{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "cc06fe17-c615-453a-9d54-b04f861ee732",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from dotenv import load_dotenv, find_dotenv\n",
    "load_dotenv(find_dotenv())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9495c8de-b218-436b-8145-78b222ed4545",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n\\nA large language model is a type of artificial intelligence (AI) system that uses a large set of text data to generate text-based predictions and generate new data.'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.llms import OpenAI\n",
    "llm = OpenAI(model_name=\"text-davinci-003\")\n",
    "llm(\"explain large language model in one sentence\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3cf04b99-b937-4fec-a5f1-093b638245b9",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.schema import (\n",
    "    AIMessage,\n",
    "    HumanMessage,\n",
    "    SystemMessage\n",
    ")\n",
    "from langchain.chat_models import ChatOpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6b42d0b0-d353-483f-994c-0ae45af8e7f8",
   "metadata": {},
   "outputs": [],
   "source": [
    "chat = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0.3)\n",
    "messages= [\n",
    "    SystemMessage(content=\"You are an expert data scientist\"),\n",
    "    HumanMessage(content=\"Write a python script that trains a neural network on stimulated data\")\n",
    "]\n",
    "response=chat(messages)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3b07b556-21cc-4c36-9d80-4f1fd2d83cba",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sure! Here's an example of a Python script that trains a neural network on simulated data using the Keras library:\n",
      "\n",
      "```python\n",
      "import numpy as np\n",
      "from keras.models import Sequential\n",
      "from keras.layers import Dense\n",
      "\n",
      "# Generate simulated data\n",
      "np.random.seed(0)\n",
      "X = np.random.rand(100, 2)\n",
      "y = np.random.randint(2, size=100)\n",
      "\n",
      "# Define the neural network model\n",
      "model = Sequential()\n",
      "model.add(Dense(10, input_dim=2, activation='relu'))\n",
      "model.add(Dense(1, activation='sigmoid'))\n",
      "\n",
      "# Compile the model\n",
      "model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
      "\n",
      "# Train the model\n",
      "model.fit(X, y, epochs=10, batch_size=10)\n",
      "\n",
      "# Evaluate the model\n",
      "loss, accuracy = model.evaluate(X, y)\n",
      "print(f\"Loss: {loss}, Accuracy: {accuracy}\")\n",
      "```\n",
      "\n",
      "In this script, we first generate simulated data using `np.random.rand()` and `np.random.randint()` functions. The input data `X` is a 2-dimensional array of random values between 0 and 1, and the target labels `y` are binary values (0 or 1).\n",
      "\n",
      "We then define a simple neural network model using the `Sequential` class from Keras. It consists of a single hidden layer with 10 neurons and a ReLU activation function, followed by an output layer with a single neuron and a sigmoid activation function.\n",
      "\n",
      "The model is compiled with the binary cross-entropy loss function and the Adam optimizer. We then train the model using the `fit()` function, specifying the number of epochs and batch size.\n",
      "\n",
      "Finally, we evaluate the trained model on the same data and print the loss and accuracy.\n"
     ]
    }
   ],
   "source": [
    "print(response.content, end='\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "30193256-290b-4c90-b91c-33ae893a271d",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}