{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "17bdd3247ce44ac49503de2fabfba776",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Epoch:   0%|          | 0/1 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d986dbe5bc614721aa5a48a74ef71d02",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Iteration:   0%|          | 0/178 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MODEL TRAINED\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[38], line 62\u001b[0m\n\u001b[1;32m     60\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m index, row \u001b[38;5;129;01min\u001b[39;00m data\u001b[38;5;241m.\u001b[39miterrows():\n\u001b[1;32m     61\u001b[0m     combined_text_tokens \u001b[38;5;241m=\u001b[39m preprocess_and_tokenize(row[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcombined_text\u001b[39m\u001b[38;5;124m'\u001b[39m])\n\u001b[0;32m---> 62\u001b[0m     embedding \u001b[38;5;241m=\u001b[39m \u001b[43mfine_tuned_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcombined_text_tokens\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     63\u001b[0m     vector_database[index] \u001b[38;5;241m=\u001b[39m embedding\n\u001b[1;32m     64\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mPKL IS SAVING\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/sentence_transformers/SentenceTransformer.py:165\u001b[0m, in \u001b[0;36mSentenceTransformer.encode\u001b[0;34m(self, sentences, batch_size, show_progress_bar, output_value, convert_to_numpy, convert_to_tensor, device, normalize_embeddings)\u001b[0m\n\u001b[1;32m    162\u001b[0m features \u001b[38;5;241m=\u001b[39m batch_to_device(features, device)\n\u001b[1;32m    164\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mno_grad():\n\u001b[0;32m--> 165\u001b[0m     out_features \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mforward\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfeatures\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    167\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m output_value \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtoken_embeddings\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m    168\u001b[0m         embeddings \u001b[38;5;241m=\u001b[39m []\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/container.py:215\u001b[0m, in \u001b[0;36mSequential.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    213\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m):\n\u001b[1;32m    214\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m module \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m:\n\u001b[0;32m--> 215\u001b[0m         \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m    216\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28minput\u001b[39m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1525\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/sentence_transformers/models/Transformer.py:66\u001b[0m, in \u001b[0;36mTransformer.forward\u001b[0;34m(self, features)\u001b[0m\n\u001b[1;32m     63\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtoken_type_ids\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01min\u001b[39;00m features:\n\u001b[1;32m     64\u001b[0m     trans_features[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtoken_type_ids\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m features[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtoken_type_ids\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[0;32m---> 66\u001b[0m output_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mauto_model\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtrans_features\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m     67\u001b[0m output_tokens \u001b[38;5;241m=\u001b[39m output_states[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m     69\u001b[0m features\u001b[38;5;241m.\u001b[39mupdate({\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtoken_embeddings\u001b[39m\u001b[38;5;124m'\u001b[39m: output_tokens, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mattention_mask\u001b[39m\u001b[38;5;124m'\u001b[39m: features[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mattention_mask\u001b[39m\u001b[38;5;124m'\u001b[39m]})\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1525\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/transformers/models/bert/modeling_bert.py:1013\u001b[0m, in \u001b[0;36mBertModel.forward\u001b[0;34m(self, input_ids, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m   1004\u001b[0m head_mask \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_head_mask(head_mask, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mnum_hidden_layers)\n\u001b[1;32m   1006\u001b[0m embedding_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39membeddings(\n\u001b[1;32m   1007\u001b[0m     input_ids\u001b[38;5;241m=\u001b[39minput_ids,\n\u001b[1;32m   1008\u001b[0m     position_ids\u001b[38;5;241m=\u001b[39mposition_ids,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1011\u001b[0m     past_key_values_length\u001b[38;5;241m=\u001b[39mpast_key_values_length,\n\u001b[1;32m   1012\u001b[0m )\n\u001b[0;32m-> 1013\u001b[0m encoder_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1014\u001b[0m \u001b[43m    \u001b[49m\u001b[43membedding_output\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1015\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextended_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1016\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1017\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1018\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_extended_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1019\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1020\u001b[0m \u001b[43m    \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1021\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1022\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1023\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1024\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1025\u001b[0m sequence_output \u001b[38;5;241m=\u001b[39m encoder_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m   1026\u001b[0m pooled_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpooler(sequence_output) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpooler \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1525\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/transformers/models/bert/modeling_bert.py:607\u001b[0m, in \u001b[0;36mBertEncoder.forward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m    596\u001b[0m     layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gradient_checkpointing_func(\n\u001b[1;32m    597\u001b[0m         layer_module\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m,\n\u001b[1;32m    598\u001b[0m         hidden_states,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    604\u001b[0m         output_attentions,\n\u001b[1;32m    605\u001b[0m     )\n\u001b[1;32m    606\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 607\u001b[0m     layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[43mlayer_module\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    608\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    609\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    610\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlayer_head_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    611\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    612\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    613\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    614\u001b[0m \u001b[43m        \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    615\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    617\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m layer_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m    618\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m use_cache:\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1525\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/transformers/models/bert/modeling_bert.py:497\u001b[0m, in \u001b[0;36mBertLayer.forward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[1;32m    485\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\n\u001b[1;32m    486\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    487\u001b[0m     hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    494\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]:\n\u001b[1;32m    495\u001b[0m     \u001b[38;5;66;03m# decoder uni-directional self-attention cached key/values tuple is at positions 1,2\u001b[39;00m\n\u001b[1;32m    496\u001b[0m     self_attn_past_key_value \u001b[38;5;241m=\u001b[39m past_key_value[:\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m past_key_value \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m--> 497\u001b[0m     self_attention_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mattention\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    498\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    499\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    500\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    501\u001b[0m \u001b[43m        \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    502\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mself_attn_past_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    503\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    504\u001b[0m     attention_output \u001b[38;5;241m=\u001b[39m self_attention_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m    506\u001b[0m     \u001b[38;5;66;03m# if decoder, the last output is tuple of self-attn cache\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1525\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/transformers/models/bert/modeling_bert.py:436\u001b[0m, in \u001b[0;36mBertAttention.forward\u001b[0;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[1;32m    417\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\n\u001b[1;32m    418\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    419\u001b[0m     hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    425\u001b[0m     output_attentions: Optional[\u001b[38;5;28mbool\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m    426\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]:\n\u001b[1;32m    427\u001b[0m     self_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mself(\n\u001b[1;32m    428\u001b[0m         hidden_states,\n\u001b[1;32m    429\u001b[0m         attention_mask,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    434\u001b[0m         output_attentions,\n\u001b[1;32m    435\u001b[0m     )\n\u001b[0;32m--> 436\u001b[0m     attention_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moutput\u001b[49m\u001b[43m(\u001b[49m\u001b[43mself_outputs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    437\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (attention_output,) \u001b[38;5;241m+\u001b[39m self_outputs[\u001b[38;5;241m1\u001b[39m:]  \u001b[38;5;66;03m# add attentions if we output them\u001b[39;00m\n\u001b[1;32m    438\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m outputs\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1525\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/transformers/models/bert/modeling_bert.py:386\u001b[0m, in \u001b[0;36mBertSelfOutput.forward\u001b[0;34m(self, hidden_states, input_tensor)\u001b[0m\n\u001b[1;32m    385\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor, input_tensor: torch\u001b[38;5;241m.\u001b[39mTensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m torch\u001b[38;5;241m.\u001b[39mTensor:\n\u001b[0;32m--> 386\u001b[0m     hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdense\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    387\u001b[0m     hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdropout(hidden_states)\n\u001b[1;32m    388\u001b[0m     hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mLayerNorm(hidden_states \u001b[38;5;241m+\u001b[39m input_tensor)\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1518\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1516\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1517\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1518\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/module.py:1527\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1522\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1523\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1524\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1525\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1526\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1527\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1529\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1530\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/Projects/semantic-search/venv/lib/python3.9/site-packages/torch/nn/modules/linear.py:114\u001b[0m, in \u001b[0;36mLinear.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m    113\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 114\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241m.\u001b[39mlinear(\u001b[38;5;28minput\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mweight, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbias)\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sentence_transformers import SentenceTransformer, InputExample, SentencesDataset, losses\n",
    "from torch.utils.data import DataLoader\n",
    "from sklearn.model_selection import train_test_split\n",
    "import pickle\n",
    "import nltk\n",
    "import re\n",
    "\n",
    "\n",
    "\n",
    "# Function for basic text preprocessing and tokenization\n",
    "def preprocess_and_tokenize(text):\n",
    "    # Remove non-English words\n",
    "    english_words = set(nltk.corpus.words.words())\n",
    "    text = \" \".join(w if w.lower() in english_words or not w.isalpha() else '' for w in text.split())\n",
    "    \n",
    "    # Remove special characters\n",
    "    text = re.sub(r'[^A-Za-z0-9 ]+', '', text)\n",
    "    \n",
    "    # Tokenization using nltk\n",
    "    tokens = nltk.word_tokenize(text)\n",
    "    \n",
    "    return tokens\n",
    "\n",
    "data = pd.read_csv('book_data.csv')\n",
    "\n",
    "data = data.dropna(subset=['Description', 'Reviews'])\n",
    "\n",
    "# Combine \"Description\" and \"Reviews\" columns for training\n",
    "data['combined_text'] = data['Description'] + ' ' + data['Reviews']\n",
    "\n",
    "train_data, test_data = train_test_split(data, test_size=0.2, random_state=42)\n",
    "\n",
    "model_name = 'sentence-transformers/paraphrase-MiniLM-L6-v2'\n",
    "model = SentenceTransformer(model_name, device='cpu')\n",
    "\n",
    "train_examples = []\n",
    "for index, row in train_data.iterrows():\n",
    "    combined_text_tokens = preprocess_and_tokenize(row['combined_text'])\n",
    "    input_example = InputExample(texts=[combined_text_tokens, combined_text_tokens], label=float(index))\n",
    "    train_examples.append(input_example)\n",
    "\n",
    "train_dataset = SentencesDataset(train_examples, model=model)\n",
    "train_dataloader = DataLoader(train_dataset, shuffle=True, batch_size=8)\n",
    "train_loss = losses.CosineSimilarityLoss(model=model)\n",
    "\n",
    "model_save_path = 'fine_tuned_model_combined'\n",
    "model.fit(\n",
    "    train_objectives=[(train_dataloader, train_loss)],\n",
    "    epochs=1,\n",
    "    warmup_steps=100,\n",
    "    output_path=model_save_path\n",
    ")\n",
    "\n",
    "fine_tuned_model = SentenceTransformer(model_save_path)\n",
    "\n",
    "print('MODEL TRAINED')\n",
    "\n",
    "vector_database = {}\n",
    "for index, row in data.iterrows():\n",
    "    combined_text_tokens = preprocess_and_tokenize(row['combined_text'])\n",
    "    embedding = fine_tuned_model.encode(combined_text_tokens)\n",
    "    vector_database[index] = embedding\n",
    "\n",
    "print('PKL IS SAVING')\n",
    "with open('vector_database_combined.pkl', 'wb') as file:\n",
    "    pickle.dump(vector_database, file)\n",
    "print('PKL IS SAVED')\n",
    "print('MODEL SAVING')\n",
    "fine_tuned_model.save('fine_tuned_model_combined')\n",
    "print('MODEL IS SAVED')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Title: The Bible of Karate: Bubishi, Score: 0.9921729564666748\n",
      "Description: Philosophy, strategy and medicine as related to the martial arts, translated with commentary.\n",
      "-----------\n",
      "Title: Antony and Cleopatra, Score: 0.9921565055847168\n",
      "Description: A romantic tragedy about the relationship between Mark Antony and the Queen of Egypt, including notes and critical commentary.\n",
      "-----------\n",
      "Title: Last Chance to See, Score: 0.9920206069946289\n",
      "Description: Join author Douglas Adams and zoologist Mark Carwardine as they take off around the world in search of exotic, endangered creatures.\n",
      "-----------\n",
      "Title: Out for Blood, Score: 0.9934567809104919\n",
      "Description: Harvey, Alyxandra\n",
      "-----------\n",
      "Title: Man-eating Leopard of Rudraprayag, Score: 0.9949787855148315\n",
      "Description: book, paperback, leopard\n",
      "-----------\n",
      "Title: A Visual Dictionary of Architecture, Score: 0.9938178658485413\n",
      "Description: A Visual Dictionary of Architecture\n",
      "-----------\n",
      "Title: Rock the Beginning, Score: 0.994428813457489\n",
      "Description: ROCK THE BEGININING (Black Falcon Prequel) Full Story\n",
      "-----------\n",
      "Title: S, M, L, XL, Score: 0.9926852583885193\n",
      "Description: Book by Rem Koolhaas, Bruce Mau\n",
      "-----------\n",
      "Title: Living the Martial Way: A Manual for the Way a Modern Warrior Should Think, Score: 0.9918533563613892\n",
      "Description: A step-by-step approach to applying the Japanese warrior's mind set to martial training and daily life.\n",
      "-----------\n",
      "Title: An Encyclopedia of Claims, Frauds, and Hoaxes of the Occult and Supernatural, Score: 0.9930614829063416\n",
      "Description: Covers illusions, psychics, mystics, clairvoyants, and frauds\n",
      "-----------\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sentence_transformers import SentenceTransformer, util\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sentence_transformers import SentencesDataset, losses\n",
    "from torch.utils.data import DataLoader\n",
    "from sentence_transformers import InputExample\n",
    "from sentence_transformers.util import pytorch_cos_sim\n",
    "from sentence_transformers.evaluation import EmbeddingSimilarityEvaluator\n",
    "from datetime import datetime\n",
    "import torch\n",
    "def semantic_search(query, vector_database, model):\n",
    "    query_embedding = model.encode(query)\n",
    "    \n",
    "    # Convert NumPy arrays to PyTorch tensors\n",
    "    corpus_embeddings = torch.stack([torch.from_numpy(embedding) for embedding in vector_database.values()])\n",
    "    \n",
    "    # Use the PyTorch tensors in semantic_search\n",
    "    hits = util.semantic_search(query_embedding, corpus_embeddings)\n",
    "    \n",
    "    results = [{'index': hit['corpus_id'], 'score': hit['score']} for hit in hits[0]]\n",
    "    return results\n",
    "\n",
    "def rerank_results(query, results, model):\n",
    "    query_embedding = model.encode(query)\n",
    "    reranked_results = sorted(results, key=lambda x: pytorch_cos_sim(query_embedding, vector_database[x['index']]), reverse=True)\n",
    "    return reranked_results\n",
    "\n",
    "query = \"Romance and Adventure\"\n",
    "results = semantic_search(query, vector_database, fine_tuned_model)\n",
    "reranked_results = rerank_results(query, results, fine_tuned_model)\n",
    "\n",
    "for result in reranked_results:\n",
    "    index = result['index']\n",
    "    print(f\"Title: {data.iloc[index]['Title']}, Score: {result['score']}\")\n",
    "    print(f\"Description: {data.iloc[index]['Description']}\")\n",
    "    print(\"-----------\")"
   ]
  }
 ],
 "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}