quickstart.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os \n",
    "import warnings \n",
    "from dotenv import load_dotenv \n",
    "\n",
    "load_dotenv() \n",
    "\n",
    "PINECONE_API_KEY = os.getenv(\"PINECONE_API_KEY\") \n",
    "OPENAI_API_KEY = os.getenv(\"OPENAI_API_KEY\")\n",
    "\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content='Large language models are advanced artificial intelligence systems that are capable of understanding and generating human-like text based on vast amounts of training data.', response_metadata={'token_usage': {'completion_tokens': 26, 'prompt_tokens': 15, 'total_tokens': 41}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-6d30ef1b-72ed-4e1a-acdb-a17abaf8fbdd-0', usage_metadata={'input_tokens': 15, 'output_tokens': 26, 'total_tokens': 41})"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "from langchain_openai.chat_models import ChatOpenAI\n",
    "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", api_key=OPENAI_API_KEY)\n",
    "llm(\"Explain large language models in one sentence\") "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.schema import (\n",
    "    AIMessage,\n",
    "    HumanMessage,\n",
    "    SystemMessage\n",
    ") \n",
    "\n",
    "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 simulated data.\") \n",
    "]\n",
    "response = chat(messages) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Here is a simple example of a Python script that trains a neural network on simulated data using the TensorFlow library:\n",
      "\n",
      "```python\n",
      "import numpy as np\n",
      "import tensorflow as tf\n",
      "\n",
      "# Generate simulated data\n",
      "X = np.random.rand(1000, 10)\n",
      "y = np.random.randint(0, 2, 1000)\n",
      "\n",
      "# Define the neural network architecture\n",
      "model = tf.keras.models.Sequential([\n",
      "    tf.keras.layers.Dense(64, activation='relu', input_shape=(10,)),\n",
      "    tf.keras.layers.Dense(64, activation='relu'),\n",
      "    tf.keras.layers.Dense(1, activation='sigmoid')\n",
      "])\n",
      "\n",
      "# Compile the model\n",
      "model.compile(optimizer='adam',\n",
      "              loss='binary_crossentropy',\n",
      "              metrics=['accuracy'])\n",
      "\n",
      "# Train the model\n",
      "model.fit(X, y, epochs=10, batch_size=32)\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:\n",
      "1. We generate simulated data `X` and `y`.\n",
      "2. We define a simple neural network model with 2 hidden layers and an output layer.\n",
      "3. We compile the model with Adam optimizer and binary crossentropy loss.\n",
      "4. We train the model on the simulated data for 10 epochs.\n",
      "5. We evaluate the model on the same data and print the loss and accuracy.\n",
      "\n",
      "You can run this script in a Python environment with TensorFlow installed to train a neural network on simulated data.\n"
     ]
    }
   ],
   "source": [
    "print(response.content, end='\\n')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PromptTemplate(input_variables=['concept'], template=' \\nYou are an expert data scientist with an expetise in building deep learning models. \\nExplain the concept {concept} in a couple of lines.\\n')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Prompt Templates\n",
    "from langchain import PromptTemplate \n",
    "\n",
    "template = \"\"\" \n",
    "You are an expert data scientist with an expetise in building deep learning models. \n",
    "Explain the concept {concept} in a couple of lines.\n",
    "\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(\n",
    "    input_variables=[\"concept\"], \n",
    "    template=template\n",
    ") \n",
    "prompt "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content='Regularization is a technique used in machine learning to prevent overfitting by adding a penalty term to the loss function. This penalty term discourages overly complex models, leading to better generalization and improved performance on unseen data.', response_metadata={'token_usage': {'completion_tokens': 45, 'prompt_tokens': 37, 'total_tokens': 82}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-345beb34-b9af-4e1f-8c51-6495243fbdde-0', usage_metadata={'input_tokens': 37, 'output_tokens': 45, 'total_tokens': 82})"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm(prompt.format(concept=\"regularization\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content='Bagging, or Bootstrap Aggregating, is a machine learning technique that involves training multiple models on different subsets of the training data and then combining their predictions to generate a final output. This helps to reduce overfitting and improve the overall accuracy and stability of the model.', response_metadata={'token_usage': {'completion_tokens': 55, 'prompt_tokens': 38, 'total_tokens': 93}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-63055b9f-c4d3-4484-880e-68b057b91ca9-0', usage_metadata={'input_tokens': 38, 'output_tokens': 55, 'total_tokens': 93})"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm(prompt.format(concept=\"bagging\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "An autoencoder is a type of artificial neural network used for unsupervised learning that aims to encode input data into a more compressed representation and then decode it back to the original input with minimal loss of information. It is commonly used for tasks such as image and text data compression, anomaly detection, and feature extraction.\n"
     ]
    }
   ],
   "source": [
    "# Chains\n",
    "from langchain.chains import LLMChain \n",
    "\n",
    "chain = LLMChain(llm=llm, prompt=prompt) \n",
    "\n",
    "# Run the chain only specifying the input variable \n",
    "print(chain.run(\"autoencoder\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LLMChain(prompt=PromptTemplate(input_variables=['ml_concept'], template=\"Turn the concept description of {ml_concept} and explain it to me like I'm five in 500 words.\"), llm=ChatOpenAI(client=<openai.resources.chat.completions.Completions object at 0x000001D343122090>, async_client=<openai.resources.chat.completions.AsyncCompletions object at 0x000001D343145FD0>, openai_api_key=SecretStr('**********'), openai_proxy=''))"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "second_prompt = PromptTemplate(\n",
    "    input_variables=['ml_concept'], \n",
    "    template=\"Turn the concept description of {ml_concept} and explain it to me like I'm five in 500 words.\"\n",
    ")\n",
    "chain_two = LLMChain(llm=llm, prompt=second_prompt) \n",
    "chain_two"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
      "\u001b[36;1m\u001b[1;3mAn autoencoder is a type of artificial neural network used for unsupervised learning that compresses input data into a lower-dimensional representation and then reconstructs the original data from this compressed representation. It is commonly used for tasks such as data denoising, dimensionality reduction, and anomaly detection.\u001b[0m\n",
      "\u001b[33;1m\u001b[1;3mAn autoencoder is like a really smart robot that can take a picture of a cat, squish it down into a tiny picture, and then make a new picture of the cat that looks almost exactly the same as the original one. It's like a magic trick where the robot can make things smaller and then bring them back to life!\n",
      "\n",
      "So, imagine you have a huge puzzle with lots and lots of pieces. The autoencoder is like a special machine that can take all those puzzle pieces and put them together in a simpler way. It's like turning a big, messy puzzle into a smaller, neater puzzle that still shows the same picture. This makes it easier for the robot to understand and work with the puzzle.\n",
      "\n",
      "But the cool thing is, the autoencoder doesn't just make things smaller, it can also help clean up messy pictures. It's like having a robot that can fix a blurry photo of your favorite toy and make it look clear and sharp again. This is really helpful for fixing mistakes or finding hidden things in pictures.\n",
      "\n",
      "Another thing the autoencoder can do is find patterns in the pictures it sees. It's like having a robot detective that can spot when something doesn't look right. Maybe there's a picture of a dog wearing a hat instead of a cat, the autoencoder can figure out that something strange is going on and help you find the mistake.\n",
      "\n",
      "Overall, the autoencoder is a super smart robot that can help us make sense of complicated pictures by making them smaller, cleaner, and easier to understand. It's like having a helpful friend who can look at a messy picture and say, \"Don't worry, I'll fix it for you!\"\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "An autoencoder is like a really smart robot that can take a picture of a cat, squish it down into a tiny picture, and then make a new picture of the cat that looks almost exactly the same as the original one. It's like a magic trick where the robot can make things smaller and then bring them back to life!\n",
      "\n",
      "So, imagine you have a huge puzzle with lots and lots of pieces. The autoencoder is like a special machine that can take all those puzzle pieces and put them together in a simpler way. It's like turning a big, messy puzzle into a smaller, neater puzzle that still shows the same picture. This makes it easier for the robot to understand and work with the puzzle.\n",
      "\n",
      "But the cool thing is, the autoencoder doesn't just make things smaller, it can also help clean up messy pictures. It's like having a robot that can fix a blurry photo of your favorite toy and make it look clear and sharp again. This is really helpful for fixing mistakes or finding hidden things in pictures.\n",
      "\n",
      "Another thing the autoencoder can do is find patterns in the pictures it sees. It's like having a robot detective that can spot when something doesn't look right. Maybe there's a picture of a dog wearing a hat instead of a cat, the autoencoder can figure out that something strange is going on and help you find the mistake.\n",
      "\n",
      "Overall, the autoencoder is a super smart robot that can help us make sense of complicated pictures by making them smaller, cleaner, and easier to understand. It's like having a helpful friend who can look at a messy picture and say, \"Don't worry, I'll fix it for you!\"\n"
     ]
    }
   ],
   "source": [
    "# Sequential Chains\n",
    "from langchain.chains import SimpleSequentialChain \n",
    "overall_chain = SimpleSequentialChain(chains=[chain, chain_two], verbose=True) \n",
    "\n",
    "explanation = overall_chain.run(\"autoencoder\") \n",
    "print(explanation)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='An autoencoder is like a really smart robot that can take a picture of a cat, squish it down into a'),\n",
       " Document(page_content='tiny picture, and then make a new picture of the cat that looks almost exactly the same as the'),\n",
       " Document(page_content=\"original one. It's like a magic trick where the robot can make things smaller and then bring them\"),\n",
       " Document(page_content='back to life!'),\n",
       " Document(page_content='So, imagine you have a huge puzzle with lots and lots of pieces. The autoencoder is like a special'),\n",
       " Document(page_content=\"machine that can take all those puzzle pieces and put them together in a simpler way. It's like\"),\n",
       " Document(page_content='turning a big, messy puzzle into a smaller, neater puzzle that still shows the same picture. This'),\n",
       " Document(page_content='makes it easier for the robot to understand and work with the puzzle.'),\n",
       " Document(page_content=\"But the cool thing is, the autoencoder doesn't just make things smaller, it can also help clean up\"),\n",
       " Document(page_content=\"messy pictures. It's like having a robot that can fix a blurry photo of your favorite toy and make\"),\n",
       " Document(page_content='it look clear and sharp again. This is really helpful for fixing mistakes or finding hidden things'),\n",
       " Document(page_content='in pictures.'),\n",
       " Document(page_content=\"Another thing the autoencoder can do is find patterns in the pictures it sees. It's like having a\"),\n",
       " Document(page_content=\"robot detective that can spot when something doesn't look right. Maybe there's a picture of a dog\"),\n",
       " Document(page_content='wearing a hat instead of a cat, the autoencoder can figure out that something strange is going on'),\n",
       " Document(page_content='and help you find the mistake.'),\n",
       " Document(page_content='Overall, the autoencoder is a super smart robot that can help us make sense of complicated pictures'),\n",
       " Document(page_content=\"by making them smaller, cleaner, and easier to understand. It's like having a helpful friend who\"),\n",
       " Document(page_content='can look at a messy picture and say, \"Don\\'t worry, I\\'ll fix it for you!\"')]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Text Splitting\n",
    "from langchain.text_splitter import RecursiveCharacterTextSplitter \n",
    "\n",
    "text_splitter = RecursiveCharacterTextSplitter(\n",
    "    chunk_size=100, \n",
    "    chunk_overlap=0\n",
    ")\n",
    "\n",
    "texts = text_splitter.create_documents([explanation])\n",
    "texts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'An autoencoder is like a really smart robot that can take a picture of a cat, squish it down into a'"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Extract plain text \n",
    "texts[0].page_content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Turn into embedding \n",
    "from langchain.embeddings import OpenAIEmbeddings\n",
    "embeddings = OpenAIEmbeddings() \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[-0.03867767949835719,\n",
       " 0.004066864237415921,\n",
       " -0.010681889568446257,\n",
       " -0.010579962826678441,\n",
       " -0.0007249517156492957,\n",
       " 0.0038833967075935574,\n",
       " -0.0023273200526148026,\n",
       " -0.030577927535437237,\n",
       " 0.0038969870329615287,\n",
       " -0.03495396853176065,\n",
       " 0.007957056573354776,\n",
       " 0.05800292938782912,\n",
       " -0.005137091766348808,\n",
       " -0.011898211814516226,\n",
       " 0.017694427609122616,\n",
       " -0.004369246066470081,\n",
       " -0.004678422825377571,\n",
       " 0.018074952994135314,\n",
       " -0.007365882774953115,\n",
       " -0.019569872952127546,\n",
       " -0.008344376888220805,\n",
       " 0.0034043425114010195,\n",
       " 0.0007325961863572835,\n",
       " -0.03767200752832142,\n",
       " -0.002488703594752533,\n",
       " -0.0035232568106328154,\n",
       " 0.022940240115769946,\n",
       " -0.03294262086639863,\n",
       " 0.003764482641192417,\n",
       " 0.015193832887126755,\n",
       " 0.03375803107525067,\n",
       " -0.022654847473994356,\n",
       " -0.03441036296762279,\n",
       " -0.06539599188219555,\n",
       " -0.04362451136616751,\n",
       " -0.0007100874573491531,\n",
       " 0.011442940338471654,\n",
       " -0.02228791194868832,\n",
       " 0.01009751163122055,\n",
       " -0.020385285023624824,\n",
       " 0.02067067952804566,\n",
       " 0.004773554171630745,\n",
       " -0.007780383740555086,\n",
       " -0.011096390534048227,\n",
       " -0.00021255906540464716,\n",
       " -0.010022765540188676,\n",
       " -0.03299698030522527,\n",
       " -0.02762885719857276,\n",
       " -0.011660382750391322,\n",
       " 0.013760067297814494,\n",
       " 0.012136039947318508,\n",
       " 0.012136039947318508,\n",
       " -0.01887677334328069,\n",
       " -0.032616456782857815,\n",
       " -0.02314409359930558,\n",
       " 0.00846668841954861,\n",
       " -0.0367206949971123,\n",
       " -0.001611286857020994,\n",
       " 0.03269799594109778,\n",
       " -0.004172188444110402,\n",
       " 0.009418001882080355,\n",
       " 0.008412328049399348,\n",
       " -0.017436214686760345,\n",
       " 0.008140523404685173,\n",
       " 0.011728333911569867,\n",
       " -0.013529034094865543,\n",
       " -0.0027774950984387216,\n",
       " 0.01115754583405082,\n",
       " 0.002267863019414232,\n",
       " -0.012679647374101613,\n",
       " 0.03726430056125016,\n",
       " 0.008792852503089425,\n",
       " -0.013909559479878243,\n",
       " -0.023810013488739113,\n",
       " 0.0009360243464927791,\n",
       " -0.016253867089957026,\n",
       " 0.017354671803229898,\n",
       " -0.004851697727589284,\n",
       " -0.013386336842655127,\n",
       " -0.01304658196808503,\n",
       " 0.04128699589197419,\n",
       " -0.009689805595471909,\n",
       " -0.02824041578653441,\n",
       " 0.005160874486496774,\n",
       " 0.019338839749178594,\n",
       " -0.003288825909926544,\n",
       " 0.0019620837254334077,\n",
       " 0.01572384952288058,\n",
       " -0.017096458880867627,\n",
       " -0.0015305952023674566,\n",
       " 0.028919923673029355,\n",
       " 0.03538885521824523,\n",
       " 0.016267456949663684,\n",
       " -0.0027588085756807532,\n",
       " -0.00847348334940194,\n",
       " 0.008643361252348299,\n",
       " 0.02253253501134393,\n",
       " 0.011680768471273936,\n",
       " 0.0027486159480701027,\n",
       " -0.017653656167357392,\n",
       " 0.011517686429503527,\n",
       " 0.01668875377644161,\n",
       " 0.008228860286746329,\n",
       " -0.018346755776204246,\n",
       " -0.008120138615125182,\n",
       " -0.009186968679131404,\n",
       " -0.016484900292905977,\n",
       " 0.013141713779999516,\n",
       " 0.017680837749415958,\n",
       " -0.007929875922618833,\n",
       " 0.012645671793512342,\n",
       " 0.05822037459371666,\n",
       " 0.0034077402091583398,\n",
       " -0.05305610124530928,\n",
       " 0.024258490034930354,\n",
       " -0.010280978462550947,\n",
       " -0.004654640105229605,\n",
       " -0.00557877291702541,\n",
       " -0.005653519008057283,\n",
       " 0.003676146457623228,\n",
       " 0.005857372025931604,\n",
       " 0.009540313413408162,\n",
       " 0.03313288262758236,\n",
       " -0.011422554617589042,\n",
       " 0.028267595505947728,\n",
       " 0.005303571738707192,\n",
       " -0.016892605397331995,\n",
       " -0.009214148398544725,\n",
       " -0.005738457959530463,\n",
       " -0.012992221597935769,\n",
       " 0.0321272106575466,\n",
       " -0.007420243610763689,\n",
       " 0.012734007744250875,\n",
       " 0.04781028873866195,\n",
       " -0.011925391533929545,\n",
       " 0.016892605397331995,\n",
       " -0.01241463859056339,\n",
       " 0.011055620023605625,\n",
       " -0.02273638849487956,\n",
       " -0.052295050475283884,\n",
       " 0.010512011665499898,\n",
       " 0.0021336598951817885,\n",
       " -0.01958346467447945,\n",
       " 0.0029643600931877506,\n",
       " 0.0035028715554115144,\n",
       " 0.008140523404685173,\n",
       " 0.004386233856764717,\n",
       " 0.01613155648995184,\n",
       " -0.0052390180424553125,\n",
       " 0.01321645987103139,\n",
       " -0.002836952131639292,\n",
       " -0.04340706616027998,\n",
       " 0.00383583103446697,\n",
       " 0.02173071466219855,\n",
       " 0.026541640482361302,\n",
       " 0.03555193726001564,\n",
       " 0.029273269338628734,\n",
       " -0.008806443294118706,\n",
       " -0.022885880676943308,\n",
       " 0.011626407169802051,\n",
       " -0.009764551686503782,\n",
       " 0.024978769363190528,\n",
       " -0.006166548784839093,\n",
       " -0.0017684234515850654,\n",
       " 0.025563148231738858,\n",
       " 0.016484900292905977,\n",
       " 0.036584792674755215,\n",
       " 0.009180173749278075,\n",
       " -0.009519927692525548,\n",
       " -0.014351241096216156,\n",
       " -0.012632081933805682,\n",
       " 0.004393028786618047,\n",
       " -0.008330786097191522,\n",
       " 0.03310570290816904,\n",
       " -0.011449735268324985,\n",
       " 0.0005491285983272559,\n",
       " -0.022260730366629754,\n",
       " -0.011952572184665488,\n",
       " -0.017368263525581802,\n",
       " -0.005786023399826395,\n",
       " -0.0026076176611536735,\n",
       " 0.010403290925201375,\n",
       " 0.016892605397331995,\n",
       " 0.03547039437648519,\n",
       " -0.016960556558510538,\n",
       " -0.001150069817354758,\n",
       " 0.016647982334676382,\n",
       " -0.004810927217146682,\n",
       " 0.005317162064075163,\n",
       " -0.008011416943504037,\n",
       " 0.017708017468829277,\n",
       " 0.006608229935515695,\n",
       " -0.009186968679131404,\n",
       " -0.007263956498846611,\n",
       " -0.6057963086320824,\n",
       " -0.009282099559723268,\n",
       " 0.022206370927803115,\n",
       " -0.028485038849190018,\n",
       " 0.025807771294394467,\n",
       " 0.02981687676541184,\n",
       " -0.006574254354926422,\n",
       " -0.021173515513063543,\n",
       " -0.016226687370543707,\n",
       " -0.0002463222025725907,\n",
       " -0.023905144369330975,\n",
       " -0.01217001552790778,\n",
       " -0.012489384681595264,\n",
       " -0.006747529257138136,\n",
       " 0.014514323137986562,\n",
       " -0.012251556548792984,\n",
       " 0.010301364183433559,\n",
       " -0.012129245017465177,\n",
       " -0.01261169621292307,\n",
       " 0.009268509700016608,\n",
       " 0.008588999950876414,\n",
       " 0.0273026912523867,\n",
       " -0.03158360136811825,\n",
       " -0.022029697163680802,\n",
       " -0.008527844650873823,\n",
       " 0.008636565391172347,\n",
       " 0.025522376789973635,\n",
       " -0.008568615161316425,\n",
       " 0.0055651825916574384,\n",
       " -0.002933782210355799,\n",
       " -0.041205456733734235,\n",
       " 0.026813445127075477,\n",
       " -0.00951313276267222,\n",
       " -0.017721607328535935,\n",
       " 0.05376279257650804,\n",
       " 0.0023884758182787054,\n",
       " 0.001708117052152829,\n",
       " 0.02788707012093503,\n",
       " 0.020602728366867117,\n",
       " 0.03737302316419393,\n",
       " -0.026419329882356117,\n",
       " -0.02311691387989226,\n",
       " 0.00930928021045921,\n",
       " -0.006747529257138136,\n",
       " -0.007352292915246456,\n",
       " 0.0024190539339413123,\n",
       " -0.032181570096373235,\n",
       " 0.0028607350846179135,\n",
       " 0.0023052360649301693,\n",
       " -0.0376176443642043,\n",
       " 0.010376110274465432,\n",
       " 0.006801890092948709,\n",
       " 0.008799648364265377,\n",
       " -0.005904937466227536,\n",
       " 0.013970715711203457,\n",
       " 0.008140523404685173,\n",
       " 0.02586213073322111,\n",
       " -0.022967421697828512,\n",
       " 0.005232223112601983,\n",
       " -0.0031376352282301194,\n",
       " 0.02984405648482516,\n",
       " 0.02408181627080804,\n",
       " -0.0040125034016053485,\n",
       " -0.00621071676020836,\n",
       " -0.0029456738032604375,\n",
       " 0.0224102225486935,\n",
       " -0.005327354458855157,\n",
       " -0.007114464316782864,\n",
       " -0.007923080992765504,\n",
       " 0.002198213125772356,\n",
       " 0.026106755658521965,\n",
       " 0.006859648393685946,\n",
       " 0.007583326118195407,\n",
       " -0.0039003844978881936,\n",
       " -0.0009521627123480848,\n",
       " 0.037155577958306395,\n",
       " -0.002979649151019054,\n",
       " -0.016607212755556405,\n",
       " 0.006757722117579442,\n",
       " 0.0066388080511783016,\n",
       " 0.034464722406449426,\n",
       " 0.0017302010398374623,\n",
       " -0.027126019350909632,\n",
       " -0.00044592809825026025,\n",
       " 0.01282913955616536,\n",
       " -0.016607212755556405,\n",
       " -0.02693575572708066,\n",
       " -0.022573306453109152,\n",
       " 0.01119152141464009,\n",
       " -0.01551999697066757,\n",
       " 0.0067169516071368405,\n",
       " 0.0189719060865178,\n",
       " -0.013073762618820971,\n",
       " -0.025264163867611364,\n",
       " -0.017286722504696598,\n",
       " 0.0015976967644836786,\n",
       " -0.033839573958781115,\n",
       " 0.034192917761735254,\n",
       " 0.01175551456230581,\n",
       " -0.007399858355542388,\n",
       " -0.009438386671640346,\n",
       " -0.006672783166106262,\n",
       " 0.009988789959599403,\n",
       " 0.018088542853841975,\n",
       " -0.0026008227313003437,\n",
       " 0.018305986197084265,\n",
       " -0.0057146747737211855,\n",
       " -0.003084973124882879,\n",
       " 0.0376176443642043,\n",
       " -0.018550609259739878,\n",
       " -0.00869772162249756,\n",
       " 0.006924201624276515,\n",
       " 0.0031970922614306895,\n",
       " 0.006893623974275218,\n",
       " -0.01326402531132732,\n",
       " -0.025590327951152177,\n",
       " 0.013773657157521154,\n",
       " 0.021771484241318532,\n",
       " 0.014799716711084775,\n",
       " -0.013698911997811904,\n",
       " 0.024394390494642197,\n",
       " -0.0021965143933090235,\n",
       " 0.009356845650755142,\n",
       " 0.0015586248700890815,\n",
       " 0.009119017517952861,\n",
       " 0.004263922325436912,\n",
       " -0.014949208893148522,\n",
       " -0.0391669293489589,\n",
       " -0.02424489831257845,\n",
       " -0.0224102225486935,\n",
       " 0.0198144978774284,\n",
       " -0.014758946200642173,\n",
       " -0.009030681567214328,\n",
       " -0.0201950232624411,\n",
       " 0.010552782175942499,\n",
       " 0.012869910066607962,\n",
       " 0.03669351155240849,\n",
       " -0.005738457959530463,\n",
       " -0.004284307580658213,\n",
       " 0.006509701124335855,\n",
       " -0.01550640711096091,\n",
       " -0.020589138507160456,\n",
       " -0.003764482641192417,\n",
       " 0.02424489831257845,\n",
       " 0.004433799297060649,\n",
       " -0.006027249463216652,\n",
       " 0.002791085190976037,\n",
       " -0.017898281092658248,\n",
       " -0.01009751163122055,\n",
       " 0.024774915879654896,\n",
       " -0.017952640531484886,\n",
       " -0.00011445487913297678,\n",
       " 0.002678966287258882,\n",
       " 0.010505216735646567,\n",
       " 0.017599296728530753,\n",
       " -0.01963782411330609,\n",
       " -0.01095369328183781,\n",
       " -0.030931273201036617,\n",
       " -0.018455478379148012,\n",
       " -0.01671593349585493,\n",
       " 0.015669488221408696,\n",
       " 0.02359257014549682,\n",
       " -0.018210855316492403,\n",
       " 0.005347739714076458,\n",
       " -0.0193524314715305,\n",
       " -0.01800700183295677,\n",
       " 0.010104306561073879,\n",
       " 0.029164548598330214,\n",
       " -0.01551999697066757,\n",
       " -0.026147525237641942,\n",
       " 0.010280978462550947,\n",
       " -0.02050759748627525,\n",
       " -0.007494989701795562,\n",
       " 0.022559714730757248,\n",
       " -0.010090715770044598,\n",
       " 0.04153162081727505,\n",
       " -0.0071416449675188055,\n",
       " -0.004545918433608459,\n",
       " 0.025807771294394467,\n",
       " -0.022804339656058104,\n",
       " 0.004005708471752019,\n",
       " 0.0017752186142690508,\n",
       " -0.004528930643313824,\n",
       " -0.003042503881976945,\n",
       " -0.017096458880867627,\n",
       " 0.009655830014882637,\n",
       " 0.010369315344612101,\n",
       " 0.0002567271717411577,\n",
       " -0.030931273201036617,\n",
       " -0.002203309555993009,\n",
       " 0.012557335842773808,\n",
       " 0.014283289935037611,\n",
       " -0.0016418648562682731,\n",
       " 0.023660521306675366,\n",
       " -0.0169061971196839,\n",
       " 0.0002354925066324426,\n",
       " -0.006054429648291283,\n",
       " 0.0224102225486935,\n",
       " 0.01571025966317392,\n",
       " 0.020371695163918166,\n",
       " -0.020208613122147757,\n",
       " -0.016919786979390557,\n",
       " 0.003259946759557925,\n",
       " 0.010858561469923323,\n",
       " 0.028566579870075222,\n",
       " -0.028457857267131455,\n",
       " 0.02011348037891065,\n",
       " -0.01284272941587202,\n",
       " 0.030632288836909122,\n",
       " 0.005609351032688017,\n",
       " -0.014269699144008328,\n",
       " -0.025155441264667594,\n",
       " -0.009397616161197744,\n",
       " 0.003784867896413718,\n",
       " 0.013739682508254506,\n",
       " 0.04106955441137715,\n",
       " 0.025726230273509267,\n",
       " 0.026337788861470916,\n",
       " -0.009234534119427337,\n",
       " -0.001339483143629441,\n",
       " -0.007481399376427591,\n",
       " -0.004800734822366688,\n",
       " 0.02151327131895626,\n",
       " 0.004457582482869926,\n",
       " 0.010600348547561053,\n",
       " 0.016729523355561587,\n",
       " 0.0030866718573462114,\n",
       " 0.0211191560742369,\n",
       " -0.006947984810085791,\n",
       " -0.056589550450722094,\n",
       " 0.0004718344086003834,\n",
       " -0.010668298777416974,\n",
       " 0.010627528266974372,\n",
       " 0.0201950232624411,\n",
       " 0.004376040996323411,\n",
       " -0.002879421607375882,\n",
       " -0.0015807089741890427,\n",
       " 0.008969525335889114,\n",
       " 0.03367649191701071,\n",
       " 0.011164340763904148,\n",
       " -0.012353482359238176,\n",
       " 0.03248055446050073,\n",
       " -0.0008927056209398507,\n",
       " -0.002261067856730247,\n",
       " 0.005840384235636968,\n",
       " 0.015900521424357647,\n",
       " 0.03079537087867953,\n",
       " 0.0045187382485338285,\n",
       " -0.022885880676943308,\n",
       " 0.005989876417700715,\n",
       " -0.021853025262203736,\n",
       " 0.01553358683037423,\n",
       " -0.014840487221527377,\n",
       " 0.033404687272296535,\n",
       " 0.014392011606658756,\n",
       " -0.005819998980415667,\n",
       " -0.007814359321144358,\n",
       " 0.007596916443563377,\n",
       " 0.03422009748114857,\n",
       " 0.012095269436875906,\n",
       " -0.0016563044314525826,\n",
       " 0.00547344917599224,\n",
       " -0.0009198859806374732,\n",
       " 0.006482520473599913,\n",
       " 0.0111711366250801,\n",
       " -0.006509701124335855,\n",
       " 0.01095369328183781,\n",
       " -0.030115861129539335,\n",
       " -0.010586757756531772,\n",
       " 0.032888261427571994,\n",
       " -0.03745456232243389,\n",
       " -0.004600279269419032,\n",
       " -0.006682976026547568,\n",
       " -0.012638876863659011,\n",
       " -0.004525533178387158,\n",
       " -0.009404411091051074,\n",
       " -0.010681889568446257,\n",
       " 0.027968611141820234,\n",
       " -0.003198790993894022,\n",
       " 0.016960556558510538,\n",
       " -0.030849732180151412,\n",
       " -0.051914526952916436,\n",
       " 0.023252814339604102,\n",
       " 0.021948156142795598,\n",
       " -0.003096864484956862,\n",
       " -0.010274183532697616,\n",
       " -0.029735335744526636,\n",
       " -0.013590190326190757,\n",
       " -0.006971767530233757,\n",
       " -0.0043896313216913825,\n",
       " -0.009784936476063773,\n",
       " 0.026786265407662158,\n",
       " -0.0006217512155723002,\n",
       " 0.008935549755299841,\n",
       " -0.04019978103840798,\n",
       " 0.0023612956332040745,\n",
       " 0.05294737864236552,\n",
       " -0.02295383183812185,\n",
       " -0.008527844650873823,\n",
       " 0.004294499975438207,\n",
       " -0.013406722563537738,\n",
       " -0.01429687979474427,\n",
       " -0.017680837749415958,\n",
       " -0.018482658098561332,\n",
       " 0.03737302316419393,\n",
       " 0.009981995029746074,\n",
       " -0.007270751894361252,\n",
       " 0.012598106353216409,\n",
       " -0.0038426261971509557,\n",
       " 0.0005576224934745738,\n",
       " -0.005646724078203953,\n",
       " 0.002430945294015295,\n",
       " -0.007284341754067912,\n",
       " 0.028050152162705434,\n",
       " -0.012061293856286634,\n",
       " 0.0009207353468691394,\n",
       " -0.012992221597935769,\n",
       " 0.0015263482547937977,\n",
       " 0.032290292699317005,\n",
       " 0.019501921790949,\n",
       " -0.012122449156289225,\n",
       " -0.01553358683037423,\n",
       " 0.006231102015429661,\n",
       " -0.015791800684059124,\n",
       " 0.025508786930266973,\n",
       " 0.02769680649710606,\n",
       " -0.030115861129539335,\n",
       " -0.004535726038828464,\n",
       " -0.03356776931406694,\n",
       " -0.01138857903699977,\n",
       " -0.03152924192929161,\n",
       " -0.0160636053287733,\n",
       " 0.022138419766624572,\n",
       " 0.024489523237879306,\n",
       " -0.0396289957548568,\n",
       " 0.01592770300641621,\n",
       " 0.029381990078927257,\n",
       " -0.0038290361046136403,\n",
       " 0.01095369328183781,\n",
       " -0.014446371976808018,\n",
       " 0.011001258722133742,\n",
       " -0.0160636053287733,\n",
       " 0.005337547319296463,\n",
       " -0.04612510515684075,\n",
       " -0.010647913987856986,\n",
       " 0.015479226460224968,\n",
       " -0.00829001558674892,\n",
       " -0.014351241096216156,\n",
       " -0.000369058591639221,\n",
       " -0.027234740091208156,\n",
       " 0.009995584889452734,\n",
       " 0.02810451346417732,\n",
       " -0.01534332413786788,\n",
       " -0.023687701026088685,\n",
       " 0.017667247889709296,\n",
       " 0.03332314438876609,\n",
       " -0.004280909650070237,\n",
       " -0.01632181825113557,\n",
       " -0.013563009675454816,\n",
       " 0.010192642511812412,\n",
       " 0.0016673464252948992,\n",
       " 0.03326878494993945,\n",
       " -0.007365882774953115,\n",
       " 0.006356811477345442,\n",
       " 0.009438386671640346,\n",
       " 0.033486226430536496,\n",
       " 0.011341013596703838,\n",
       " -0.011109980393754887,\n",
       " -0.0018346756474696211,\n",
       " -0.011259472575818635,\n",
       " 0.016253867089957026,\n",
       " -0.00036162646248914966,\n",
       " 0.01448714248725062,\n",
       " -0.010790611240067402,\n",
       " 0.01883600376416071,\n",
       " -0.01738185338528846,\n",
       " -0.035796562185316495,\n",
       " 0.024041046691688064,\n",
       " -0.001846567123958932,\n",
       " -0.024421572076700763,\n",
       " 0.004450787087355285,\n",
       " -0.0020028542358760094,\n",
       " -0.003202188458820687,\n",
       " -0.011721538981716536,\n",
       " -0.0068154804183166795,\n",
       " -0.00139299449679302,\n",
       " -0.0034824863001902137,\n",
       " 0.0013946932292563524,\n",
       " -0.008371556607634124,\n",
       " 0.00017646012744387354,\n",
       " 0.0025821362085423753,\n",
       " 0.0019790715157280434,\n",
       " -0.01115754583405082,\n",
       " 0.010579962826678441,\n",
       " -0.015615128782582055,\n",
       " -0.0248564569005401,\n",
       " -0.03226311297990368,\n",
       " 0.009404411091051074,\n",
       " -0.019501921790949,\n",
       " 0.012027318275697361,\n",
       " 0.026759083825603592,\n",
       " -0.026922165867374,\n",
       " 0.0017871099743430338,\n",
       " 0.009900453077538248,\n",
       " -0.016403359272020773,\n",
       " -0.019556283092420884,\n",
       " 0.010437265574468023,\n",
       " -0.05892706219962492,\n",
       " -0.009424796811933686,\n",
       " 0.003869806615056242,\n",
       " -0.026133935377935284,\n",
       " -0.028648120890960426,\n",
       " -0.01861856042091842,\n",
       " -0.0056874945886465555,\n",
       " 0.04030850364135175,\n",
       " -0.013148508709852845,\n",
       " 0.03590528106296977,\n",
       " 0.020602728366867117,\n",
       " -0.011809874932455071,\n",
       " 0.00015288963243849645,\n",
       " 0.01874087288356885,\n",
       " 0.017313902224109917,\n",
       " 0.006581049750441064,\n",
       " -0.033241605230526126,\n",
       " 0.023252814339604102,\n",
       " -0.00403288912248796,\n",
       " 0.01492202824241258,\n",
       " -0.01947474207153568,\n",
       " 0.023918734229037637,\n",
       " -0.0026704723921115643,\n",
       " 0.010573167896825112,\n",
       " 0.015057930564769667,\n",
       " -0.00033295965367844733,\n",
       " -0.02482927718112678,\n",
       " 0.004107634747858523,\n",
       " 0.00580980611997436,\n",
       " 0.02083376156981607,\n",
       " -0.02665036308530507,\n",
       " -0.01923011900888007,\n",
       " 0.014568683508135824,\n",
       " -0.011864236233926954,\n",
       " -0.007827949180851017,\n",
       " -0.0058845522110062345,\n",
       " -0.015125881725948212,\n",
       " -0.01607719518847996,\n",
       " -0.004675025360450906,\n",
       " 0.03723712084183684,\n",
       " 0.012353482359238176,\n",
       " -0.00723677631377198,\n",
       " 0.002728230692848802,\n",
       " 0.006115585413955185,\n",
       " 0.00040558224181965965,\n",
       " -0.012068088786139963,\n",
       " 0.01880882218210215,\n",
       " -0.021825845542790417,\n",
       " 0.026772673685310253,\n",
       " -0.013800837808257096,\n",
       " -0.04569021847035617,\n",
       " -0.013596985256044088,\n",
       " -0.012197195247321099,\n",
       " 0.002425848863794642,\n",
       " 0.025495197070560315,\n",
       " 0.01671593349585493,\n",
       " -0.0008120138498709855,\n",
       " -0.010484831946086577,\n",
       " 0.01863215028062508,\n",
       " -0.014446371976808018,\n",
       " -0.005337547319296463,\n",
       " -0.01155845693994613,\n",
       " -0.041640343420218814,\n",
       " -0.005422485805108332,\n",
       " 0.010573167896825112,\n",
       " 0.013855199109728981,\n",
       " 0.0624061519662111,\n",
       " -0.005347739714076458,\n",
       " -0.002371488260814725,\n",
       " 0.00026373461777539584,\n",
       " -0.028430677547718136,\n",
       " 0.014283289935037611,\n",
       " -0.039248468507198854,\n",
       " -0.012523360262184535,\n",
       " 0.00243434275894196,\n",
       " 0.019991169778905468,\n",
       " 0.026854214706195458,\n",
       " 0.05311046440942641,\n",
       " 0.009662624944735966,\n",
       " 0.010919717701248537,\n",
       " -0.00517786227679141,\n",
       " 0.00024313699189234644,\n",
       " 0.01240784366071006,\n",
       " 0.03226311297990368,\n",
       " -0.0033346928505897985,\n",
       " -0.03856896062070391,\n",
       " 0.01678388465703347,\n",
       " 0.03326878494993945,\n",
       " 0.0014439576348462722,\n",
       " 0.0016809366342475426,\n",
       " -0.013338771402359194,\n",
       " 0.009010295846331715,\n",
       " 0.029545073983342912,\n",
       " 0.00044168117978043325,\n",
       " -0.015628718642288715,\n",
       " 0.01302619717852504,\n",
       " -0.026242656118233808,\n",
       " -0.004376040996323411,\n",
       " 0.012706828024837555,\n",
       " 0.026011622915284856,\n",
       " 0.0169741464182172,\n",
       " -0.02957225370275623,\n",
       " -0.011008053651987072,\n",
       " 0.03090409161897805,\n",
       " -0.010382905204318763,\n",
       " 0.01880882218210215,\n",
       " 0.009214148398544725,\n",
       " 0.03307852318875572,\n",
       " -0.0015824077066523752,\n",
       " 0.009703395455178569,\n",
       " -0.015982064307888094,\n",
       " -0.004780349567145387,\n",
       " 0.01200693255481475,\n",
       " -0.016743113215268248,\n",
       " -0.027003706888259205,\n",
       " 0.0007686951243180572,\n",
       " 0.020045531080377352,\n",
       " 0.046342546637437795,\n",
       " 0.017680837749415958,\n",
       " 0.00047905419619253815,\n",
       " 0.010994463792280411,\n",
       " 0.009621854434293364,\n",
       " -0.00931607514031254,\n",
       " -0.005259403763337925,\n",
       " -0.021458910017484376,\n",
       " -0.01970577527448463,\n",
       " -0.030713829857794327,\n",
       " -0.024937997921425304,\n",
       " -0.01450073234695728,\n",
       " -0.045771761353886616,\n",
       " -0.02360616000520348,\n",
       " 0.008555024370287143,\n",
       " 0.014527912997693222,\n",
       " -0.01610437490789328,\n",
       " 0.04248293334848417,\n",
       " -0.02911018729685833,\n",
       " -0.03405701543937816,\n",
       " -0.019433972492415703,\n",
       " 0.02957225370275623,\n",
       " 0.01508511121550561,\n",
       " -0.00809975289424257,\n",
       " 0.03171950369047533,\n",
       " 0.030605107254850557,\n",
       " 0.005313764133487186,\n",
       " -0.006122380809469826,\n",
       " 0.0066388080511783016,\n",
       " 0.009445182532816298,\n",
       " -0.005877757281152905,\n",
       " 0.011769104422012469,\n",
       " 0.017966230391191548,\n",
       " -0.015044340705063008,\n",
       " -0.011789490142895081,\n",
       " 0.016172326069071822,\n",
       " -0.014595864158871766,\n",
       " -0.016022833887008075,\n",
       " -0.050582687174049366,\n",
       " 0.012122449156289225,\n",
       " 0.02459824397817783,\n",
       " 0.005456461385697604,\n",
       " -0.001477933215435544,\n",
       " -0.003040804916682957,\n",
       " 0.01551999697066757,\n",
       " -0.0026976528100168505,\n",
       " 4.047859173217246e-05,\n",
       " -0.014758946200642173,\n",
       " -0.032915441146985316,\n",
       " -0.004481365203017892,\n",
       " -0.02900146469391456,\n",
       " 0.017857509650893024,\n",
       " -0.02997995880718225,\n",
       " 0.007678457464448582,\n",
       " -0.010240207952108345,\n",
       " -0.0122379657577637,\n",
       " -0.004022696262046654,\n",
       " -0.024041046691688064,\n",
       " 0.008568615161316425,\n",
       " 0.006278667921386904,\n",
       " -0.002678966287258882,\n",
       " 0.002199912091066344,\n",
       " 0.002865831282007911,\n",
       " 0.004345463346322115,\n",
       " -0.004511943318680499,\n",
       " 0.0066659882362529324,\n",
       " -0.005639928682689312,\n",
       " -0.018333165916497585,\n",
       " 0.00869092669264423,\n",
       " 0.02995277908776893,\n",
       " -0.01610437490789328,\n",
       " -0.019923218617726925,\n",
       " 0.019393201050650476,\n",
       " -0.006207319295281695,\n",
       " 0.0004654640163437269,\n",
       " -0.00253626926787912,\n",
       " -0.021689943220433328,\n",
       " -0.021404548716012495,\n",
       " -0.027384232273271903,\n",
       " -0.00557197798717208,\n",
       " 0.02228791194868832,\n",
       " -0.0002037466724723703,\n",
       " -0.023429488103726415,\n",
       " 0.0027791938309020543,\n",
       " -0.005514219686434842,\n",
       " 0.0063398236870508065,\n",
       " 0.018890365065632596,\n",
       " 0.020765810408637526,\n",
       " 0.005748650354310458,\n",
       " -0.012081678645846623,\n",
       " 0.008337581958367474,\n",
       " 0.001599395496947011,\n",
       " -0.012435024311446002,\n",
       " 0.007739613230112484,\n",
       " 0.03022458186983786,\n",
       " -0.009132607377659521,\n",
       " 0.01738185338528846,\n",
       " 0.034519081845276064,\n",
       " -0.01448714248725062,\n",
       " 0.0431352615155658,\n",
       " 0.009594673783557424,\n",
       " 0.009839297777535656,\n",
       " -0.020561956925101894,\n",
       " 0.0034332216617696384,\n",
       " -0.004464377412723256,\n",
       " -0.011905006744369557,\n",
       " 0.020140661960969215,\n",
       " -0.017694427609122616,\n",
       " 0.0006060375328328274,\n",
       " -0.02133659755483395,\n",
       " -0.027234740091208156,\n",
       " 0.013603780185897418,\n",
       " 0.009254919840309949,\n",
       " -0.0010668299475908942,\n",
       " 0.010471241155057296,\n",
       " 0.01534332413786788,\n",
       " 0.007787178670408416,\n",
       " -0.03791662872833179,\n",
       " -0.014758946200642173,\n",
       " 0.01325043545162066,\n",
       " 0.01815649401502052,\n",
       " 0.013386336842655127,\n",
       " 0.037318660000076796,\n",
       " -0.02216559948603789,\n",
       " -0.043379886440866655,\n",
       " -0.007501785097310203,\n",
       " 0.003832433569540305,\n",
       " 0.03226311297990368,\n",
       " -0.021390958856305833,\n",
       " -0.016376179552607454,\n",
       " -0.007583326118195407,\n",
       " 0.02785989040152171,\n",
       " -0.02005912094008401,\n",
       " 0.002677267321964894,\n",
       " -0.002675568589501562,\n",
       " -0.020330923722152942,\n",
       " -0.019569872952127546,\n",
       " 0.022709206912820995,\n",
       " 0.024747736160241576,\n",
       " -0.04525533178387159,\n",
       " -0.0015042641506938365,\n",
       " 0.009649035085029307,\n",
       " -0.018781642462688826,\n",
       " -0.011055620023605625,\n",
       " -0.022274322088981658,\n",
       " -0.01508511121550561,\n",
       " -0.006417967243009345,\n",
       " -0.004878878378325226,\n",
       " -0.022437404130752066,\n",
       " 0.006696566351915539,\n",
       " -0.014337650305186873,\n",
       " 0.02727551153297338,\n",
       " 0.003998913541898689,\n",
       " -0.020018349498318787,\n",
       " -0.00930248528060588,\n",
       " 0.007114464316782864,\n",
       " -0.03965617547427012,\n",
       " -0.011857440372751002,\n",
       " -0.020358105304211505,\n",
       " -0.007094079061561563,\n",
       " 0.005531207476729478,\n",
       " 0.014011486221646057,\n",
       " -0.005368124969297759,\n",
       " 0.016756704937620152,\n",
       " -0.014786126851378116,\n",
       " 0.02273638849487956,\n",
       " 0.002430945294015295,\n",
       " 0.009689805595471909,\n",
       " -0.0012579420063289096,\n",
       " 0.015492816319931628,\n",
       " -0.006621820260883666,\n",
       " -0.009370436441784424,\n",
       " -0.050908851257590176,\n",
       " -0.02009989051920399,\n",
       " 0.011048824162429673,\n",
       " -0.0240138651096295,\n",
       " -0.014378420815629475,\n",
       " 0.044548644177963316,\n",
       " -0.0027095441700908337,\n",
       " 0.007331907660025155,\n",
       " 0.0072095956630360385,\n",
       " 0.00021850477454547057,\n",
       " 0.016308228391428908,\n",
       " -0.007420243610763689,\n",
       " 0.04055312856665261,\n",
       " -0.028919923673029355,\n",
       " -0.016471310433199316,\n",
       " 0.012632081933805682,\n",
       " -0.015017160054327067,\n",
       " -0.021499681459249603,\n",
       " -0.016620802615263063,\n",
       " -0.002605918928690341,\n",
       " 0.0068834311138339125,\n",
       " -0.010321748972993547,\n",
       " -0.024883638482598665,\n",
       " 0.010043150329748665,\n",
       " 0.024747736160241576,\n",
       " -0.0050929237909795415,\n",
       " 0.017055689301747647,\n",
       " 0.03397547628113821,\n",
       " -0.02008630065949733,\n",
       " 0.04623382775978452,\n",
       " 0.0026687736596482316,\n",
       " -0.026799855267368815,\n",
       " -0.017341081943523236,\n",
       " -0.00803859759423998,\n",
       " -0.007202800733182709,\n",
       " 0.00850066400013788,\n",
       " 0.020589138507160456,\n",
       " 0.008337581958367474,\n",
       " 0.01035572455358282,\n",
       " -0.010382905204318763,\n",
       " 0.03737302316419393,\n",
       " -0.06023172225907867,\n",
       " 0.005306969203633856,\n",
       " -0.0012290628559602909,\n",
       " -0.00600006881248071,\n",
       " -0.03862332005953055,\n",
       " 0.032806718544041547,\n",
       " -0.011633203030978003,\n",
       " -0.006900418904128548,\n",
       " 0.006713553676548864,\n",
       " 0.0017335986211794551,\n",
       " -0.020765810408637526,\n",
       " -0.021988927584560822,\n",
       " 0.0005045358234268282,\n",
       " 0.005150682091716779,\n",
       " -0.02995277908776893,\n",
       " -0.009492747973112229,\n",
       " 0.007692047324155241,\n",
       " -0.0044983529933125274,\n",
       " -0.02791424984034835,\n",
       " -0.009988789959599403,\n",
       " 0.014133797752973864,\n",
       " 0.0169061971196839,\n",
       " -0.00725036617347864,\n",
       " 0.15384095207104057,\n",
       " -0.002928686012965802,\n",
       " 0.007413448680910358,\n",
       " 0.037155577958306395,\n",
       " -0.00642136470793601,\n",
       " -0.00401929879711999,\n",
       " 0.01715082018233951,\n",
       " -0.015669488221408696,\n",
       " -0.007433833936131659,\n",
       " 0.005004587374579697,\n",
       " -0.009057861286627647,\n",
       " 0.015764620964645804,\n",
       " -0.01119152141464009,\n",
       " 0.005147284626790114,\n",
       " 0.03147487876517448,\n",
       " 0.009560699134290774,\n",
       " -0.01923011900888007,\n",
       " 0.011769104422012469,\n",
       " -0.010070330980484607,\n",
       " 0.02273638849487956,\n",
       " -0.009017090776185045,\n",
       " -0.004053274377709261,\n",
       " -0.02302178113665515,\n",
       " -0.016444130713785997,\n",
       " 0.02690857600766734,\n",
       " 0.0011602624449654085,\n",
       " -0.014976389543884465,\n",
       " -0.01713723032263285,\n",
       " 0.02412258771257327,\n",
       " -0.00865015618220163,\n",
       " -0.03604118338532686,\n",
       " -0.0052695961581179195,\n",
       " 0.00047990359152803635,\n",
       " 0.009424796811933686,\n",
       " 0.0003960266388827589,\n",
       " 0.006740734327284806,\n",
       " -0.019692185414777973,\n",
       " 0.0005945707976670137,\n",
       " 0.018305986197084265,\n",
       " 0.03519859345706151,\n",
       " 0.013617370045604078,\n",
       " 0.003349981908421102,\n",
       " 0.028158872903003958,\n",
       " 0.002101383047055849,\n",
       " 0.021078384632471678,\n",
       " 0.006784902302654073,\n",
       " ...]"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Vector Representation (Store into Pinecone)\n",
    "query_result = embeddings.embed_query(texts[0].page_content) \n",
    "query_result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create Pinecone Instance\n",
    "import pinecone \n",
    "from langchain.vectorstores import Pinecone \n",
    "\n",
    "pinecone_client = pinecone.Pinecone(api_key=PINECONE_API_KEY) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Store to Pinecone\n",
    "index_name = \"langchain-quickstart\"\n",
    "search = Pinecone.from_documents(texts, embeddings, index_name=index_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='Overall, the autoencoder is a super smart robot that can help us make sense of complicated pictures'),\n",
       " Document(page_content=\"But the cool thing is, the autoencoder doesn't just make things smaller, it can also help clean up\"),\n",
       " Document(page_content='wearing a hat instead of a cat, the autoencoder can figure out that something strange is going on'),\n",
       " Document(page_content='So, imagine you have a huge puzzle with lots and lots of pieces. The autoencoder is like a special')]"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# We can ask questions \n",
    "query = \"What is magical about an autoencoder?\" \n",
    "\n",
    "result = search.similarity_search(query) \n",
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "pioneerdevai",
   "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}