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'No, the president did not mention nbQA in the state of the union.'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "92203aa9-f63a-4ce1-b562-fadf4474ad9d",
"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
}
|