app.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using load.env and find.env we are using the API keys of Pinecone and OpenAI for our applicaiton."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "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())\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## LLM Wrappers\n",
    "\n",
    "1. Opening the OpenAI wrapper\n",
    "2. Initiating the ```text-davinci-003``` completion model\n",
    "3. Asking the question"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n\\nLarge language models are deep neural networks trained on large corpora of text to generate context-aware predictions about words, phrases, and sentences. They are used to build natural language processing (NLP) systems that can understand and generate human-like language.'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.llms import OpenAI\n",
    "llm = OpenAI(model_name= \"text-davinci-003\")\n",
    "llm(\"Explain large language models in a few words.\")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chat Model\n",
    "\n",
    "We will be importing a schema containing 3 parts:\n",
    "1. AI Message\n",
    "2. Human Message --> User Message\n",
    "3. System Message --> User to configure the system in the playground"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.schema import (\n",
    "    AIMessage,\n",
    "    HumanMessage,\n",
    "    SystemMessage,\n",
    ")\n",
    "from langchain.chat_models import ChatOpenAI"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To use the chat model we combine the system message and human message and use it as a list as an input to the chat model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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 sciipt to train a neural network on simulated data\")\n",
    "]\n",
    "response = chat(messages)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sure, here's an example script that trains a simple 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",
      "x = np.random.rand(1000, 10)\n",
      "y = np.sum(x, axis=1)\n",
      "\n",
      "# Define the neural network architecture\n",
      "model = Sequential()\n",
      "model.add(Dense(32, input_dim=10, activation='relu'))\n",
      "model.add(Dense(1, activation='linear'))\n",
      "\n",
      "# Compile the model\n",
      "model.compile(loss='mean_squared_error', optimizer='adam')\n",
      "\n",
      "# Train the model\n",
      "model.fit(x, y, epochs=100, batch_size=32, validation_split=0.2)\n",
      "```\n",
      "\n",
      "In this script, we first generate a simulated dataset with 1000 samples, where each sample has 10 features and the target variable is the sum of the features. We then define a simple neural network architecture with one hidden layer of 32 neurons and an output layer with one neuron. We compile the model with the mean squared error loss function and the Adam optimizer, and then train the model on the simulated data for 100 epochs with a batch size of 32 and a validation split of 0.2.\n"
     ]
    }
   ],
   "source": [
    "print(response.content, end=\"\\n\")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prompt Templates\n",
    "\n",
    "Prompts are the things that we are going to send to our language model.\n",
    "Most of the time these prompt are not going to be static buy dynamic so for this LangChain has Prompt Templates."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain import PromptTemplate\n",
    "\n",
    "template = \"\"\"\n",
    "You are an expert data scientist with the expertise in building deep learning models.\n",
    "Explain the concept of {concept} in couple of lines.\n",
    "\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(\n",
    "    input_variables= [\"concept\"],\n",
    "    template= template,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PromptTemplate(input_variables=['concept'], output_parser=None, partial_variables={}, template='\\nYou are an expert data scientist with the expertise in building deep learning models.\\nExplain the concept of {concept} in couple of lines.\\n', template_format='f-string', validate_template=True)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prompt"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now take a piece of text and use it as user input. We can then use the user input to format the prompt to the language model.\n",
    "\n",
    "As the user input changes, we will have the required answers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\nBatch Normalization is a technique used to reduce internal covariate shift in deep learning models. It normalizes the inputs to a layer for each mini-batch and helps the model learn faster and more accurately. It also helps keep the activations in a reasonable range, which can reduce the chances of overfitting and improve generalization.'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm(prompt.format(concept= \"batch normalization\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\nGrid Search CV is a technique used in hyperparameter tuning that allows a user to define a grid of hyperparameter values, and exhaustively search for the best performing model by evaluating all combinations of these hyperparameters. It works by taking a grid of parameters and evaluating a model for each combination of parameters, and then selecting the model that performs the best.'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm(prompt.format(concept= \"Grid Seach CV\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\nEncoders are used to transform data into a form that is more suitable for machine learning models. They are used to compress the amount of data required to represent a given input and to reduce the dimensionality of the input space. Encoders help to convert input data of a certain type into numerical representations which can be used as input to deep learning models.'"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm(prompt.format(concept= \"encoders\"))"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chains\n",
    "\n",
    "A chain takes a language model and a prompt template and combines them into an interface that takes input from the user and outputs an answer from the language model (like a composite function where the inner function is the prompt template and the outer function is language model)\n",
    "\n",
    "We can also build sequential chains where we have one chain returning an output and then a second chain taking the output from the first chain as an input."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Encoders are a type of neural network architecture used to reduce the dimensionality of input data by extracting important features from the data. They are primarily used for representation learning, where the goal is to compress the input data into a more efficient representation that can be used for downstream tasks such as classification and prediction.\n"
     ]
    }
   ],
   "source": [
    "from langchain.chains import LLMChain\n",
    "chain = LLMChain(llm= llm, prompt= prompt)\n",
    "\n",
    "#specify the input variables\n",
    "print(chain.run(\"encoders\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "second_prompt = PromptTemplate(\n",
    "    input_variables= [\"ml_concept\"],\n",
    "    template= \"Turn the concept description of {ml_concept} and explain it to a 5 year old in 500 words.\",\n",
    ")\n",
    "chain_two = LLMChain(llm=llm, prompt=second_prompt)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Combining both the chains to get the explanation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
      "\u001b[36;1m\u001b[1;3m\n",
      "An encoder is a type of deep learning model that compresses data into a lower dimensional representation, usually for use in other downstream models. It is commonly used in natural language processing tasks, such as translating text or speech into a numerical representation that can be fed into a neural network.\u001b[0m\n",
      "\u001b[33;1m\u001b[1;3m\n",
      "\n",
      "An encoder is a special type of computer program that can take information from one place and make it smaller and easier to use. For example, it can take a big block of text and turn it into a series of numbers or symbols that are easier for a computer to understand.\n",
      "\n",
      "Let's say you had a book full of words. An encoder can take those words and turn them into a series of numbers that represent the words. So instead of having to remember the words, the computer can just remember the numbers. It's like having a secret code that only the computer can understand.\n",
      "\n",
      "Let's say you wanted to send a message to your friend. An encoder can take the message and make it into a secret code that only your friend can understand. The encoder will turn the message into a series of numbers, like a code, and your friend will use a special program called a decoder to read the message.\n",
      "\n",
      "This same process is used in machine learning, which is how computers learn. Sometimes the data is too big and complex for the computer to understand, so the encoder will turn it into a simpler version that the computer can understand. This way, the computer can process the data and learn from it.\n",
      "\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "An encoder is a special type of computer program that can take information from one place and make it smaller and easier to use. For example, it can take a big block of text and turn it into a series of numbers or symbols that are easier for a computer to understand.\n",
      "\n",
      "Let's say you had a book full of words. An encoder can take those words and turn them into a series of numbers that represent the words. So instead of having to remember the words, the computer can just remember the numbers. It's like having a secret code that only the computer can understand.\n",
      "\n",
      "Let's say you wanted to send a message to your friend. An encoder can take the message and make it into a secret code that only your friend can understand. The encoder will turn the message into a series of numbers, like a code, and your friend will use a special program called a decoder to read the message.\n",
      "\n",
      "This same process is used in machine learning, which is how computers learn. Sometimes the data is too big and complex for the computer to understand, so the encoder will turn it into a simpler version that the computer can understand. This way, the computer can process the data and learn from it.\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from langchain.chains import SimpleSequentialChain\n",
    "combined_chain = SimpleSequentialChain(chains=[chain, chain_two], verbose=True)\n",
    "\n",
    "#running the chain specifying the input of the first chain only\n",
    "explanation = combined_chain.run(\"encoders\")\n",
    "print(explanation)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Embeddings and VectorStores\n",
    "\n",
    "Taking the explanation and spliting it into chunks as we need to further store them into Vector Spaces"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "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])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='An encoder is a special type of computer program that can take information from one place and make', metadata={}),\n",
       " Document(page_content='it smaller and easier to use. For example, it can take a big block of text and turn it into a series', metadata={}),\n",
       " Document(page_content='of numbers or symbols that are easier for a computer to understand.', metadata={}),\n",
       " Document(page_content=\"Let's say you had a book full of words. An encoder can take those words and turn them into a series\", metadata={}),\n",
       " Document(page_content='of numbers that represent the words. So instead of having to remember the words, the computer can', metadata={}),\n",
       " Document(page_content=\"just remember the numbers. It's like having a secret code that only the computer can understand.\", metadata={}),\n",
       " Document(page_content=\"Let's say you wanted to send a message to your friend. An encoder can take the message and make it\", metadata={}),\n",
       " Document(page_content='into a secret code that only your friend can understand. The encoder will turn the message into a', metadata={}),\n",
       " Document(page_content='series of numbers, like a code, and your friend will use a special program called a decoder to read', metadata={}),\n",
       " Document(page_content='the message.', metadata={}),\n",
       " Document(page_content='This same process is used in machine learning, which is how computers learn. Sometimes the data is', metadata={}),\n",
       " Document(page_content='too big and complex for the computer to understand, so the encoder will turn it into a simpler', metadata={}),\n",
       " Document(page_content='version that the computer can understand. This way, the computer can process the data and learn from', metadata={}),\n",
       " Document(page_content='it.', metadata={})]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "texts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'An encoder is a special type of computer program that can take information from one place and make'"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "texts[0].page_content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'it smaller and easier to use. For example, it can take a big block of text and turn it into a series'"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "texts[1].page_content"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Vector representation of the text --> embeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.embeddings import OpenAIEmbeddings\n",
    "\n",
    "embeddings = OpenAIEmbeddings(model_name = 'ada')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[-0.03485928179961753,\n",
       " 0.05722920349882175,\n",
       " 0.00021713228966146255,\n",
       " 0.022472629817635873,\n",
       " 0.027792933076667206,\n",
       " 0.0028065110708098222,\n",
       " 0.020439001249579196,\n",
       " 0.0118114829797385,\n",
       " 0.006260085988574631,\n",
       " 0.01108225179984785,\n",
       " -0.04026175006327804,\n",
       " -0.023787299694025734,\n",
       " 0.035927449211539106,\n",
       " 0.07522373811868205,\n",
       " 0.015447365459645325,\n",
       " -0.030956356535407722,\n",
       " 0.03609178294608784,\n",
       " -0.027176680640786863,\n",
       " 0.012273671375326164,\n",
       " -0.003959414636214966,\n",
       " 0.013105610673648476,\n",
       " 0.0008441358990276038,\n",
       " 0.07279981832805603,\n",
       " 0.0013788622175790024,\n",
       " 0.050902356581340714,\n",
       " 0.01047113653940202,\n",
       " 0.029333560441077686,\n",
       " 0.030278480346055497,\n",
       " -0.005654105575256828,\n",
       " -0.03878274645233945,\n",
       " -0.01392727934639214,\n",
       " 0.007405286351965141,\n",
       " 0.03705724410222294,\n",
       " 0.022698589168301676,\n",
       " 0.023581881594517223,\n",
       " 0.01032734405601058,\n",
       " 0.03810487026298722,\n",
       " -0.00011474470627358384,\n",
       " -0.042069421143314106,\n",
       " -0.033832196890010546,\n",
       " 0.003617908652313542,\n",
       " -0.038351372727455514,\n",
       " 0.015334385784312421,\n",
       " 0.00463472316917253,\n",
       " -0.0283064755314707,\n",
       " 0.007795578505857084,\n",
       " -0.051107772818204035,\n",
       " 0.027484806858727034,\n",
       " -0.02865568425172546,\n",
       " 0.03701616159990836,\n",
       " 0.023766758442868442,\n",
       " 0.0032686994663974848,\n",
       " 0.011832024230895796,\n",
       " 0.03307215197073876,\n",
       " 0.006090616941236575,\n",
       " -0.06392579666242444,\n",
       " 0.02467059212024128,\n",
       " -0.02391054906361469,\n",
       " -0.03933737513474791,\n",
       " -0.020397916884619414,\n",
       " 0.014255945884167011,\n",
       " -0.012396921676237713,\n",
       " 0.027032890020040615,\n",
       " -0.0015290734927111225,\n",
       " -0.05653078605831222,\n",
       " -0.02366404846179159,\n",
       " 0.025040343954298525,\n",
       " -0.030114146611506763,\n",
       " 0.024239216532712157,\n",
       " -0.061337543137249685,\n",
       " -0.012263400749747516,\n",
       " 0.03358569442554226,\n",
       " 0.031305563393017294,\n",
       " -0.03689291036767421,\n",
       " -0.02446517588337796,\n",
       " -0.022472629817635873,\n",
       " 0.0179739952313482,\n",
       " 0.015837658544859863,\n",
       " 0.04009741632872931,\n",
       " -0.005191917179669165,\n",
       " 0.006429555035912688,\n",
       " -0.014615426161323013,\n",
       " 0.004788785812481318,\n",
       " -0.007076618882867675,\n",
       " -0.026170136982337174,\n",
       " 0.031634230862114754,\n",
       " -0.00975217691641261,\n",
       " -0.027649140593275768,\n",
       " -0.01366023656208915,\n",
       " -0.026580971318709005,\n",
       " 0.025656594527533678,\n",
       " -0.005726001351291249,\n",
       " -0.046752930715307804,\n",
       " 0.025882553878199484,\n",
       " 0.01235583824260053,\n",
       " -0.022698589168301676,\n",
       " 0.006778764221828745,\n",
       " 0.023273757239222242,\n",
       " -0.033359736937521645,\n",
       " 0.030073062246546985,\n",
       " -0.0044036289713786985,\n",
       " -0.05381927757561294,\n",
       " -0.06240571427446164,\n",
       " -0.04313758855523568,\n",
       " -0.01689555533120279,\n",
       " 0.03208614956344637,\n",
       " -0.020880647462686967,\n",
       " -0.003723184892801162,\n",
       " -0.005387063256615136,\n",
       " 0.004829869246118501,\n",
       " 0.0008146071519970473,\n",
       " -0.002927193482496061,\n",
       " 0.0005963515272148357,\n",
       " -0.05003960540628247,\n",
       " 0.04646534574852493,\n",
       " 0.02475275898751565,\n",
       " -0.002988818632951836,\n",
       " 0.05008068790859705,\n",
       " -0.0019951134893061023,\n",
       " 0.05221702645773058,\n",
       " 0.004683509571993698,\n",
       " 0.015714407312625717,\n",
       " -0.01702907718901558,\n",
       " 0.001987410287291468,\n",
       " 0.02890218485354856,\n",
       " 0.02939518605719476,\n",
       " 0.020541709368010856,\n",
       " -0.025122510821572894,\n",
       " -0.0050763698479416005,\n",
       " -0.011924462655071404,\n",
       " 0.03231210705146698,\n",
       " -0.0021389055070362433,\n",
       " -0.0023289162711928914,\n",
       " -0.01200662952234577,\n",
       " -0.00798045395722441,\n",
       " -0.0031017980754540903,\n",
       " -0.010938460247779006,\n",
       " 0.03878274645233945,\n",
       " 0.09087652167783589,\n",
       " -0.009916510650961344,\n",
       " 0.004324029760498994,\n",
       " -0.0033123505564293296,\n",
       " 0.01542682420848803,\n",
       " -0.01849781017437553,\n",
       " -0.003990226978612205,\n",
       " 0.042439171114726164,\n",
       " -0.011544441126758108,\n",
       " 0.03280510825511318,\n",
       " 0.014954364255999126,\n",
       " -0.005107182656000137,\n",
       " 0.017727494629525102,\n",
       " -0.026889097536649177,\n",
       " 0.02561551202521909,\n",
       " 0.06634972390363122,\n",
       " 0.06339171668175404,\n",
       " 0.019144872624346623,\n",
       " -0.02836810114758777,\n",
       " 0.05952987205721363,\n",
       " -0.02111687743893142,\n",
       " 0.001914230566644391,\n",
       " 0.015570615760556874,\n",
       " -0.0013069662087139319,\n",
       " -0.04708159818440527,\n",
       " 0.04535609583428876,\n",
       " -0.03344190194215082,\n",
       " -0.039501708869296645,\n",
       " -0.04338409101970397,\n",
       " -0.0066144304872800125,\n",
       " 0.005838981026624152,\n",
       " -0.009772718167569906,\n",
       " 0.02128121117348015,\n",
       " 0.0637203841508515,\n",
       " -0.0196789581929526,\n",
       " -0.011719045486885488,\n",
       " 0.05496961371745407,\n",
       " -0.003766835982833007,\n",
       " 0.050779105349106575,\n",
       " -0.03338027818867894,\n",
       " -0.02645772194912005,\n",
       " 0.03679020038659736,\n",
       " 0.06811630875606232,\n",
       " 0.03448953182820548,\n",
       " 0.027977808062373235,\n",
       " 0.03255860951593527,\n",
       " 0.030730397184741916,\n",
       " 0.001188209539323689,\n",
       " 0.07058131104900293,\n",
       " -0.02156879427761784,\n",
       " 0.01587874104717445,\n",
       " 0.0012825730073033476,\n",
       " 0.03276402575279859,\n",
       " -0.05743461973568507,\n",
       " 0.038556788964318835,\n",
       " 0.02600580324778844,\n",
       " 0.0026729899114889765,\n",
       " 0.007030400136441168,\n",
       " -0.003902924798548514,\n",
       " -0.031531524606328284,\n",
       " -0.018241037084328594,\n",
       " 0.00883293543802661,\n",
       " 0.02666313818598337,\n",
       " -0.007045806540470437,\n",
       " 0.012931006313521095,\n",
       " 0.017573431520555016,\n",
       " 0.00884834137639458,\n",
       " 0.00623954427175604,\n",
       " 0.04720484941663942,\n",
       " 0.0009449186244092411,\n",
       " -0.013249402225717319,\n",
       " -0.014255945884167011,\n",
       " 0.01653607598536938,\n",
       " -0.008262902679895368,\n",
       " 0.016885284705624143,\n",
       " 0.0004355484366240871,\n",
       " 0.014266217441068253,\n",
       " -0.003109501277468724,\n",
       " 0.004896630175024897,\n",
       " -0.05127210655275277,\n",
       " 0.027834015578981797,\n",
       " 0.019535165709561163,\n",
       " -0.08237225743419713,\n",
       " -0.03243535828370113,\n",
       " 0.007785307880278437,\n",
       " 0.008458049222502637,\n",
       " 0.0030453084706182874,\n",
       " -0.00675308719222083,\n",
       " -0.03559878174244164,\n",
       " 0.0037539974680290493,\n",
       " -0.05501069621976866,\n",
       " 0.022390462950361505,\n",
       " 0.03296944198966192,\n",
       " -0.008000996139704298,\n",
       " -0.02156879427761784,\n",
       " 0.046547514478444484,\n",
       " -0.0012800052344933614,\n",
       " -0.013156964732864306,\n",
       " 0.006809576564225984,\n",
       " 0.03627665793179387,\n",
       " -0.019360561349433782,\n",
       " -0.02816268304807926,\n",
       " 0.039912541343023286,\n",
       " -0.07238898585432937,\n",
       " 0.004783650499691995,\n",
       " 0.06630864140131665,\n",
       " -0.06400796911763439,\n",
       " -0.013680778744569041,\n",
       " -0.004678374259204375,\n",
       " -0.00697904561156404,\n",
       " 0.031675317089719726,\n",
       " 0.004352274446501571,\n",
       " -0.010650876212318723,\n",
       " -0.024444634632220668,\n",
       " 0.05155969151953565,\n",
       " -0.029888187260840957,\n",
       " 0.028285934280313407,\n",
       " 0.006814711877015308,\n",
       " -0.03181910957311116,\n",
       " -0.01063033496116143,\n",
       " 0.03816649774174948,\n",
       " 0.015015989872116197,\n",
       " 0.001150335676179833,\n",
       " 0.04597234454487873,\n",
       " -0.012417462927395007,\n",
       " -0.07395015074460677,\n",
       " 0.00516367202800529,\n",
       " -0.0005623293232859589,\n",
       " -0.01903189388033632,\n",
       " 0.0028578653628563012,\n",
       " 0.047944349359463526,\n",
       " -0.007220410900597816,\n",
       " 0.047862184354834345,\n",
       " 0.020305479391766402,\n",
       " 0.030730397184741916,\n",
       " -0.005132859685608052,\n",
       " -0.011390378017788022,\n",
       " -0.014132696514578056,\n",
       " 0.04621884700934702,\n",
       " -0.017645327762250734,\n",
       " -0.07362148327550931,\n",
       " 0.03531119677565876,\n",
       " -0.024485717134535255,\n",
       " 0.010322208743221258,\n",
       " -0.006383336289486181,\n",
       " -0.0011098942730566395,\n",
       " -0.024341926513789008,\n",
       " 0.00734879651429869,\n",
       " 0.0421105036456287,\n",
       " -0.029066518588097293,\n",
       " -0.010825480572446103,\n",
       " 0.013968362780029322,\n",
       " 0.02230829608308714,\n",
       " 0.02845026801486214,\n",
       " -0.03140827337409414,\n",
       " -0.2105114357258289,\n",
       " 0.007158785750142041,\n",
       " 0.000903835190772058,\n",
       " 0.030011436630429912,\n",
       " -0.013043985057531403,\n",
       " -0.012643422278060812,\n",
       " -0.01651553473421209,\n",
       " 0.018158870217054226,\n",
       " 0.03409923688034575,\n",
       " -0.04457550966385969,\n",
       " 0.009875427217324161,\n",
       " 0.019935729420354348,\n",
       " -0.0010309370926909246,\n",
       " 0.003558851158252429,\n",
       " 0.013896466538333603,\n",
       " 0.011955274531807345,\n",
       " 0.04913576800361924,\n",
       " 0.010409510923284947,\n",
       " 0.005505178244737363,\n",
       " -0.031223398388388113,\n",
       " 0.00953135287853613,\n",
       " 0.008822663881125367,\n",
       " -0.02310942350467351,\n",
       " 0.0025279140655615046,\n",
       " -0.05451769501612246,\n",
       " -0.00581330353135494,\n",
       " -0.007040670762019815,\n",
       " -0.022143962348538406,\n",
       " -0.05057368911224325,\n",
       " 0.0028142142728244564,\n",
       " 0.04342517352201856,\n",
       " -0.06150187687179842,\n",
       " 0.029066518588097293,\n",
       " -0.005931418519477165,\n",
       " -0.026724763802100444,\n",
       " -0.0067428161009808855,\n",
       " 0.040754751266924245,\n",
       " 0.03909087267027962,\n",
       " -0.011873107664532978,\n",
       " 0.014440821801195632,\n",
       " 0.007364202918327957,\n",
       " -0.032722943250484006,\n",
       " -0.013917007789490898,\n",
       " -0.00916160197580148,\n",
       " -0.004732296440476164,\n",
       " 0.0005899322116051948,\n",
       " -0.03375002816009099,\n",
       " -0.006059804133178039,\n",
       " 0.02475275898751565,\n",
       " 0.007600432428911112,\n",
       " 0.037673496538103285,\n",
       " -0.016772305961613835,\n",
       " 0.0007183178835137302,\n",
       " -0.028491350517176727,\n",
       " -0.08915101932771938,\n",
       " 0.046794013217622395,\n",
       " 0.048149765596326846,\n",
       " -0.014060800272882337,\n",
       " 0.023438090973770975,\n",
       " -0.015611699194194056,\n",
       " 0.021199044306205787,\n",
       " 0.01260233884442363,\n",
       " 0.00501988001027515,\n",
       " -0.07066348350421288,\n",
       " -0.019401643851748373,\n",
       " 0.04860168429765845,\n",
       " 0.04330192228978441,\n",
       " 0.024732217736358354,\n",
       " 0.005556532303953193,\n",
       " 0.035413906756735614,\n",
       " -0.012746130396492474,\n",
       " 0.00250352086415092,\n",
       " 0.03648207416865719,\n",
       " 0.005957095549085081,\n",
       " 0.016782576587192483,\n",
       " -0.06409013412226355,\n",
       " -0.0005790194390972335,\n",
       " -0.0450274283651913,\n",
       " 0.009659738492237002,\n",
       " 0.0042778110140724865,\n",
       " -0.00954162443543737,\n",
       " -0.02516359332388748,\n",
       " 0.024876010219749792,\n",
       " -0.038618412717790714,\n",
       " 0.11207556970933205,\n",
       " -0.07485398814727,\n",
       " -0.006758222505010154,\n",
       " -0.010548168093887063,\n",
       " -0.035680950472361195,\n",
       " -0.0200795200411006,\n",
       " -0.06392579666242444,\n",
       " 0.03662586665204862,\n",
       " 0.021527711775303254,\n",
       " 0.021548253026460545,\n",
       " 0.014851656137567466,\n",
       " 0.028820017986274194,\n",
       " 0.020367105007883475,\n",
       " 0.06035154072995729,\n",
       " 0.028511891768334022,\n",
       " 0.019730311320845836,\n",
       " 0.011010356489474725,\n",
       " 0.003168558771529837,\n",
       " -0.015283031725096591,\n",
       " 0.002878407079674893,\n",
       " 0.053038695130474246,\n",
       " 0.006285763018182546,\n",
       " -0.04215158614794328,\n",
       " 0.0278134743278245,\n",
       " -0.024403550267260887,\n",
       " 0.0026280549932598007,\n",
       " -0.006588753457672097,\n",
       " -0.030668771568624843,\n",
       " 0.007698005700214747,\n",
       " -0.042069421143314106,\n",
       " -0.018364288316562737,\n",
       " 0.047862184354834345,\n",
       " 0.0037334557512104577,\n",
       " -0.0004695706405529639,\n",
       " -0.021897461746715308,\n",
       " -0.018970268264219246,\n",
       " -0.05751678474031424,\n",
       " -0.03974820760847455,\n",
       " -0.007163921062931365,\n",
       " 0.00348952280578202,\n",
       " -0.03794053652843849,\n",
       " -0.007744224446641254,\n",
       " -0.05065585411687243,\n",
       " 0.01397863340560797,\n",
       " -0.012417462927395007,\n",
       " -0.04001525132410014,\n",
       " -0.015293302350675239,\n",
       " 0.022390462950361505,\n",
       " 0.002765427637172639,\n",
       " -0.06347388168638321,\n",
       " -0.04106287748486442,\n",
       " 0.004344571477317585,\n",
       " -0.042439171114726164,\n",
       " -0.05344952760420089,\n",
       " -0.005618157454408968,\n",
       " -0.008550486715355651,\n",
       " 0.021548253026460545,\n",
       " 0.00523556826970101,\n",
       " -0.026334470716885904,\n",
       " 0.040816375020396124,\n",
       " 0.015796574179900085,\n",
       " 0.03034010409952738,\n",
       " 0.00038965055993541977,\n",
       " 0.036564242898576745,\n",
       " 0.010712501828435797,\n",
       " 0.010070572828608834,\n",
       " -0.019011352629179024,\n",
       " 0.009048623231791172,\n",
       " 0.02115795994124601,\n",
       " -0.028183226161881746,\n",
       " 0.004876088458206305,\n",
       " -0.0012100350843396114,\n",
       " 0.009741905359511369,\n",
       " -0.04539717833660335,\n",
       " -0.0071793274669606335,\n",
       " -0.0006945665379941491,\n",
       " -0.011256857091297826,\n",
       " -0.007020129045201224,\n",
       " -0.0112055021007594,\n",
       " 0.05045043788000911,\n",
       " -0.014974906438479015,\n",
       " 0.044123590962528075,\n",
       " -0.06400796911763439,\n",
       " -0.016176596639535974,\n",
       " 0.042808921086138214,\n",
       " -0.00884834137639458,\n",
       " -0.007045806540470437,\n",
       " -0.043959257227979345,\n",
       " -0.01223258794168898,\n",
       " -0.020695772476980942,\n",
       " -0.0566129510629414,\n",
       " 0.003615340763088232,\n",
       " -0.00206315801357918,\n",
       " 0.018230766458749947,\n",
       " 0.03978929011078914,\n",
       " 0.010835752129347346,\n",
       " -0.007918829272429932,\n",
       " 0.027731307460550136,\n",
       " 0.018908642648102172,\n",
       " 0.004134018996342345,\n",
       " 0.015652781696508647,\n",
       " 0.04408250846021349,\n",
       " 0.018723767662396147,\n",
       " -0.0026909639719129067,\n",
       " -0.0057414077553205175,\n",
       " -0.001105400757950657,\n",
       " 0.029538978540586198,\n",
       " -0.01867241453450291,\n",
       " -0.010661146837897371,\n",
       " -0.03286673573387544,\n",
       " -0.0012498345733641394,\n",
       " -0.007600432428911112,\n",
       " 0.01162660706270988,\n",
       " 0.026724763802100444,\n",
       " -0.02261642230102731,\n",
       " -0.010928189622200359,\n",
       " 0.036132865448402426,\n",
       " 0.007672328670606832,\n",
       " -0.08791851445595869,\n",
       " 0.019596791325678237,\n",
       " -0.014543529919627294,\n",
       " -0.024239216532712157,\n",
       " -0.094491863837908,\n",
       " -0.04124775247057044,\n",
       " -0.06084454193360349,\n",
       " 0.021240126808520374,\n",
       " 0.04457550966385969,\n",
       " 0.017891828364073836,\n",
       " 0.03533174175210644,\n",
       " -0.012520171977149263,\n",
       " 0.023088882253516217,\n",
       " 0.0021555957392628425,\n",
       " 0.03200398455881719,\n",
       " 0.02530738580727892,\n",
       " 0.02955951979174349,\n",
       " 0.012191504508051797,\n",
       " 0.04122721121941315,\n",
       " -0.0030376052686036533,\n",
       " -0.0006294108017880521,\n",
       " 0.01392727934639214,\n",
       " 0.0383924552297701,\n",
       " -0.006593888770461421,\n",
       " 0.019956270671511643,\n",
       " 0.01874430891355344,\n",
       " 0.022431547315321283,\n",
       " -0.03138773212293685,\n",
       " 0.007004723106833253,\n",
       " -0.005982773044354293,\n",
       " -0.02865568425172546,\n",
       " 0.014759218644714451,\n",
       " 0.015786303554321438,\n",
       " 0.03068931468242733,\n",
       " -0.000580945239600892,\n",
       " -0.029785479142409296,\n",
       " 0.03385273814116784,\n",
       " 0.02590309512935678,\n",
       " -0.031182314023428335,\n",
       " -0.017326932781377105,\n",
       " -0.04625992951166161,\n",
       " 0.015087885182489323,\n",
       " 0.007066348257289028,\n",
       " 0.03301052821726688,\n",
       " 0.004524311615895586,\n",
       " 0.03399653062455928,\n",
       " -0.003959414636214966,\n",
       " -0.02000762566205007,\n",
       " -0.008247496741527397,\n",
       " -0.009202685409438664,\n",
       " -0.024834925854790014,\n",
       " -0.012684505711697996,\n",
       " -0.01570413668704707,\n",
       " -0.03165477583856243,\n",
       " 0.006994452015593309,\n",
       " 0.023088882253516217,\n",
       " -0.008560757340934297,\n",
       " -0.011719045486885488,\n",
       " -0.015067343931332028,\n",
       " -0.030956356535407722,\n",
       " 0.00046860774030113464,\n",
       " 0.07571674304761862,\n",
       " -0.004372816163320162,\n",
       " 0.034777113069697975,\n",
       " 0.04667076198538825,\n",
       " 0.007302577767872183,\n",
       " -0.03208614956344637,\n",
       " 0.0009750892855384632,\n",
       " -0.03216831829336592,\n",
       " 0.026231762598454243,\n",
       " 0.027176680640786863,\n",
       " 0.042439171114726164,\n",
       " 0.009952457840486609,\n",
       " 0.011647149245189769,\n",
       " 0.0033945174237036964,\n",
       " -0.017881557738495188,\n",
       " 0.01905243513149361,\n",
       " -0.03824866274637866,\n",
       " 0.011462274259483742,\n",
       " -0.001114387788162622,\n",
       " -0.005484636527918771,\n",
       " 0.029641686659017858,\n",
       " -0.028861102351233972,\n",
       " 0.007723682729822662,\n",
       " -0.023232672874262464,\n",
       " -0.06367930164853691,\n",
       " -0.0008499132423309172,\n",
       " -0.019360561349433782,\n",
       " -0.04880710053452177,\n",
       " -0.008940778869247594,\n",
       " -0.039707125106159966,\n",
       " -0.03303106946842418,\n",
       " -0.018456725809415753,\n",
       " -0.0007452789159419627,\n",
       " -0.006789034847407393,\n",
       " -0.012294212626483458,\n",
       " -0.01212987982325732,\n",
       " 0.04367167598648685,\n",
       " 0.015108427364969212,\n",
       " -0.03340081943983623,\n",
       " 0.018651871420700426,\n",
       " -0.011061710548690555,\n",
       " 0.014615426161323013,\n",
       " 0.004930010173816797,\n",
       " 0.006075210537207307,\n",
       " 0.051518605291930676,\n",
       " -0.0026498805382757233,\n",
       " -0.02875839237015712,\n",
       " 0.028963810469665632,\n",
       " 0.019699499444109897,\n",
       " 0.012386651050659066,\n",
       " -0.05369603006866917,\n",
       " -0.023869466561300103,\n",
       " 0.014368925559499913,\n",
       " -0.03282565323156086,\n",
       " -0.07251223336127315,\n",
       " 0.022431547315321283,\n",
       " 0.039563332622768524,\n",
       " -0.03779674404504705,\n",
       " 0.06774655878465027,\n",
       " -0.019411914477327017,\n",
       " -0.05583236489251232,\n",
       " 0.046711848212993214,\n",
       " -0.03034010409952738,\n",
       " -0.012972089747158279,\n",
       " -0.031326108369464964,\n",
       " 0.038762205201182155,\n",
       " -0.030668771568624843,\n",
       " 0.004036445725038711,\n",
       " 0.010055166890240864,\n",
       " 0.04535609583428876,\n",
       " -0.013177506915344195,\n",
       " -0.016885284705624143,\n",
       " 0.061337543137249685,\n",
       " -0.008992132928463424,\n",
       " -0.034674406813911506,\n",
       " -0.00804207957334148,\n",
       " 0.054723114978276165,\n",
       " 0.046588596980759074,\n",
       " -0.01801507959630798,\n",
       " -0.018241037084328594,\n",
       " -0.03722157783677168,\n",
       " 0.007698005700214747,\n",
       " 0.019278394482159417,\n",
       " 0.011708773929984245,\n",
       " 0.036666952879653596,\n",
       " 0.030175770364978646,\n",
       " 0.02721776500574664,\n",
       " -0.004267539922832542,\n",
       " 0.030031979744232395,\n",
       " 0.05361386133874962,\n",
       " -0.028881643602391264,\n",
       " -0.010085979698299401,\n",
       " 0.011061710548690555,\n",
       " 0.05665403356525599,\n",
       " 0.0383924552297701,\n",
       " 0.019257853231002122,\n",
       " -0.0034612781197794432,\n",
       " -0.013886195912754957,\n",
       " 0.00717419215417131,\n",
       " -0.02421867528155486,\n",
       " -0.053572778836435034,\n",
       " -0.00019755347309470019,\n",
       " 0.039666042603845375,\n",
       " -0.008149923004562465,\n",
       " 0.04128883497288503,\n",
       " -0.02541009392571058,\n",
       " 0.007076618882867675,\n",
       " 0.045643677075781264,\n",
       " -0.022431547315321283,\n",
       " -0.0037976485580608946,\n",
       " 0.02232883733424443,\n",
       " 0.0008268038109100016,\n",
       " -0.015334385784312421,\n",
       " -0.019699499444109897,\n",
       " -0.06602105643453376,\n",
       " 0.03921412390251376,\n",
       " 0.03040172971564445,\n",
       " 0.005107182656000137,\n",
       " 0.08553567716764725,\n",
       " -0.025286844556121624,\n",
       " 0.010979543681416189,\n",
       " 0.037570786557026434,\n",
       " -0.026930181901608955,\n",
       " 0.03181910957311116,\n",
       " -0.0030786887022408367,\n",
       " -0.025574427660259313,\n",
       " 0.029580061042900785,\n",
       " -0.011924462655071404,\n",
       " 0.02356134034335993,\n",
       " -0.06240571427446164,\n",
       " -0.0008441358990276038,\n",
       " -0.0005815871536995575,\n",
       " -0.027032890020040615,\n",
       " -0.003453574917764809,\n",
       " 0.018466996434994398,\n",
       " 0.001398120106200263,\n",
       " -0.032620233269407155,\n",
       " 0.03144935587640873,\n",
       " 0.006034127103570124,\n",
       " 0.046383180743895754,\n",
       " -0.014471634609254169,\n",
       " 0.009012675110943313,\n",
       " -0.02690963878780647,\n",
       " -0.040857461248001097,\n",
       " 0.0364204504151853,\n",
       " 0.03229156580030969,\n",
       " -0.025779845759767824,\n",
       " -0.009510811627378836,\n",
       " -0.00903835167488993,\n",
       " 0.019730311320845836,\n",
       " -0.018898372022523525,\n",
       " 0.016587430975907806,\n",
       " 0.027032890020040615,\n",
       " 0.03338027818867894,\n",
       " 0.020295208766187754,\n",
       " 0.03416086435910801,\n",
       " 0.06934881362782301,\n",
       " 0.0571059522665876,\n",
       " -0.046752930715307804,\n",
       " -0.009967864710177174,\n",
       " 0.0044344413137759366,\n",
       " 0.019042164505914963,\n",
       " 0.006907149835529618,\n",
       " 0.032887276985032736,\n",
       " -0.03159314835980017,\n",
       " 0.07768874786220342,\n",
       " -0.027382098740295374,\n",
       " 0.02705343127119791,\n",
       " 1.0842572248366933e-05,\n",
       " -0.01619713789069327,\n",
       " 0.006840389372284521,\n",
       " -0.02994981287695803,\n",
       " -0.02984710289588118,\n",
       " -0.021014169320499758,\n",
       " -0.032681860748169415,\n",
       " 0.02006924941552195,\n",
       " 0.0280599749296476,\n",
       " 0.0009230930793933187,\n",
       " 0.012458546361032191,\n",
       " 0.003715481690786528,\n",
       " -0.016875014080045495,\n",
       " 0.04617776450703243,\n",
       " -0.09013702173501177,\n",
       " 0.000831297326015984,\n",
       " 0.008904830748399734,\n",
       " 0.05147752278961609,\n",
       " 0.05332627637196674,\n",
       " -0.02931301918992039,\n",
       " -0.010147604383093877,\n",
       " 0.04272675608150904,\n",
       " -0.04560259457346667,\n",
       " 0.0043753842853761216,\n",
       " 0.013588340320393431,\n",
       " 0.062118129307678766,\n",
       " 0.035619322993598934,\n",
       " 0.002791104666780554,\n",
       " 0.01902162325475767,\n",
       " 0.047903266857148935,\n",
       " 0.02627284696341402,\n",
       " -0.006352523481427645,\n",
       " -0.004873520336150346,\n",
       " -0.04011795757988661,\n",
       " -0.049710937937185,\n",
       " 0.02341754785996849,\n",
       " 0.0049171718918434885,\n",
       " 0.0012299348870595376,\n",
       " 0.02836810114758777,\n",
       " -0.006480909095128518,\n",
       " -0.01233529606012064,\n",
       " -0.002539468752168131,\n",
       " 0.06125537813262051,\n",
       " -0.008262902679895368,\n",
       " -0.037447535324792294,\n",
       " 0.011195231475180752,\n",
       " 0.013691049370147687,\n",
       " 0.007898287089950043,\n",
       " 0.03364731817901414,\n",
       " 0.028943269218508337,\n",
       " 0.025369011423395992,\n",
       " -0.018857289520208938,\n",
       " -0.01337265252662887,\n",
       " -0.061091044398071774,\n",
       " -0.022739671670616263,\n",
       " 0.00872509107548303,\n",
       " -0.013393194709108758,\n",
       " 0.013495902827540419,\n",
       " -0.008155058317351789,\n",
       " -0.042603504849274894,\n",
       " 0.06959530864171054,\n",
       " 0.03389382064348243,\n",
       " 0.03909087267027962,\n",
       " 0.04765676439268065,\n",
       " 0.012150421074414613,\n",
       " 0.027792933076667206,\n",
       " 0.008473455160870608,\n",
       " -0.02261642230102731,\n",
       " 0.011534169569856865,\n",
       " 0.02076766871867666,\n",
       " -0.007482317440788886,\n",
       " -0.029189769820331436,\n",
       " 0.041905087408765376,\n",
       " 0.01905243513149361,\n",
       " 0.015899282298331745,\n",
       " 0.0006387187890493499,\n",
       " 0.005874928681810714,\n",
       " -0.021692045509851984,\n",
       " -0.011277398342455119,\n",
       " -0.02475275898751565,\n",
       " -0.006814711877015308,\n",
       " -0.027669681844433063,\n",
       " -0.0364409916663426,\n",
       " -0.031079605904996675,\n",
       " -0.005910876802658574,\n",
       " 0.017111244056289946,\n",
       " -0.01235583824260053,\n",
       " -0.05254569392682804,\n",
       " -0.046013430772483696,\n",
       " 0.016453909118095016,\n",
       " 0.07444315567354336,\n",
       " -0.0018217928409607286,\n",
       " -0.011041168366210666,\n",
       " 0.03759132780818373,\n",
       " 0.013793757488579347,\n",
       " 0.008909966061189057,\n",
       " -0.012396921676237713,\n",
       " 0.040508252527746334,\n",
       " 0.04114504248949359,\n",
       " -0.011400648643366668,\n",
       " -0.010404375610495623,\n",
       " -0.03806378776067264,\n",
       " 0.031120690269956452,\n",
       " 0.000872380701445505,\n",
       " 0.025882553878199484,\n",
       " 0.008601840774571481,\n",
       " -0.008411829544753535,\n",
       " 0.00645009675273128,\n",
       " -0.029066518588097293,\n",
       " -0.020171959396598802,\n",
       " 0.044863094630642565,\n",
       " 0.032784567003955885,\n",
       " 0.028984351720822924,\n",
       " -0.003240454547564259,\n",
       " 0.026231762598454243,\n",
       " 0.018836748269051642,\n",
       " 0.04642426324621034,\n",
       " 0.00031647072287301824,\n",
       " -0.041329917475199617,\n",
       " -0.020367105007883475,\n",
       " 0.016176596639535974,\n",
       " 0.011780670171679965,\n",
       " 0.015334385784312421,\n",
       " -0.00645009675273128,\n",
       " -0.005361386227007221,\n",
       " 0.027176680640786863,\n",
       " 0.013013173180795461,\n",
       " 0.0011689516507024282,\n",
       " -0.04782109812722938,\n",
       " 0.007805849597097028,\n",
       " -0.031326108369464964,\n",
       " 0.0243624677649463,\n",
       " 0.013773216237422054,\n",
       " -0.03759132780818373,\n",
       " -0.000499420286425191,\n",
       " -0.007456640411180971,\n",
       " -0.0226575048033419,\n",
       " 0.011719045486885488,\n",
       " 0.03235319327907195,\n",
       " 0.0019386237680549753,\n",
       " 0.01055843871946571,\n",
       " -0.0013519012433584321,\n",
       " 0.009187279471070692,\n",
       " 0.011534169569856865,\n",
       " 0.003959414636214966,\n",
       " 0.006367929885456913,\n",
       " -0.004922307204632812,\n",
       " 0.009510811627378836,\n",
       " 0.022821838537890632,\n",
       " 0.014553801476528535,\n",
       " 0.017018806563436933,\n",
       " -0.004876088458206305,\n",
       " -0.05381927757561294,\n",
       " -0.02949789417562642,\n",
       " -0.043959257227979345,\n",
       " 0.010640605586740076,\n",
       " -0.12579742350563491,\n",
       " 0.02446517588337796,\n",
       " -0.05866712088215537,\n",
       " -0.02063414686086387,\n",
       " 0.024999259589338747,\n",
       " 0.023499714727242858,\n",
       " 0.053983611310161675,\n",
       " -0.031736940843191605,\n",
       " -0.011493086136219683,\n",
       " -0.038762205201182155,\n",
       " -0.0029759801181478787,\n",
       " -0.040919085001472975,\n",
       " 0.0017704385489142496,\n",
       " -0.010075708141398158,\n",
       " -0.0019232175968563559,\n",
       " 0.02984710289588118,\n",
       " -0.04326083978746983,\n",
       " 0.0033662727377011194,\n",
       " -0.013814299671059236,\n",
       " 0.011945003906228697,\n",
       " -0.06162512810403256,\n",
       " -0.019206498240463696,\n",
       " -0.0032199128307456673,\n",
       " -0.029518437289428903,\n",
       " 0.0393784576370625,\n",
       " -0.02875839237015712,\n",
       " 0.05690053602972428,\n",
       " -0.03270240199932671,\n",
       " -0.02031575001734505,\n",
       " 0.07637407798581355,\n",
       " -0.015519261701341044,\n",
       " 0.024403550267260887,\n",
       " -0.010353021551279793,\n",
       " 0.007097160599686267,\n",
       " 0.018271850823709725,\n",
       " -0.0068455246850738435,\n",
       " -0.0445344271615451,\n",
       " -0.004295785074496417,\n",
       " 0.001987410287291468,\n",
       " -0.013526715635598955,\n",
       " -0.026067428863905513,\n",
       " 0.01260233884442363,\n",
       " -0.012715318519756533,\n",
       " 0.013680778744569041,\n",
       " 0.022287754831929844,\n",
       " -0.013290485659354503,\n",
       " -0.13902628727416272,\n",
       " -0.03416086435910801,\n",
       " -0.0026139324174278638,\n",
       " 0.014533259294048646,\n",
       " 0.02251371418259565,\n",
       " 0.03231210705146698,\n",
       " 0.024629509617926693,\n",
       " -0.014358654933921267,\n",
       " 0.024239216532712157,\n",
       " 0.02310942350467351,\n",
       " 0.02366404846179159,\n",
       " -0.007086889508446322,\n",
       " 0.01608415914668296,\n",
       " -0.007230681526176464,\n",
       " -0.03631774043410845,\n",
       " -0.00042270986361246735,\n",
       " 0.06844497622515978,\n",
       " -0.0030812563586354986,\n",
       " -0.03259969201824986,\n",
       " -0.029333560441077686,\n",
       " 0.023787299694025734,\n",
       " 0.03284619448271815,\n",
       " 0.02052116811685356,\n",
       " 0.006588753457672097,\n",
       " -0.03350352942091308,\n",
       " 0.028594058635608387,\n",
       " -0.004169967117190206,\n",
       " -0.013721862178206224,\n",
       " 0.024033800295848833,\n",
       " 0.011246585534396582,\n",
       " -0.0045345822414742335,\n",
       " 0.07649732549275733,\n",
       " 0.01640255412755659,\n",
       " -0.018035620847465274,\n",
       " 0.004321462104104332,\n",
       " -0.04761568189036606,\n",
       " 0.010306802804853287,\n",
       " 0.04001525132410014,\n",
       " -0.049957436676362904,\n",
       " -0.05870820710976034,\n",
       " 0.013824570296637884,\n",
       " -0.00038098451587661867,\n",
       " 0.054887448712824895,\n",
       " -0.04708159818440527,\n",
       " -0.014882468014303407,\n",
       " 0.03843353773208469,\n",
       " -0.007528536652876691,\n",
       " 0.011996357965444527,\n",
       " -0.018867560145787585,\n",
       " -0.052134857727811026,\n",
       " 0.024732217736358354,\n",
       " -0.13919061728342108,\n",
       " 0.05250460769922308,\n",
       " -0.06581563647238006,\n",
       " 0.03342136069099352,\n",
       " 0.010979543681416189,\n",
       " 0.015837658544859863,\n",
       " -0.019401643851748373,\n",
       " -0.04597234454487873,\n",
       " 0.02150717052414596,\n",
       " -0.012088796389620137,\n",
       " -0.027279390621863714,\n",
       " 0.029477352924469125,\n",
       " -0.02785455869278428,\n",
       " -0.021527711775303254,\n",
       " -0.012263400749747516,\n",
       " -0.006917420461108266,\n",
       " 0.0010001245174630373,\n",
       " -0.010234906563157568,\n",
       " -0.03418140561026531,\n",
       " -0.028101059294607378,\n",
       " -0.019668687567373954,\n",
       " -0.001239563831370168,\n",
       " 0.02352025784104534,\n",
       " ...]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query_result = embeddings.embed_query(texts[0].page_content)\n",
    "query_result"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We have the vector representation of the docuement, now we are going to store it in PineCone, which a vector store"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\index.py:4: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from tqdm.autonotebook import tqdm\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import pinecone\n",
    "from langchain.vectorstores import Pinecone\n",
    "\n",
    "#initialize pinecone\n",
    "pinecone.init(api_key= os.getenv(\"PINECONE_API_KEY\"), environment= os.getenv(\"PINECONE_ENV\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "ename": "ApiException",
     "evalue": "(400)\nReason: Bad Request\nHTTP response headers: HTTPHeaderDict({'content-type': 'application/json', 'date': 'Mon, 26 Jun 2023 11:22:55 GMT', 'x-envoy-upstream-service-time': '1', 'content-length': '104', 'server': 'envoy'})\nHTTP response body: {\"code\":3,\"message\":\"Vector dimension 1024 does not match the dimension of the index 1500\",\"details\":[]}\n",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mApiException\u001b[0m                              Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[36], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m index_name \u001b[39m=\u001b[39m \u001b[39m'\u001b[39m\u001b[39mlangchain-quickstart\u001b[39m\u001b[39m'\u001b[39m\n\u001b[1;32m----> 2\u001b[0m search \u001b[39m=\u001b[39m Pinecone\u001b[39m.\u001b[39;49mfrom_documents(texts, embeddings, index_name\u001b[39m=\u001b[39;49m index_name)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\langchain\\vectorstores\\base.py:164\u001b[0m, in \u001b[0;36mVectorStore.from_documents\u001b[1;34m(cls, documents, embedding, **kwargs)\u001b[0m\n\u001b[0;32m    162\u001b[0m texts \u001b[39m=\u001b[39m [d\u001b[39m.\u001b[39mpage_content \u001b[39mfor\u001b[39;00m d \u001b[39min\u001b[39;00m documents]\n\u001b[0;32m    163\u001b[0m metadatas \u001b[39m=\u001b[39m [d\u001b[39m.\u001b[39mmetadata \u001b[39mfor\u001b[39;00m d \u001b[39min\u001b[39;00m documents]\n\u001b[1;32m--> 164\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mcls\u001b[39;49m\u001b[39m.\u001b[39;49mfrom_texts(texts, embedding, metadatas\u001b[39m=\u001b[39;49mmetadatas, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\langchain\\vectorstores\\pinecone.py:246\u001b[0m, in \u001b[0;36mPinecone.from_texts\u001b[1;34m(cls, texts, embedding, metadatas, ids, batch_size, text_key, index_name, namespace, **kwargs)\u001b[0m\n\u001b[0;32m    243\u001b[0m     to_upsert \u001b[39m=\u001b[39m \u001b[39mzip\u001b[39m(ids_batch, embeds, metadata)\n\u001b[0;32m    245\u001b[0m     \u001b[39m# upsert to Pinecone\u001b[39;00m\n\u001b[1;32m--> 246\u001b[0m     index\u001b[39m.\u001b[39;49mupsert(vectors\u001b[39m=\u001b[39;49m\u001b[39mlist\u001b[39;49m(to_upsert), namespace\u001b[39m=\u001b[39;49mnamespace)\n\u001b[0;32m    247\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mcls\u001b[39m(index, embedding\u001b[39m.\u001b[39membed_query, text_key, namespace)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\utils\\error_handling.py:17\u001b[0m, in \u001b[0;36mvalidate_and_convert_errors.<locals>.inner_func\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m     15\u001b[0m Config\u001b[39m.\u001b[39mvalidate()  \u001b[39m# raises exceptions in case of invalid config\u001b[39;00m\n\u001b[0;32m     16\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m---> 17\u001b[0m     \u001b[39mreturn\u001b[39;00m func(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[0;32m     18\u001b[0m \u001b[39mexcept\u001b[39;00m MaxRetryError \u001b[39mas\u001b[39;00m e:\n\u001b[0;32m     19\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(e\u001b[39m.\u001b[39mreason, ProtocolError):\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\index.py:147\u001b[0m, in \u001b[0;36mIndex.upsert\u001b[1;34m(self, vectors, namespace, batch_size, show_progress, **kwargs)\u001b[0m\n\u001b[0;32m    142\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39m'\u001b[39m\u001b[39masync_req is not supported when batch_size is provided.\u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m    143\u001b[0m                      \u001b[39m'\u001b[39m\u001b[39mTo upsert in parallel, please follow: \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m    144\u001b[0m                      \u001b[39m'\u001b[39m\u001b[39mhttps://docs.pinecone.io/docs/insert-data#sending-upserts-in-parallel\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[0;32m    146\u001b[0m \u001b[39mif\u001b[39;00m batch_size \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m--> 147\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_upsert_batch(vectors, namespace, _check_type, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[0;32m    149\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39misinstance\u001b[39m(batch_size, \u001b[39mint\u001b[39m) \u001b[39mor\u001b[39;00m batch_size \u001b[39m<\u001b[39m\u001b[39m=\u001b[39m \u001b[39m0\u001b[39m:\n\u001b[0;32m    150\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39m'\u001b[39m\u001b[39mbatch_size must be a positive integer\u001b[39m\u001b[39m'\u001b[39m)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\index.py:231\u001b[0m, in \u001b[0;36mIndex._upsert_batch\u001b[1;34m(self, vectors, namespace, _check_type, **kwargs)\u001b[0m\n\u001b[0;32m    228\u001b[0m         \u001b[39mreturn\u001b[39;00m _dict_to_vector(item)\n\u001b[0;32m    229\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mInvalid vector value passed: cannot interpret type \u001b[39m\u001b[39m{\u001b[39;00m\u001b[39mtype\u001b[39m(item)\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m)\n\u001b[1;32m--> 231\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_vector_api\u001b[39m.\u001b[39;49mupsert(\n\u001b[0;32m    232\u001b[0m     UpsertRequest(\n\u001b[0;32m    233\u001b[0m         vectors\u001b[39m=\u001b[39;49m\u001b[39mlist\u001b[39;49m(\u001b[39mmap\u001b[39;49m(_vector_transform, vectors)),\n\u001b[0;32m    234\u001b[0m         \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49margs_dict,\n\u001b[0;32m    235\u001b[0m         _check_type\u001b[39m=\u001b[39;49m_check_type,\n\u001b[0;32m    236\u001b[0m         \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49m{k: v \u001b[39mfor\u001b[39;49;00m k, v \u001b[39min\u001b[39;49;00m kwargs\u001b[39m.\u001b[39;49mitems() \u001b[39mif\u001b[39;49;00m k \u001b[39mnot\u001b[39;49;00m \u001b[39min\u001b[39;49;00m _OPENAPI_ENDPOINT_PARAMS}\n\u001b[0;32m    237\u001b[0m     ),\n\u001b[0;32m    238\u001b[0m     \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49m{k: v \u001b[39mfor\u001b[39;49;00m k, v \u001b[39min\u001b[39;49;00m kwargs\u001b[39m.\u001b[39;49mitems() \u001b[39mif\u001b[39;49;00m k \u001b[39min\u001b[39;49;00m _OPENAPI_ENDPOINT_PARAMS}\n\u001b[0;32m    239\u001b[0m )\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\api_client.py:776\u001b[0m, in \u001b[0;36mEndpoint.__call__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m    765\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__call__\u001b[39m(\u001b[39mself\u001b[39m, \u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs):\n\u001b[0;32m    766\u001b[0m     \u001b[39m\"\"\" This method is invoked when endpoints are called\u001b[39;00m\n\u001b[0;32m    767\u001b[0m \u001b[39m    Example:\u001b[39;00m\n\u001b[0;32m    768\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    774\u001b[0m \n\u001b[0;32m    775\u001b[0m \u001b[39m    \"\"\"\u001b[39;00m\n\u001b[1;32m--> 776\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mcallable(\u001b[39mself\u001b[39;49m, \u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\api\\vector_operations_api.py:956\u001b[0m, in \u001b[0;36mVectorOperationsApi.__init__.<locals>.__upsert\u001b[1;34m(self, upsert_request, **kwargs)\u001b[0m\n\u001b[0;32m    953\u001b[0m kwargs[\u001b[39m'\u001b[39m\u001b[39m_host_index\u001b[39m\u001b[39m'\u001b[39m] \u001b[39m=\u001b[39m kwargs\u001b[39m.\u001b[39mget(\u001b[39m'\u001b[39m\u001b[39m_host_index\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[0;32m    954\u001b[0m kwargs[\u001b[39m'\u001b[39m\u001b[39mupsert_request\u001b[39m\u001b[39m'\u001b[39m] \u001b[39m=\u001b[39m \\\n\u001b[0;32m    955\u001b[0m     upsert_request\n\u001b[1;32m--> 956\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mcall_with_http_info(\u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\api_client.py:838\u001b[0m, in \u001b[0;36mEndpoint.call_with_http_info\u001b[1;34m(self, **kwargs)\u001b[0m\n\u001b[0;32m    834\u001b[0m     header_list \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mapi_client\u001b[39m.\u001b[39mselect_header_content_type(\n\u001b[0;32m    835\u001b[0m         content_type_headers_list)\n\u001b[0;32m    836\u001b[0m     params[\u001b[39m'\u001b[39m\u001b[39mheader\u001b[39m\u001b[39m'\u001b[39m][\u001b[39m'\u001b[39m\u001b[39mContent-Type\u001b[39m\u001b[39m'\u001b[39m] \u001b[39m=\u001b[39m header_list\n\u001b[1;32m--> 838\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mapi_client\u001b[39m.\u001b[39;49mcall_api(\n\u001b[0;32m    839\u001b[0m     \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msettings[\u001b[39m'\u001b[39;49m\u001b[39mendpoint_path\u001b[39;49m\u001b[39m'\u001b[39;49m], \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msettings[\u001b[39m'\u001b[39;49m\u001b[39mhttp_method\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    840\u001b[0m     params[\u001b[39m'\u001b[39;49m\u001b[39mpath\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    841\u001b[0m     params[\u001b[39m'\u001b[39;49m\u001b[39mquery\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    842\u001b[0m     params[\u001b[39m'\u001b[39;49m\u001b[39mheader\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    843\u001b[0m     body\u001b[39m=\u001b[39;49mparams[\u001b[39m'\u001b[39;49m\u001b[39mbody\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    844\u001b[0m     post_params\u001b[39m=\u001b[39;49mparams[\u001b[39m'\u001b[39;49m\u001b[39mform\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    845\u001b[0m     files\u001b[39m=\u001b[39;49mparams[\u001b[39m'\u001b[39;49m\u001b[39mfile\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    846\u001b[0m     response_type\u001b[39m=\u001b[39;49m\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msettings[\u001b[39m'\u001b[39;49m\u001b[39mresponse_type\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    847\u001b[0m     auth_settings\u001b[39m=\u001b[39;49m\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msettings[\u001b[39m'\u001b[39;49m\u001b[39mauth\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    848\u001b[0m     async_req\u001b[39m=\u001b[39;49mkwargs[\u001b[39m'\u001b[39;49m\u001b[39masync_req\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    849\u001b[0m     _check_type\u001b[39m=\u001b[39;49mkwargs[\u001b[39m'\u001b[39;49m\u001b[39m_check_return_type\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    850\u001b[0m     _return_http_data_only\u001b[39m=\u001b[39;49mkwargs[\u001b[39m'\u001b[39;49m\u001b[39m_return_http_data_only\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    851\u001b[0m     _preload_content\u001b[39m=\u001b[39;49mkwargs[\u001b[39m'\u001b[39;49m\u001b[39m_preload_content\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    852\u001b[0m     _request_timeout\u001b[39m=\u001b[39;49mkwargs[\u001b[39m'\u001b[39;49m\u001b[39m_request_timeout\u001b[39;49m\u001b[39m'\u001b[39;49m],\n\u001b[0;32m    853\u001b[0m     _host\u001b[39m=\u001b[39;49m_host,\n\u001b[0;32m    854\u001b[0m     collection_formats\u001b[39m=\u001b[39;49mparams[\u001b[39m'\u001b[39;49m\u001b[39mcollection_format\u001b[39;49m\u001b[39m'\u001b[39;49m])\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\api_client.py:413\u001b[0m, in \u001b[0;36mApiClient.call_api\u001b[1;34m(self, resource_path, method, path_params, query_params, header_params, body, post_params, files, response_type, auth_settings, async_req, _return_http_data_only, collection_formats, _preload_content, _request_timeout, _host, _check_type)\u001b[0m\n\u001b[0;32m    359\u001b[0m \u001b[39m\"\"\"Makes the HTTP request (synchronous) and returns deserialized data.\u001b[39;00m\n\u001b[0;32m    360\u001b[0m \n\u001b[0;32m    361\u001b[0m \u001b[39mTo make an async_req request, set the async_req parameter.\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    410\u001b[0m \u001b[39m    then the method will return the response directly.\u001b[39;00m\n\u001b[0;32m    411\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[0;32m    412\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m async_req:\n\u001b[1;32m--> 413\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m__call_api(resource_path, method,\n\u001b[0;32m    414\u001b[0m                            path_params, query_params, header_params,\n\u001b[0;32m    415\u001b[0m                            body, post_params, files,\n\u001b[0;32m    416\u001b[0m                            response_type, auth_settings,\n\u001b[0;32m    417\u001b[0m                            _return_http_data_only, collection_formats,\n\u001b[0;32m    418\u001b[0m                            _preload_content, _request_timeout, _host,\n\u001b[0;32m    419\u001b[0m                            _check_type)\n\u001b[0;32m    421\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpool\u001b[39m.\u001b[39mapply_async(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m__call_api, (resource_path,\n\u001b[0;32m    422\u001b[0m                                                method, path_params,\n\u001b[0;32m    423\u001b[0m                                                query_params,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    431\u001b[0m                                                _request_timeout,\n\u001b[0;32m    432\u001b[0m                                                _host, _check_type))\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\api_client.py:207\u001b[0m, in \u001b[0;36mApiClient.__call_api\u001b[1;34m(self, resource_path, method, path_params, query_params, header_params, body, post_params, files, response_type, auth_settings, _return_http_data_only, collection_formats, _preload_content, _request_timeout, _host, _check_type)\u001b[0m\n\u001b[0;32m    205\u001b[0m \u001b[39mexcept\u001b[39;00m ApiException \u001b[39mas\u001b[39;00m e:\n\u001b[0;32m    206\u001b[0m     e\u001b[39m.\u001b[39mbody \u001b[39m=\u001b[39m e\u001b[39m.\u001b[39mbody\u001b[39m.\u001b[39mdecode(\u001b[39m'\u001b[39m\u001b[39mutf-8\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m--> 207\u001b[0m     \u001b[39mraise\u001b[39;00m e\n\u001b[0;32m    209\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mlast_response \u001b[39m=\u001b[39m response_data\n\u001b[0;32m    211\u001b[0m return_data \u001b[39m=\u001b[39m response_data\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\api_client.py:200\u001b[0m, in \u001b[0;36mApiClient.__call_api\u001b[1;34m(self, resource_path, method, path_params, query_params, header_params, body, post_params, files, response_type, auth_settings, _return_http_data_only, collection_formats, _preload_content, _request_timeout, _host, _check_type)\u001b[0m\n\u001b[0;32m    196\u001b[0m     url \u001b[39m=\u001b[39m _host \u001b[39m+\u001b[39m resource_path\n\u001b[0;32m    198\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m    199\u001b[0m     \u001b[39m# perform request and return response\u001b[39;00m\n\u001b[1;32m--> 200\u001b[0m     response_data \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mrequest(\n\u001b[0;32m    201\u001b[0m         method, url, query_params\u001b[39m=\u001b[39;49mquery_params, headers\u001b[39m=\u001b[39;49mheader_params,\n\u001b[0;32m    202\u001b[0m         post_params\u001b[39m=\u001b[39;49mpost_params, body\u001b[39m=\u001b[39;49mbody,\n\u001b[0;32m    203\u001b[0m         _preload_content\u001b[39m=\u001b[39;49m_preload_content,\n\u001b[0;32m    204\u001b[0m         _request_timeout\u001b[39m=\u001b[39;49m_request_timeout)\n\u001b[0;32m    205\u001b[0m \u001b[39mexcept\u001b[39;00m ApiException \u001b[39mas\u001b[39;00m e:\n\u001b[0;32m    206\u001b[0m     e\u001b[39m.\u001b[39mbody \u001b[39m=\u001b[39m e\u001b[39m.\u001b[39mbody\u001b[39m.\u001b[39mdecode(\u001b[39m'\u001b[39m\u001b[39mutf-8\u001b[39m\u001b[39m'\u001b[39m)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\api_client.py:459\u001b[0m, in \u001b[0;36mApiClient.request\u001b[1;34m(self, method, url, query_params, headers, post_params, body, _preload_content, _request_timeout)\u001b[0m\n\u001b[0;32m    451\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mrest_client\u001b[39m.\u001b[39mOPTIONS(url,\n\u001b[0;32m    452\u001b[0m                                     query_params\u001b[39m=\u001b[39mquery_params,\n\u001b[0;32m    453\u001b[0m                                     headers\u001b[39m=\u001b[39mheaders,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    456\u001b[0m                                     _request_timeout\u001b[39m=\u001b[39m_request_timeout,\n\u001b[0;32m    457\u001b[0m                                     body\u001b[39m=\u001b[39mbody)\n\u001b[0;32m    458\u001b[0m \u001b[39melif\u001b[39;00m method \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mPOST\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[1;32m--> 459\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mrest_client\u001b[39m.\u001b[39;49mPOST(url,\n\u001b[0;32m    460\u001b[0m                                  query_params\u001b[39m=\u001b[39;49mquery_params,\n\u001b[0;32m    461\u001b[0m                                  headers\u001b[39m=\u001b[39;49mheaders,\n\u001b[0;32m    462\u001b[0m                                  post_params\u001b[39m=\u001b[39;49mpost_params,\n\u001b[0;32m    463\u001b[0m                                  _preload_content\u001b[39m=\u001b[39;49m_preload_content,\n\u001b[0;32m    464\u001b[0m                                  _request_timeout\u001b[39m=\u001b[39;49m_request_timeout,\n\u001b[0;32m    465\u001b[0m                                  body\u001b[39m=\u001b[39;49mbody)\n\u001b[0;32m    466\u001b[0m \u001b[39melif\u001b[39;00m method \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mPUT\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[0;32m    467\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mrest_client\u001b[39m.\u001b[39mPUT(url,\n\u001b[0;32m    468\u001b[0m                                 query_params\u001b[39m=\u001b[39mquery_params,\n\u001b[0;32m    469\u001b[0m                                 headers\u001b[39m=\u001b[39mheaders,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    472\u001b[0m                                 _request_timeout\u001b[39m=\u001b[39m_request_timeout,\n\u001b[0;32m    473\u001b[0m                                 body\u001b[39m=\u001b[39mbody)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\rest.py:271\u001b[0m, in \u001b[0;36mRESTClientObject.POST\u001b[1;34m(self, url, headers, query_params, post_params, body, _preload_content, _request_timeout)\u001b[0m\n\u001b[0;32m    269\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mPOST\u001b[39m(\u001b[39mself\u001b[39m, url, headers\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m, query_params\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m, post_params\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m,\n\u001b[0;32m    270\u001b[0m          body\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m, _preload_content\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m, _request_timeout\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m):\n\u001b[1;32m--> 271\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mrequest(\u001b[39m\"\u001b[39;49m\u001b[39mPOST\u001b[39;49m\u001b[39m\"\u001b[39;49m, url,\n\u001b[0;32m    272\u001b[0m                         headers\u001b[39m=\u001b[39;49mheaders,\n\u001b[0;32m    273\u001b[0m                         query_params\u001b[39m=\u001b[39;49mquery_params,\n\u001b[0;32m    274\u001b[0m                         post_params\u001b[39m=\u001b[39;49mpost_params,\n\u001b[0;32m    275\u001b[0m                         _preload_content\u001b[39m=\u001b[39;49m_preload_content,\n\u001b[0;32m    276\u001b[0m                         _request_timeout\u001b[39m=\u001b[39;49m_request_timeout,\n\u001b[0;32m    277\u001b[0m                         body\u001b[39m=\u001b[39;49mbody)\n",
      "File \u001b[1;32mc:\\Users\\VANI SETH\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\pinecone\\core\\client\\rest.py:230\u001b[0m, in \u001b[0;36mRESTClientObject.request\u001b[1;34m(self, method, url, query_params, headers, body, post_params, _preload_content, _request_timeout)\u001b[0m\n\u001b[0;32m    227\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39m500\u001b[39m \u001b[39m<\u001b[39m\u001b[39m=\u001b[39m r\u001b[39m.\u001b[39mstatus \u001b[39m<\u001b[39m\u001b[39m=\u001b[39m \u001b[39m599\u001b[39m:\n\u001b[0;32m    228\u001b[0m         \u001b[39mraise\u001b[39;00m ServiceException(http_resp\u001b[39m=\u001b[39mr)\n\u001b[1;32m--> 230\u001b[0m     \u001b[39mraise\u001b[39;00m ApiException(http_resp\u001b[39m=\u001b[39mr)\n\u001b[0;32m    232\u001b[0m \u001b[39mreturn\u001b[39;00m r\n",
      "\u001b[1;31mApiException\u001b[0m: (400)\nReason: Bad Request\nHTTP response headers: HTTPHeaderDict({'content-type': 'application/json', 'date': 'Mon, 26 Jun 2023 11:22:55 GMT', 'x-envoy-upstream-service-time': '1', 'content-length': '104', 'server': 'envoy'})\nHTTP response body: {\"code\":3,\"message\":\"Vector dimension 1024 does not match the dimension of the index 1500\",\"details\":[]}\n"
     ]
    }
   ],
   "source": [
    "index_name = 'langchain-quickstart'\n",
    "search = Pinecone.from_documents(texts, embeddings, index_name= index_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "query = \"What is different about encoder?\"\n",
    "result = search.similarity_search(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "result"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Agents\n",
    "\n",
    "Go over to OpenAI, chatGPT's plug-in page, you'll notice a python code interpreter, we will do something similar in langchain."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "from langchain.agents.agent_toolkits import create_python_agent\n",
    "from langchain.tools.python.tool import PythonREPLTool\n",
    "from langchain.python import PythonREPL\n",
    "from langchain.llms.openai import OpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# initiating a python agent executor\n",
    "\n",
    "agent_executor = create_python_agent(\n",
    "    llm = OpenAI(temperature=0, max_tokens=1000),\n",
    "    tool = PythonREPLTool(),\n",
    "    verbose = True\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# allowing language model to run python code\n",
    "agent_executor.run(\"FInd the roots (zeros) if the quadratic fucntion 3 * x**2 + 2 * x - 1\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.1"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}