Create ChatGPT clone-Copy1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "sgbMZHz6pmAt"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "\n",
      "Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "```\n",
      "/home/user\n",
      "```\n"
     ]
    }
   ],
   "source": [
    "from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate\n",
    "from langchain.memory import ConversationBufferWindowMemory\n",
    "\n",
    "\n",
    "template = \"\"\"Assistant is a large language model trained by OpenAI.\n",
    "\n",
    "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
    "\n",
    "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
    "\n",
    "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
    "\n",
    "{history}\n",
    "Human: {human_input}\n",
    "Assistant:\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(input_variables=[\"history\", \"human_input\"], template=template)\n",
    "\n",
    "\n",
    "chatgpt_chain = LLMChain(\n",
    "    llm=OpenAI(temperature=0),\n",
    "    prompt=prompt,\n",
    "    verbose=True,\n",
    "    memory=ConversationBufferWindowMemory(k=2),\n",
    ")\n",
    "\n",
    "output = chatgpt_chain.predict(\n",
    "    human_input=\"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\"\n",
    ")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "id": "PhfJZXA7pxGS"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\n",
      "AI: \n",
      "```\n",
      "/home/user\n",
      "```\n",
      "Human: ls ~\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "```\n",
      "Desktop/ Documents/ Downloads/ Music/ Pictures/ Public/ Templates/ Videos/\n",
      "```\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(human_input=\"ls ~\")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "id": "Z9xLa-bjpzL5"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\n",
      "AI: \n",
      "```\n",
      "/home/user\n",
      "```\n",
      "Human: ls ~\n",
      "AI: \n",
      "```\n",
      "Desktop/ Documents/ Downloads/ Music/ Pictures/ Public/ Templates/ Videos/\n",
      "```\n",
      "Human: cd ~\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      " \n",
      "```\n",
      "/home/user\n",
      "```\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(human_input=\"cd ~\")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "id": "NGtaZxZKp2sX"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: ls ~\n",
      "AI: \n",
      "```\n",
      "Desktop/ Documents/ Downloads/ Music/ Pictures/ Public/ Templates/ Videos/\n",
      "```\n",
      "Human: cd ~\n",
      "AI:  \n",
      "```\n",
      "/home/user\n",
      "```\n",
      "Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "Jokes.txt created.\n",
      "\n",
      "Jokes added to jokes.txt:\n",
      "\n",
      "Q: What did the fish say when it hit the wall?\n",
      "A: Dam!\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(\n",
    "    human_input=\"{Please make a file jokes.txt inside and put some jokes inside}\"\n",
    ")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "id": "SD7JLJKhqCMa"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: cd ~\n",
      "AI:  \n",
      "```\n",
      "/home/user\n",
      "```\n",
      "Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
      "AI: \n",
      "\n",
      "Jokes.txt created.\n",
      "\n",
      "Jokes added to jokes.txt:\n",
      "\n",
      "Q: What did the fish say when it hit the wall?\n",
      "A: Dam!\n",
      "Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "Result:33\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(\n",
    "    human_input=\"\"\"echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\"\"\"\n",
    ")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "id": "RS0rTE6rqD5I"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
      "AI: \n",
      "\n",
      "Jokes.txt created.\n",
      "\n",
      "Jokes added to jokes.txt:\n",
      "\n",
      "Q: What did the fish say when it hit the wall?\n",
      "A: Dam!\n",
      "Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
      "AI: \n",
      "\n",
      "Result:33\n",
      "Human: echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "Result:[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(\n",
    "    human_input=\"\"\"echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\"\"\"\n",
    ")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "id": "OZ5NQvFFqGDa"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
      "AI: \n",
      "\n",
      "Result:33\n",
      "Human: echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\n",
      "AI: \n",
      "\n",
      "Result:[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]\n",
      "Human: echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\n",
      "COPY entrypoint.sh entrypoint.sh\n",
      "ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "Hello from Docker\n"
     ]
    }
   ],
   "source": [
    "docker_input = \"\"\"echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\\nCOPY entrypoint.sh entrypoint.sh\\nENTRYPOINT [\\\"/bin/sh\\\",\\\"entrypoint.sh\\\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\"\"\"\n",
    "output = chatgpt_chain.predict(human_input=docker_input)\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "id": "AjscXNifqR5U"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\n",
      "AI: \n",
      "\n",
      "Result:[2, 3, 5, 7, 11, 13, 17, 19, 23, 29]\n",
      "Human: echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\n",
      "COPY entrypoint.sh entrypoint.sh\n",
      "ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\n",
      "AI: \n",
      "\n",
      "Hello from Docker\n",
      "Human: nvidia-smi\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "Nvidia-smi is a command line utility that allows you to view information about your Nvidia GPU, such as its current utilization, temperature, memory usage, and more. It can also be used to control various settings on your GPU, such as overclocking and fan speed.\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(human_input=\"nvidia-smi\")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "52mR6D6uqSQb"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\n",
      "COPY entrypoint.sh entrypoint.sh\n",
      "ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\n",
      "AI: \n",
      "\n",
      "Hello from Docker\n",
      "Human: nvidia-smi\n",
      "AI: \n",
      "\n",
      "Nvidia-smi is a command line utility that allows you to view information about your Nvidia GPU, such as its current utilization, temperature, memory usage, and more. It can also be used to control various settings on your GPU, such as overclocking and fan speed.\n",
      "Human: ping bbc.com\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "Pinging bbc.com [212.58.244.70] with 32 bytes of data:\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "\n",
      "Ping statistics for 212.58.244.70:\n",
      "    Packets: Sent = 3, Received = 3, Lost = 0 (0% loss),\n",
      "Approximate round trip times in milli-seconds:\n",
      "    Minimum = 25ms, Maximum = 25ms, Average = 25ms\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(human_input=\"ping bbc.com\")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "id": "ecdtDV_XqT7A"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: nvidia-smi\n",
      "AI: \n",
      "\n",
      "Nvidia-smi is a command line utility that allows you to view information about your Nvidia GPU, such as its current utilization, temperature, memory usage, and more. It can also be used to control various settings on your GPU, such as overclocking and fan speed.\n",
      "Human: ping bbc.com\n",
      "AI: \n",
      "\n",
      "Pinging bbc.com [212.58.244.70] with 32 bytes of data:\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "\n",
      "Ping statistics for 212.58.244.70:\n",
      "    Packets: Sent = 3, Received = 3, Lost = 0 (0% loss),\n",
      "Approximate round trip times in milli-seconds:\n",
      "    Minimum = 25ms, Maximum = 25ms, Average = 25ms\n",
      "Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "The command you entered will return the latest version of PyTorch. The output of the command should be a version number such as \"1.7.1\" or \"1.8.0\".\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(\n",
    "    human_input=\"\"\"curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\"\"\"\n",
    ")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "i50CIUU_qVKh"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: ping bbc.com\n",
      "AI: \n",
      "\n",
      "Pinging bbc.com [212.58.244.70] with 32 bytes of data:\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "Reply from 212.58.244.70: bytes=32 time=25ms TTL=54\n",
      "\n",
      "Ping statistics for 212.58.244.70:\n",
      "    Packets: Sent = 3, Received = 3, Lost = 0 (0% loss),\n",
      "Approximate round trip times in milli-seconds:\n",
      "    Minimum = 25ms, Maximum = 25ms, Average = 25ms\n",
      "Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
      "AI: \n",
      "\n",
      "The command you entered will return the latest version of PyTorch. The output of the command should be a version number such as \"1.7.1\" or \"1.8.0\".\n",
      "Human: lynx https://www.deepmind.com/careers\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "Lynx is a text-based web browser that can be used to view webpages. When you enter the command \"lynx https://www.deepmind.com/careers\", Lynx will open the DeepMind Careers page in a text-based format. You can then use the arrow keys to navigate the page and view the available job postings.\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(human_input=\"lynx https://www.deepmind.com/careers\")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "id": "InzZFgiiqWyx"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
      "AI: \n",
      "\n",
      "The command you entered will return the latest version of PyTorch. The output of the command should be a version number such as \"1.7.1\" or \"1.8.0\".\n",
      "Human: lynx https://www.deepmind.com/careers\n",
      "AI: \n",
      "\n",
      "Lynx is a text-based web browser that can be used to view webpages. When you enter the command \"lynx https://www.deepmind.com/careers\", Lynx will open the DeepMind Careers page in a text-based format. You can then use the arrow keys to navigate the page and view the available job postings.\n",
      "Human: curl https://chat.openai.com/chat\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "The command you entered will open a chat window with OpenAI. You can use this chat window to ask questions and get answers from OpenAI's team of experts. You can also use the chat window to discuss topics related to AI and machine learning.\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(human_input=\"curl https://chat.openai.com/chat\")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "id": "BBJx0zCIqcev"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: lynx https://www.deepmind.com/careers\n",
      "AI: \n",
      "\n",
      "Lynx is a text-based web browser that can be used to view webpages. When you enter the command \"lynx https://www.deepmind.com/careers\", Lynx will open the DeepMind Careers page in a text-based format. You can then use the arrow keys to navigate the page and view the available job postings.\n",
      "Human: curl https://chat.openai.com/chat\n",
      "AI: \n",
      "\n",
      "The command you entered will open a chat window with OpenAI. You can use this chat window to ask questions and get answers from OpenAI's team of experts. You can also use the chat window to discuss topics related to AI and machine learning.\n",
      "Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "The command you entered will send a POST request to the OpenAI chat window with the message \"What is artificial intelligence?\". The response you will receive will be an explanation of artificial intelligence, including its definition, applications, and potential implications.\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(\n",
    "    human_input=\"\"\"curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\"\"\"\n",
    ")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "id": "JjzKFMbfqeYj"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
      "\n",
      "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
      "\n",
      "Assistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
      "\n",
      "Overall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n",
      "\n",
      "Human: curl https://chat.openai.com/chat\n",
      "AI: \n",
      "\n",
      "The command you entered will open a chat window with OpenAI. You can use this chat window to ask questions and get answers from OpenAI's team of experts. You can also use the chat window to discuss topics related to AI and machine learning.\n",
      "Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
      "AI: \n",
      "\n",
      "The command you entered will send a POST request to the OpenAI chat window with the message \"What is artificial intelligence?\". The response you will receive will be an explanation of artificial intelligence, including its definition, applications, and potential implications.\n",
      "Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\"}' https://chat.openai.com/chat\n",
      "Assistant:\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
      "\n",
      "```\n",
      "/home/user\n",
      "```\n"
     ]
    }
   ],
   "source": [
    "output = chatgpt_chain.predict(\n",
    "    human_input=\"\"\"curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\"}' https://chat.openai.com/chat\"\"\"\n",
    ")\n",
    "print(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "authorship_tag": "ABX9TyMO1zXaichVGy8LuvwgS7d0",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}