practice.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "47fe0518-8997-4575-a69e-aad12efeb57e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# from secret_key import openapi_key\n",
    "# import os\n",
    "# os.environ['OPENAI_API_KEY'] = openapi_key\n",
    "\n",
    "import os\n",
    "os.environ['OPENAI_API_KEY'] = \"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\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bcfbfc5a-bb66-4e9d-92b9-106579741a42",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\"The Masala Mantra\"\n"
     ]
    }
   ],
   "source": [
    "from langchain.llms import OpenAI\n",
    "\n",
    "llm = OpenAI(temperature=0.9)\n",
    "name = llm.predict(\"I want to open a restaurant for Indian food. Suggest a fency name for this.\")\n",
    "print(name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "11656c56-f174-46ce-9b46-1c6558366b12",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"\\n\\nMaharaja's Palace of Indian Cuisine\""
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm(\"I want to open a restaurant for Indian food. Suggest a fency name for this.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "976df71a-66c8-4730-9e76-88e1deb49483",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "I want to open a restaurant for Italian food. Suggest a fency name for this.\n"
     ]
    }
   ],
   "source": [
    "from langchain.prompts import PromptTemplate\n",
    "\n",
    "prompt_template_name = PromptTemplate(\n",
    "    input_variables =['cuisine'],\n",
    "    template = \"I want to open a restaurant for {cuisine} food. Suggest a fency name for this.\"\n",
    ")\n",
    "p = prompt_template_name.format(cuisine=\"Italian\")\n",
    "print(p)\n",
    "\n",
    "# print(llm.predict(p))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "56a1a990-43b7-4fa5-a9fe-a7b7fbfd18c6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n\\nForkful of Flavor'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.chains import LLMChain\n",
    "\n",
    "chain = LLMChain(llm=llm, prompt=prompt_template_name)\n",
    "chain.run(\"American\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "06daa175-57e5-4762-befb-e01b19e747fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0.6)\n",
    "\n",
    "prompt_template_name = PromptTemplate(\n",
    "    input_variables =['cuisine'],\n",
    "    template = \"I want to open a restaurant for {cuisine} food. Suggest a fency name for this.\"\n",
    ")\n",
    "\n",
    "name_chain =LLMChain(llm=llm, prompt=prompt_template_name)\n",
    "\n",
    "prompt_template_items = PromptTemplate(\n",
    "    input_variables = ['restaurant_name'],\n",
    "    template=\"\"\"Suggest some menu items for {restaurant_name}\"\"\"\n",
    ")\n",
    "\n",
    "food_items_chain = LLMChain(llm=llm, prompt=prompt_template_items)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "16ac6fd6-5a28-42e5-a4e5-a4e730743795",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "-Tandoori Chicken \n",
      "-Butter Chicken \n",
      "-Matar Paneer \n",
      "-Chana Masala \n",
      "-Aloo Gobi \n",
      "-Samosas \n",
      "-Vegetable Biryani \n",
      "-Naan Bread \n",
      "-Raita \n",
      "-Mango Lassi \n",
      "-Gulab Jamun\n"
     ]
    }
   ],
   "source": [
    "from langchain.chains import SimpleSequentialChain\n",
    "chain = SimpleSequentialChain(chains = [name_chain, food_items_chain])\n",
    "\n",
    "content = chain.run(\"Indian\")\n",
    "print(content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "c5ac9a53-26d5-4060-ad80-8f946bfb4258",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0.7)\n",
    "\n",
    "prompt_template_name = PromptTemplate(\n",
    "    input_variables =['cuisine'],\n",
    "    template = \"I want to open a restaurant for {cuisine} food. Suggest a fency name for this.\"\n",
    ")\n",
    "\n",
    "name_chain =LLMChain(llm=llm, prompt=prompt_template_name, output_key=\"restaurant_name\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "63890314-7944-4663-8c7c-7a27c58e2773",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0.7)\n",
    "\n",
    "prompt_template_items = PromptTemplate(\n",
    "    input_variables = ['restaurant_name'],\n",
    "    template=\"Suggest some menu items for {restaurant_name}.\"\n",
    ")\n",
    "\n",
    "food_items_chain =LLMChain(llm=llm, prompt=prompt_template_items, output_key=\"menu_items\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "b2bb5cd6-e4ed-4e6e-9a3b-98d539b26fb7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains import SequentialChain\n",
    "\n",
    "chain = SequentialChain(\n",
    "    chains = [name_chain, food_items_chain],\n",
    "    input_variables = ['cuisine'],\n",
    "    output_variables = ['restaurant_name', \"menu_items\"]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "32a0be13-cd82-48dd-a30a-9df926dc02cc",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'cuisine': 'Indian',\n",
       " 'restaurant_name': '\\n\\n\"The Spice Palace\"',\n",
       " 'menu_items': '\\n\\n-Tandoori Chicken\\n-Coconut Curry\\n-Lamb Kebab\\n-Mango Chutney\\n-Biryani\\n-Tikka Masala\\n-Saag Paneer\\n-Chilli Paneer\\n-Butter Chicken\\n-Masala Dosa\\n-Samosas\\n-Naan Bread\\n-Papadum\\n-Mint Raita'}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain({\"cuisine\": \"Indian\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "decf6412-55c1-4a28-916c-8bf6f3b3e214",
   "metadata": {},
   "outputs": [],
   "source": [
    "os.environ['SERPAPI_API_KEY'] = \"c244a84dc9684b7b595e10f9aa4b2fba96e43bc89a37b25ce66e69c21dc9786d\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "268371e2-3fec-4d7e-86d4-a97560cc067d",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "db87257c-0a1a-4293-a406-ec95ff85ed18",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m I need to find the GDP of US in 2022\n",
      "Action: Search\n",
      "Action Input: US GDP in 2022\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m25462.70 USD Billion\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to add 5 to this number\n",
      "Action: Calculator\n",
      "Action Input: 25462.70 + 5\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 25467.7\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: 25467.7 USD Billion\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'25467.7 USD Billion'"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.agents import AgentType, initialize_agent, load_tools\n",
    "from langchain.llms import OpenAI\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "\n",
    "# The tools we'll give the Agent access to. Note that the 'llm-math' tool uses an LLM, so we need to pass that in.\n",
    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
    "\n",
    "# Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.\n",
    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)\n",
    "\n",
    "# Let's test it out!\n",
    "agent.run(\"What was the GDP of US in 2022 plus 5?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "84702f3c-ed24-4911-8472-bf07bfdb28c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.memory import ConversationBufferMemory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "fb6f991d-1087-4b19-b534-098a0defec41",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "Taco Fiesta\n"
     ]
    }
   ],
   "source": [
    "from langchain.memory import ConversationBufferMemory\n",
    "\n",
    "memory = ConversationBufferMemory()\n",
    "\n",
    "chain = LLMChain(llm=llm, prompt=prompt_template_name, memory=memory)\n",
    "name = chain.run(\"Mexican\")\n",
    "print(name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "e0811438-a245-4246-bd42-eedd1cae377e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "langchain.memory.buffer.ConversationBufferMemory"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(chain.memory)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "766e0fbc-3cd8-4f52-af59-4a8a7d8ced17",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "Al-Fez Restaurant\n"
     ]
    }
   ],
   "source": [
    "name = chain.run(\"Arabic\")\n",
    "print(name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "5057ef2a-d9a0-4f56-bef4-79cbb2c03dcf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Human: Mexican\n",
      "AI: \n",
      "\n",
      "Taco Fiesta\n",
      "Human: Arabic\n",
      "AI: \n",
      "\n",
      "Al-Fez Restaurant\n"
     ]
    }
   ],
   "source": [
    "print(chain.memory.buffer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "6fc354e4-f706-41e1-ad12-1ecc4ed54442",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
      "\n",
      "Current conversation:\n",
      "{history}\n",
      "Human: {input}\n",
      "AI:\n"
     ]
    }
   ],
   "source": [
    "from langchain.chains import ConversationChain\n",
    "\n",
    "convo = ConversationChain(llm=OpenAI(temperature=0.7))\n",
    "print(convo.prompt.template)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "2ec0511b-4ce8-49c1-8079-c53de98575e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' The first Cricket World Cup was won by the West Indies in 1975. They beat Australia by 17 runs in the final.'"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "convo.run(\"Who won the first cricket world cup?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "8fba5967-a12b-4e7f-b837-9ba7e3e26daf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' 5+5 is equal to 10.'"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "convo.run(\"How much is 5+5?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "81b024ae-5a33-4f07-bb2b-be6ce2c6f875",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' The captain of the winning team in the 1975 Cricket World Cup was Clive Lloyd.'"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "convo.run(\"Who was the captain ofthe winning team?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "1ca0825d-d830-4ecf-8974-ac067dea8231",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Human: Who won the first cricket world cup?\n",
      "AI:  The first Cricket World Cup was held in 1975 between England and Australia and Australia won the tournament by 17 runs.\n",
      "Human: How much is 5+5?\n",
      "AI:  The sum of 5 + 5 is 10.\n",
      "Human: Who was the captain of the winning team?\n",
      "AI:  The captain of the winning team at the 1975 Cricket World Cup was Ian Chappell from Australia.\n"
     ]
    }
   ],
   "source": [
    "print(convo.memory.buffer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "744b8d41-708e-455c-b369-0b6cd67e6d6a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' The first Cricket World Cup was held in 1975 between England and Australia and Australia won the tournament by 17 runs.'"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.memory import ConversationBufferWindowMemory\n",
    "\n",
    "memory = ConversationBufferWindowMemory(k=5)\n",
    "\n",
    "convo = ConversationChain(\n",
    "    llm=OpenAI(temperature=0.7),\n",
    "    memory=memory\n",
    ")\n",
    "convo.run(\"Who won the first cricket world cup?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "f1d29ba0-4e33-49d5-8fc0-debc95484bd9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' The sum of 5 + 5 is 10.'"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "convo.run(\"How much is 5+5?\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "4ab98548-66ce-4ebe-aab4-bd98e184a5a8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' The captain of the winning team at the 1975 Cricket World Cup was Ian Chappell from Australia.'"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "convo.run(\"Who was the captain of the winning team?\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}