File size: 8,924 Bytes
bc0299d |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 20,
"id": "081405cc",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import os\n",
"from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader\n",
"from langchain_community.vectorstores import FAISS\n",
"from langchain_community.embeddings import HuggingFaceEmbeddings\n",
"from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "3c40840f",
"metadata": {},
"outputs": [],
"source": [
"MODEL_NAME = \"sentence-transformers/all-MiniLM-L12-v2\"\n",
"DATA_PATH=\"data/\""
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "90fc0a47",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading documents from data/...\n",
"Loaded 2087 PDF document(s).\n",
"Split into 25938 chunks.\n",
"Creating and saving FAISS vector store...\n"
]
}
],
"source": [
"embeddings = HuggingFaceEmbeddings(model_name=MODEL_NAME)\n",
"\n",
"print(f\"Loading documents from {DATA_PATH}...\")\n",
"loader = DirectoryLoader(\n",
" DATA_PATH,\n",
" glob='*.pdf', \n",
" loader_cls=PyPDFLoader \n",
")\n",
"documents = loader.load()\n",
"\n",
"if not documents:\n",
" print(\"No PDF documents found. Make sure your PDFs are in the /data folder.\")\n",
" exit()\n",
"\n",
"print(f\"Loaded {len(documents)} PDF document(s).\")\n",
"\n",
"# 3. Split Documents\n",
"text_splitter = RecursiveCharacterTextSplitter(\n",
" chunk_size=300, \n",
" chunk_overlap=200,\n",
" separators=[\"\\n\\n\", \"\\n\", \".\", \"!\", \"?\", \" \", \"\"]\n",
" )\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"print(f\"Split into {len(docs)} chunks.\")\n",
"\n",
"# 4. Create and Save FAISS Vector Store\n",
"print(\"Creating and saving FAISS vector store...\")\n",
"db = FAISS.from_documents(docs, embeddings)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9ca0ee2b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading embedding model: sentence-transformers/all-MiniLM-L12-v2...\n",
"\n",
"✅ Retriever is ready.\n",
" Enter your query to test. Type 'exit' to quit.\n",
"\n",
"--- Retrieving docs for: 'who is director' ---\n",
"\n",
"--- Document 1 ---\n",
"Source: data/iiitdmj_crawl_data_1.pdf\n",
"Page: 133\n",
"\n",
"Content:\n",
"director@iiitdmj.ac.in\n",
"2.\n",
"Deputy Director\n",
"To be nominated on appointment\n",
"3.\n",
"Deans (Ex-officio)\n",
"1. Dr. Mukesh Kumar Roy\n",
"Faculty-in-Charge (Student Affairs)\n",
"mkroy@iiitdmj.ac.in\n",
"2. Prof. V. K. Gupta\n",
"Professor In-charge (Academic)\n",
"dean.acad@iiitdmj.ac.in\n",
"3. Prof. Pritee Khanna\n",
"--------------------\n",
"\n",
"--- Document 2 ---\n",
"Source: data/IIITDM Jabalpur.pdf\n",
"Page: 2\n",
"\n",
"Content:\n",
" The Deputy Director (to be nominated on appointment) \n",
" The Deans \n",
" The Heads of various disciplines and \n",
" The Registrar \n",
" \n",
" \n",
" \n",
" \n",
"Building And Works Committee \n",
"S. No. Name Designation \n",
"1. Prof. Bhartendu Kumar Singh \n",
"Director \n",
"PDPM-IIITDM Jabalpur \n",
"director@iiitdmj.ac.in\n",
"--------------------\n",
"\n",
"--- Document 3 ---\n",
"Source: data/iiitdmj_crawl_data_1.pdf\n",
"Page: 133\n",
"\n",
"Content:\n",
"S. No.\n",
"Name\n",
"Address\n",
"1.\n",
"Director as Chairperson (Ex-officio)\n",
"Prof. Bhartendu K Singh (Director)\n",
"director@iiitdmj.ac.in\n",
"2.\n",
"Deputy Director\n",
"To be nominated on appointment\n",
"3.\n",
"Deans (Ex-officio)\n",
"1. Dr. Mukesh Kumar Roy\n",
"Faculty-in-Charge (Student Affairs)\n",
"mkroy@iiitdmj.ac.in\n",
"2. Prof. V. K. Gupta\n",
"--------------------\n"
]
}
],
"source": [
"import sys\n",
"from langchain_community.vectorstores import FAISS\n",
"from langchain_community.embeddings import HuggingFaceEmbeddings\n",
"\n",
"\n",
"def check_retriever():\n",
" \"\"\"\n",
" A standalone script to test the FAISS retriever.\n",
" \"\"\"\n",
" \n",
" # 1. Load the Embedding Model\n",
" print(f\"Loading embedding model: {MODEL_NAME}...\")\n",
" try:\n",
" # This line might show a deprecation warning, which is OK.\n",
" # It's the same one your agent.py is using.\n",
" embeddings = HuggingFaceEmbeddings(model_name=MODEL_NAME)\n",
" except Exception as e:\n",
" print(f\"Error loading embeddings: {e}\")\n",
" print(\"Make sure 'sentence-transformers' is installed: pip install sentence-transformers\")\n",
" return\n",
"\n",
" # # 2. Load the FAISS Vector Store\n",
" # print(f\"Loading FAISS index from: {DB_FAISS_PATH}...\")\n",
" # try:\n",
" # db = FAISS.load_local(\n",
" # DB_FAISS_PATH, \n",
" # embeddings, \n",
" # allow_dangerous_deserialization=True # This is required\n",
" # )\n",
" # except Exception as e:\n",
" # print(f\"Error loading FAISS index: {e}\")\n",
" # print(\"Be sure you have run 'python ingest.py' successfully first.\")\n",
" # return\n",
"\n",
" retriever = db.as_retriever(search_kwargs={'k': 3})\n",
" \n",
" print(\"\\n✅ Retriever is ready.\")\n",
" print(\" Enter your query to test. Type 'exit' to quit.\")\n",
" \n",
" while True:\n",
" try:\n",
" query = input(\"\\nQuery> \")\n",
" if query.lower() == 'exit':\n",
" break\n",
" if not query:\n",
" continue\n",
" \n",
" print(f\"\\n--- Retrieving docs for: '{query}' ---\")\n",
" \n",
" documents = retriever.invoke(query)\n",
" \n",
" if not documents:\n",
" print(\"\\n!!! No documents found. !!!\")\n",
" else:\n",
" for i, doc in enumerate(documents):\n",
" print(f\"\\n--- Document {i+1} ---\")\n",
" print(f\"Source: {doc.metadata.get('source', 'N/A')}\")\n",
" print(f\"Page: {doc.metadata.get('page', 'N/A')}\")\n",
" print(\"\\nContent:\")\n",
" print(doc.page_content)\n",
" print(\"-\" * 20)\n",
" \n",
" except Exception as e:\n",
" print(f\"An error occurred: {e}\")\n",
"\n",
"if __name__ == \"__main__\":\n",
" check_retriever()\n"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "45430224",
"metadata": {},
"outputs": [],
"source": [
"DB_FAISS_PATH = \"vectorstore/faiss_index2\"\n"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "9488f2a3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Successfully created and saved FAISS index to vectorstore/faiss_index2\n"
]
}
],
"source": [
"db = FAISS.from_documents(docs, embeddings)\n",
"db.save_local(DB_FAISS_PATH)\n",
"\n",
"print(f\"Successfully created and saved FAISS index to {DB_FAISS_PATH}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bef0e8c2",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"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": "3.13.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|