Spaces:
Running
Running
File size: 11,292 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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# FAISS\n",
"\n",
">[Facebook AI Similarity Search (Faiss)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.\n",
"\n",
"[Faiss documentation](https://faiss.ai/).\n",
"\n",
"This notebook shows how to use functionality related to the `FAISS` vector database."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "497fcd89-e832-46a7-a74a-c71199666206",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"#!pip install faiss\n",
"# OR\n",
"!pip install faiss-cpu"
]
},
{
"cell_type": "markdown",
"id": "38237514-b3fa-44a4-9cff-30cd6bf50073",
"metadata": {},
"source": [
"We want to use OpenAIEmbeddings so we have to get the OpenAI API Key. "
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "47f9b495-88f1-4286-8d5d-1416103931a7",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdin",
"output_type": "stream",
"text": [
"OpenAI API Key: 路路路路路路路路\n"
]
}
],
"source": [
"import os\n",
"import getpass\n",
"\n",
"os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "aac9563e",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import FAISS\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "a3c3999a",
"metadata": {
"tags": []
},
"outputs": [],
"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",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "5eabdb75",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"db = FAISS.from_documents(docs, embeddings)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "4b172de8",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you鈥檙e at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I鈥檇 like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer鈥攁n Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation鈥檚 top legal minds, who will continue Justice Breyer鈥檚 legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "markdown",
"id": "f13473b5",
"metadata": {},
"source": [
"## Similarity Search with score\n",
"There are some FAISS specific methods. One of them is `similarity_search_with_score`, which allows you to return not only the documents but also the similarity score of the query to them."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "186ee1d8",
"metadata": {},
"outputs": [],
"source": [
"docs_and_scores = db.similarity_search_with_score(query)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "284e04b5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you鈥檙e at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I鈥檇 like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer鈥攁n Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation鈥檚 top legal minds, who will continue Justice Breyer鈥檚 legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
" 0.3914415)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs_and_scores[0]"
]
},
{
"cell_type": "markdown",
"id": "f34420cf",
"metadata": {},
"source": [
"It is also possible to do a search for documents similar to a given embedding vector using `similarity_search_by_vector` which accepts an embedding vector as a parameter instead of a string."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "b558ebb7",
"metadata": {},
"outputs": [],
"source": [
"embedding_vector = embeddings.embed_query(query)\n",
"docs_and_scores = db.similarity_search_by_vector(embedding_vector)"
]
},
{
"cell_type": "markdown",
"id": "31bda7fd",
"metadata": {},
"source": [
"## Saving and loading\n",
"You can also save and load a FAISS index. This is useful so you don't have to recreate it everytime you use it."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "428a6816",
"metadata": {},
"outputs": [],
"source": [
"db.save_local(\"faiss_index\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "56d1841c",
"metadata": {},
"outputs": [],
"source": [
"new_db = FAISS.load_local(\"faiss_index\", embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "39055525",
"metadata": {},
"outputs": [],
"source": [
"docs = new_db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "98378c4e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you鈥檙e at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I鈥檇 like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer鈥攁n Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation鈥檚 top legal minds, who will continue Justice Breyer鈥檚 legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs[0]"
]
},
{
"cell_type": "markdown",
"id": "57da60d4",
"metadata": {},
"source": [
"## Merging\n",
"You can also merge two FAISS vectorstores"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "6dfd2b78",
"metadata": {},
"outputs": [],
"source": [
"db1 = FAISS.from_texts([\"foo\"], embeddings)\n",
"db2 = FAISS.from_texts([\"bar\"], embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "29960da7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'e0b74348-6c93-4893-8764-943139ec1d17': Document(page_content='foo', lookup_str='', metadata={}, lookup_index=0)}"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db1.docstore._dict"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "83392605",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'bdc50ae3-a1bb-4678-9260-1b0979578f40': Document(page_content='bar', lookup_str='', metadata={}, lookup_index=0)}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db2.docstore._dict"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "a3fcc1c7",
"metadata": {},
"outputs": [],
"source": [
"db1.merge_from(db2)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "41c51f89",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'e0b74348-6c93-4893-8764-943139ec1d17': Document(page_content='foo', lookup_str='', metadata={}, lookup_index=0),\n",
" 'd5211050-c777-493d-8825-4800e74cfdb6': Document(page_content='bar', lookup_str='', metadata={}, lookup_index=0)}"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db1.docstore._dict"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f80b60de",
"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": "3.10.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|