src/FAISS.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create vectorstore\n",
    "import pandas as pd\n",
    "from vectordatabase import load_documents\n",
    "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
    "from langchain_community.vectorstores import FAISS\n",
    "\n",
    "\n",
    "df = pd.read_pickle(\"C:\\\\Users\\Tom\\SynologyDrive\\Programming\\\\NLP\\PoliticsToYou\\ChatBot\\Speeches\\speeches_1949_09_12.pkl\")\n",
    "# Split speeches into documents\n",
    "documents = load_documents(df)\n",
    "embeddings = HuggingFaceEmbeddings(model_name=\"paraphrase-multilingual-MiniLM-L12-v2\")\n",
    "db = FAISS.from_documents(documents, embeddings)\n",
    "db.save_local(folder_path=\"ChatBot\\FAISS\", index_name=\"speeches_1949_09_12\")\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}