{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2025-01-12 10:07:12,956 INFO: PyTorch version 2.5.1 available.\n"
     ]
    }
   ],
   "source": [
    "import hopsworks\n",
    "from sentence_transformers import SentenceTransformer, InputExample, losses\n",
    "from torch.utils.data import DataLoader\n",
    "from sklearn.model_selection import train_test_split\n",
    "from dotenv import load_dotenv\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2025-01-12 10:07:14,851 INFO: Initializing external client\n",
      "2025-01-12 10:07:14,852 INFO: Base URL: https://c.app.hopsworks.ai:443\n",
      "2025-01-12 10:07:15,245 WARNING: InsecureRequestWarning: Unverified HTTPS request is being made to host 'c.app.hopsworks.ai'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings\n",
      "\n",
      "2025-01-12 10:07:18,039 INFO: Python Engine initialized.\n",
      "\n",
      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/1158296\n"
     ]
    }
   ],
   "source": [
    "# Initialize Hopsworks connection\n",
    "load_dotenv()\n",
    "\n",
    "api_key = os.getenv(\"HOPSWORKS_API_KEY\")\n",
    "project = hopsworks.login(project=\"orestavf\", api_key_value=api_key)\n",
    "fs = project.get_feature_store()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Finished: Reading data from Hopsworks, using Hopsworks Feature Query Service (2.46s) \n"
     ]
    }
   ],
   "source": [
    "# Load preprocessed data\n",
    "feedback_fg = fs.get_feature_group(name=\"job_feedback\", version=1)\n",
    "feedback_df = feedback_fg.read()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Split into train and validation sets\n",
    "train_df, val_df = train_test_split(feedback_df, test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Prepare data for SentenceTransformer\n",
    "def prepare_examples(df):\n",
    "    examples = []\n",
    "    for _, row in df.iterrows():\n",
    "        examples.append(\n",
    "            InputExample(\n",
    "                texts=[row[\"resume_text\"], row[\"job_description\"]],\n",
    "                label=float(row[\"is_relevant\"])  # Convert to float for loss calculation\n",
    "            )\n",
    "        )\n",
    "    return examples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_examples = prepare_examples(train_df)\n",
    "val_examples = prepare_examples(val_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2025-01-12 10:07:23,794 INFO: Use pytorch device_name: cpu\n",
      "2025-01-12 10:07:23,795 INFO: Load pretrained SentenceTransformer: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2\n"
     ]
    }
   ],
   "source": [
    "# Load pretrained SentenceTransformer\n",
    "model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define DataLoader\n",
    "train_dataloader = DataLoader(train_examples, shuffle=True, batch_size=16)\n",
    "val_dataloader = DataLoader(val_examples, shuffle=False, batch_size=16)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define loss\n",
    "train_loss = losses.CosineSimilarityLoss(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Configure training\n",
    "num_epochs = 3\n",
    "warmup_steps = int(len(train_dataloader) * num_epochs * 0.1)  # 10% of training as warmup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "13a4c4779de349a4a93c26a2a952d713",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/6 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'train_runtime': 16.1772, 'train_samples_per_second': 4.265, 'train_steps_per_second': 0.371, 'train_loss': 0.18365144729614258, 'epoch': 3.0}\n",
      "2025-01-12 10:07:44,670 INFO: Save model to ./finetuned_model\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a36ca79a9a5245c3931717a3c466bba9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Computing widget examples:   0%|          | 0/1 [00:00<?, ?example/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Train the model\n",
    "model.fit(\n",
    "    train_objectives=[(train_dataloader, train_loss)],\n",
    "    evaluator=None,  # Add an evaluator if needed\n",
    "    epochs=num_epochs,\n",
    "    warmup_steps=warmup_steps,\n",
    "    output_path=\"./finetuned_model\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save the trained model locally\n",
    "#model.save(\"./finetuned_model\")\n",
    "#print(\"Model finetuned and saved locally!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "from hsml.schema import Schema\n",
    "from hsml.model_schema import ModelSchema"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the Model Schema\n",
    "X_train_sample = train_df[[\"resume_text\", \"job_description\"]].sample(1).values  # Input example\n",
    "y_train_sample = train_df[\"is_relevant\"].sample(1).values  # Output example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_schema = Schema(X_train_sample)\n",
    "output_schema = Schema(y_train_sample)\n",
    "model_schema = ModelSchema(input_schema=input_schema, output_schema=output_schema)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2025-01-12 10:07:45,746 WARNING: InsecureRequestWarning: Unverified HTTPS request is being made to host 'c.app.hopsworks.ai'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Get Model Registry\n",
    "mr = project.get_model_registry()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2025-01-12 10:08:24,657 WARNING: VersionWarning: No version provided for getting model `job_matching_sentence_transformer`, defaulting to `1`.\n",
      "\n",
      "Model already exists with version 1\n"
     ]
    }
   ],
   "source": [
    "# Check if the model already exists and get the latest version\n",
    "try:\n",
    "    existing_model = mr.get_model(name=\"job_matching_sentence_transformer\")\n",
    "    latest_version = existing_model.version\n",
    "    print(f\"Model already exists with version {latest_version}\")\n",
    "except:\n",
    "    # If the model doesn't exist, set version to 1\n",
    "    latest_version = 0\n",
    "\n",
    "# Set the new version dynamically\n",
    "new_version = latest_version + 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Register the model in the Model Registry\n",
    "job_matching_model = mr.python.create_model(\n",
    "    name=\"job_matching_sentence_transformer\",\n",
    "    #metrics=metrics,\n",
    "    model_schema=model_schema,\n",
    "    input_example=X_train_sample,\n",
    "    description=\"Finetuned SentenceTransformer for job matching\",\n",
    "    version=new_version,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "78d7674e395848acb4586dd4dff1fee8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/6 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ff6231d9469840229d992abb28a5740b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/727 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "53650ea045a24041a44626336d9a9c9b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/212 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "21e688c69c7a46a4bb7485d1d088c887",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/470637416 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c68dc00bc2ae4804b73780d0f23e21ba",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/242 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bb846d6b71b746749d59c0bf25779f61",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/21034 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "afda6046a57c42dca546be6defd13f11",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/56 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "df4c630a40954b9784a2a631be4ed4e3",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/1015 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4c6430695b7e43c0815fe278328e0448",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/17082987 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a1aa72dd0b344a26b22d8839aa12c4fb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/1512 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2b599ffc95d4499b80673d873b6dfe7a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/14763260 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "fa11d5018fcb4ab094dac6c27128bcf5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/305 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7e37354a957d45b88b7a25007b3c7889",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/6678 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f4e0c3e6d64b457bb01e5a0ac2162433",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading: 0.000%|          | 0/216 elapsed<00:00 remaining<?"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model created, explore it at https://c.app.hopsworks.ai:443/p/1158296/models/job_matching_sentence_transformer/1\n",
      "Model registered in Hopsworks Model Registry!\n"
     ]
    }
   ],
   "source": [
    "# Save model artifacts to the Model Registry\n",
    "job_matching_model.save(\"./finetuned_model\")\n",
    "print(\"Model registered in Hopsworks Model Registry!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "ename": "HfHubHTTPError",
     "evalue": "409 Client Error: Conflict for url: https://huggingface.co/api/repos/create (Request ID: Root=1-678391c6-22b5b53a19ac4add675f0e05;3fa72b47-baef-4170-8fe3-772ad458534e)\n\nYou already created this model repo",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mHTTPError\u001b[0m                                 Traceback (most recent call last)",
      "File \u001b[1;32mc:\\Users\\Filip\\jobsai\\venv\\Lib\\site-packages\\huggingface_hub\\utils\\_http.py:406\u001b[0m, in \u001b[0;36mhf_raise_for_status\u001b[1;34m(response, endpoint_name)\u001b[0m\n\u001b[0;32m    405\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 406\u001b[0m     \u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    407\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m HTTPError \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[1;32mc:\\Users\\Filip\\jobsai\\venv\\Lib\\site-packages\\requests\\models.py:1024\u001b[0m, in \u001b[0;36mResponse.raise_for_status\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m   1023\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m http_error_msg:\n\u001b[1;32m-> 1024\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m HTTPError(http_error_msg, response\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m)\n",
      "\u001b[1;31mHTTPError\u001b[0m: 409 Client Error: Conflict for url: https://huggingface.co/api/repos/create",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[1;31mHfHubHTTPError\u001b[0m                            Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[20], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# Push the model to huggingface\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpush_to_hub\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mforestav/job_matching_sentence_transformer\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32mc:\\Users\\Filip\\jobsai\\venv\\Lib\\site-packages\\sentence_transformers\\SentenceTransformer.py:1370\u001b[0m, in \u001b[0;36mSentenceTransformer.push_to_hub\u001b[1;34m(self, repo_id, token, private, safe_serialization, commit_message, local_model_path, exist_ok, replace_model_card, train_datasets, revision, create_pr)\u001b[0m\n\u001b[0;32m   1350\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   1351\u001b[0m \u001b[38;5;124;03mUploads all elements of this Sentence Transformer to a new HuggingFace Hub repository.\u001b[39;00m\n\u001b[0;32m   1352\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1367\u001b[0m \u001b[38;5;124;03m    str: The url of the commit of your model in the repository on the Hugging Face Hub.\u001b[39;00m\n\u001b[0;32m   1368\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   1369\u001b[0m api \u001b[38;5;241m=\u001b[39m HfApi(token\u001b[38;5;241m=\u001b[39mtoken)\n\u001b[1;32m-> 1370\u001b[0m repo_url \u001b[38;5;241m=\u001b[39m \u001b[43mapi\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate_repo\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1371\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1372\u001b[0m \u001b[43m    \u001b[49m\u001b[43mprivate\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprivate\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1373\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m   1374\u001b[0m \u001b[43m    \u001b[49m\u001b[43mexist_ok\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexist_ok\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mcreate_pr\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1375\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1376\u001b[0m repo_id \u001b[38;5;241m=\u001b[39m repo_url\u001b[38;5;241m.\u001b[39mrepo_id  \u001b[38;5;66;03m# Update the repo_id in case the old repo_id didn't contain a user or organization\u001b[39;00m\n\u001b[0;32m   1377\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_card_data\u001b[38;5;241m.\u001b[39mset_model_id(repo_id)\n",
      "File \u001b[1;32mc:\\Users\\Filip\\jobsai\\venv\\Lib\\site-packages\\huggingface_hub\\utils\\_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[0;32m    112\u001b[0m     kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[1;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\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[1;32mc:\\Users\\Filip\\jobsai\\venv\\Lib\\site-packages\\huggingface_hub\\hf_api.py:3525\u001b[0m, in \u001b[0;36mHfApi.create_repo\u001b[1;34m(self, repo_id, token, private, repo_type, exist_ok, resource_group_id, space_sdk, space_hardware, space_storage, space_sleep_time, space_secrets, space_variables)\u001b[0m\n\u001b[0;32m   3522\u001b[0m     \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[0;32m   3524\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m-> 3525\u001b[0m     \u001b[43mhf_raise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43mr\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   3526\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m HTTPError \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[0;32m   3527\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m exist_ok \u001b[38;5;129;01mand\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m409\u001b[39m:\n\u001b[0;32m   3528\u001b[0m         \u001b[38;5;66;03m# Repo already exists and `exist_ok=True`\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\Filip\\jobsai\\venv\\Lib\\site-packages\\huggingface_hub\\utils\\_http.py:477\u001b[0m, in \u001b[0;36mhf_raise_for_status\u001b[1;34m(response, endpoint_name)\u001b[0m\n\u001b[0;32m    473\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m _format(HfHubHTTPError, message, response) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[0;32m    475\u001b[0m \u001b[38;5;66;03m# Convert `HTTPError` into a `HfHubHTTPError` to display request information\u001b[39;00m\n\u001b[0;32m    476\u001b[0m \u001b[38;5;66;03m# as well (request id and/or server error message)\u001b[39;00m\n\u001b[1;32m--> 477\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m _format(HfHubHTTPError, \u001b[38;5;28mstr\u001b[39m(e), response) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
      "\u001b[1;31mHfHubHTTPError\u001b[0m: 409 Client Error: Conflict for url: https://huggingface.co/api/repos/create (Request ID: Root=1-678391c6-22b5b53a19ac4add675f0e05;3fa72b47-baef-4170-8fe3-772ad458534e)\n\nYou already created this model repo"
     ]
    }
   ],
   "source": [
    "# Push the model to huggingface\n",
    "model.push_to_hub(repo_id=\"forestav/job_matching_sentence_transformer\", exist_ok=True)"
   ]
  }
 ],
 "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": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}