Chapter7_Continue(Advanced_Text_Generation).ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "authorship_tag": "ABX9TyPwlD0wHoq7uUbkkWGNW8Cb",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Zohreh6384NKH/LLM_Project/blob/main/Chapter7_Continue(Advanced_Text_Generation).ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "##**Agents**"
      ],
      "metadata": {
        "id": "aQiTppqzWW97"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install langchain>=0.1.17 openai>=1.13.3 langchain_openai>=0.1.6 transformers>=4.40.1 datasets>=2.18.0 accelerate>=0.27.2 sentence-transformers>=2.5.1 duckduckgo-search>=5.2.2 langchain_community\n",
        "!CMAKE_ARGS=\"-DLLAMA_CUDA=on\" pip install llama-cpp-python==0.2.69\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Wweb2EjLWXHh",
        "outputId": "222c1eda-2c0d-47b8-826c-00addbd0b484"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "gcsfs 2024.10.0 requires fsspec==2024.10.0, but you have fsspec 2024.9.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mCollecting llama-cpp-python==0.2.69\n",
            "  Downloading llama_cpp_python-0.2.69.tar.gz (42.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.5/42.5 MB\u001b[0m \u001b[31m25.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
            "  Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python==0.2.69) (4.12.2)\n",
            "Requirement already satisfied: numpy>=1.20.0 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python==0.2.69) (1.26.4)\n",
            "Collecting diskcache>=5.6.1 (from llama-cpp-python==0.2.69)\n",
            "  Downloading diskcache-5.6.3-py3-none-any.whl.metadata (20 kB)\n",
            "Requirement already satisfied: jinja2>=2.11.3 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python==0.2.69) (3.1.4)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2>=2.11.3->llama-cpp-python==0.2.69) (3.0.2)\n",
            "Downloading diskcache-5.6.3-py3-none-any.whl (45 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.5/45.5 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hBuilding wheels for collected packages: llama-cpp-python\n",
            "  Building wheel for llama-cpp-python (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for llama-cpp-python: filename=llama_cpp_python-0.2.69-cp310-cp310-linux_x86_64.whl size=55265945 sha256=b1b96ecc6c3e127a8182dc3ec495044bee9cfc420f286ef5a3dd796b9739d026\n",
            "  Stored in directory: /root/.cache/pip/wheels/e4/18/46/58b5c613b17c8d000d79ae650980fe871b3b490e04e6faa1c1\n",
            "Successfully built llama-cpp-python\n",
            "Installing collected packages: diskcache, llama-cpp-python\n",
            "Successfully installed diskcache-5.6.3 llama-cpp-python-0.2.69\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!wget https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-fp16.gguf\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yg234d1aXx9U",
        "outputId": "e863a85f-680a-4d1c-e9d7-68db78d6feba"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2024-11-17 13:51:38--  https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-fp16.gguf\n",
            "Resolving huggingface.co (huggingface.co)... 18.245.124.37, 18.245.124.105, 18.245.124.26, ...\n",
            "Connecting to huggingface.co (huggingface.co)|18.245.124.37|:443... connected.\n",
            "HTTP request sent, awaiting response... 302 Found\n",
            "Location: https://cdn-lfs-us-1.hf.co/repos/41/c8/41c860f65b01de5dc4c68b00d84cead799d3e7c48e38ee749f4c6057776e2e9e/5d99003e395775659b0dde3f941d88ff378b2837a8dc3a2ea94222ab1420fad3?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27Phi-3-mini-4k-instruct-fp16.gguf%3B+filename%3D%22Phi-3-mini-4k-instruct-fp16.gguf%22%3B&Expires=1732110699&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczMjExMDY5OX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzQxL2M4LzQxYzg2MGY2NWIwMWRlNWRjNGM2OGIwMGQ4NGNlYWQ3OTlkM2U3YzQ4ZTM4ZWU3NDlmNGM2MDU3Nzc2ZTJlOWUvNWQ5OTAwM2UzOTU3NzU2NTliMGRkZTNmOTQxZDg4ZmYzNzhiMjgzN2E4ZGMzYTJlYTk0MjIyYWIxNDIwZmFkMz9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=gZ3Ov7vqU6sQ4B%7E%7E0XFFAoy9dDi1C%7Eqh9OwlwJk0%7EeGK3Y9-G6MKwhgopBHNCEde5bEs4Ms7YvGUcoPcjnwPqQjgi0cJSHjXSdpo2X1V05W9BNYQmBlzx38ylGsIcsfUqn5VlITIL8y6HHwHOxQVVn746L0Sq8yQPGPyEnw8zxhgGdKPcZEa%7EGksBEBABYw43wME9U4gPQUHfIXRudTt93TRsZ9%7EASAOwbh6lAWuqMbqHUUHeMDFxMvhxAd42Bl%7EuSJG22obFGKo4j69Kpd5d1pajOsiViH7hd8UHz03rLsl4FmcN8Q9esoqepfql4qm2IZ9UlDneF%7EutGW0IRmjwg__&Key-Pair-Id=K24J24Z295AEI9 [following]\n",
            "--2024-11-17 13:51:39--  https://cdn-lfs-us-1.hf.co/repos/41/c8/41c860f65b01de5dc4c68b00d84cead799d3e7c48e38ee749f4c6057776e2e9e/5d99003e395775659b0dde3f941d88ff378b2837a8dc3a2ea94222ab1420fad3?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27Phi-3-mini-4k-instruct-fp16.gguf%3B+filename%3D%22Phi-3-mini-4k-instruct-fp16.gguf%22%3B&Expires=1732110699&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczMjExMDY5OX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzQxL2M4LzQxYzg2MGY2NWIwMWRlNWRjNGM2OGIwMGQ4NGNlYWQ3OTlkM2U3YzQ4ZTM4ZWU3NDlmNGM2MDU3Nzc2ZTJlOWUvNWQ5OTAwM2UzOTU3NzU2NTliMGRkZTNmOTQxZDg4ZmYzNzhiMjgzN2E4ZGMzYTJlYTk0MjIyYWIxNDIwZmFkMz9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=gZ3Ov7vqU6sQ4B%7E%7E0XFFAoy9dDi1C%7Eqh9OwlwJk0%7EeGK3Y9-G6MKwhgopBHNCEde5bEs4Ms7YvGUcoPcjnwPqQjgi0cJSHjXSdpo2X1V05W9BNYQmBlzx38ylGsIcsfUqn5VlITIL8y6HHwHOxQVVn746L0Sq8yQPGPyEnw8zxhgGdKPcZEa%7EGksBEBABYw43wME9U4gPQUHfIXRudTt93TRsZ9%7EASAOwbh6lAWuqMbqHUUHeMDFxMvhxAd42Bl%7EuSJG22obFGKo4j69Kpd5d1pajOsiViH7hd8UHz03rLsl4FmcN8Q9esoqepfql4qm2IZ9UlDneF%7EutGW0IRmjwg__&Key-Pair-Id=K24J24Z295AEI9\n",
            "Resolving cdn-lfs-us-1.hf.co (cdn-lfs-us-1.hf.co)... 18.238.85.92, 18.238.85.13, 18.238.85.124, ...\n",
            "Connecting to cdn-lfs-us-1.hf.co (cdn-lfs-us-1.hf.co)|18.238.85.92|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 7643295904 (7.1G) [binary/octet-stream]\n",
            "Saving to: ‘Phi-3-mini-4k-instruct-fp16.gguf’\n",
            "\n",
            "Phi-3-mini-4k-instr 100%[===================>]   7.12G  40.1MB/s    in 3m 2s   \n",
            "\n",
            "2024-11-17 13:54:41 (40.1 MB/s) - ‘Phi-3-mini-4k-instruct-fp16.gguf’ saved [7643295904/7643295904]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "from langchain_openai import ChatOpenAI"
      ],
      "metadata": {
        "id": "MDiqI_69Xz-q"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load OpenAI's LLMs with LangChain\n",
        "os.environ[\"OPENAI_API_KEY\"] = \"my_api_key\"\n",
        "openai_llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)"
      ],
      "metadata": {
        "id": "Pc-iLvYKYH3C"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain import PromptTemplate\n",
        "\n",
        "# Create the ReAct template\n",
        "react_template = \"\"\"Answer the following questions as best you can. You have access to the following tools:\n",
        "\n",
        "{tools}\n",
        "\n",
        "Use the following format:\n",
        "\n",
        "Question: the input question you must answer\n",
        "Thought: you should always think about what to do\n",
        "Action: the action to take, should be one of [{tool_names}]\n",
        "Action Input: the input to the action\n",
        "Observation: the result of the action\n",
        "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
        "Thought: I now know the final answer\n",
        "Final Answer: the final answer to the original input question\n",
        "\n",
        "Begin!\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "Question: {input}\n",
        "Thought:{agent_scratchpad}\"\"\"\n",
        "\n",
        "prompt = PromptTemplate(\n",
        "    template=react_template,\n",
        "    input_variables=[\"tools\", \"tool_names\", \"input\", \"agent_scratchpad\"]\n",
        ")"
      ],
      "metadata": {
        "id": "bNnyvOA2awTt"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents import load_tools, Tool\n",
        "from langchain.tools import DuckDuckGoSearchResults\n",
        "\n",
        "# You can create the tool to pass to an agent\n",
        "search = DuckDuckGoSearchResults()\n",
        "search_tool = Tool(\n",
        "    name=\"duckduck\",\n",
        "    description=\"A web search engine. Use this to as a search engine for general queries.\",\n",
        "    func=search.run,\n",
        ")\n",
        "\n",
        "# Prepare tools\n",
        "tools = load_tools([\"llm-math\"], llm=openai_llm)\n",
        "tools.append(search_tool)"
      ],
      "metadata": {
        "id": "9qC9-e_sa1-w"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents import AgentExecutor, create_react_agent\n",
        "\n",
        "# Construct the ReAct agent\n",
        "agent = create_react_agent(openai_llm, tools, prompt)\n",
        "agent_executor = AgentExecutor(\n",
        "    agent=agent, tools=tools, verbose=True, handle_parsing_errors=True\n",
        ")"
      ],
      "metadata": {
        "id": "dKn3CKikbAdP"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# What is the Price of a MacBook Pro?\n",
        "agent_executor.invoke(\n",
        "    {\n",
        "        \"input\": \"What is the current price of a MacBook Pro in USD? How much would it cost in EUR if the exchange rate is 0.85 EUR for 1 USD?\"\n",
        "    }\n",
        ")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wG3cm5UTbDBB",
        "outputId": "6b911834-7b3e-445f-9025-7ffc361ea50e"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mI should use a web search engine to find the current price of a MacBook Pro in USD and then use a calculator to convert it to EUR based on the exchange rate.\n",
            "Action: duckduck\n",
            "Action Input: \"current price of MacBook Pro in USD\"\u001b[0m\u001b[33;1m\u001b[1;3msnippet: MacBook Pro 14\" (M4 Max/1TB): was $3,199 now $3,049 @ Best Buy Member exclusive deal: My Best Buy Plus/Total members can get Apple's most powerful MacBook yet is now on sale for $150 off., title: M4 MacBook Pro is already up to $150 off at Best Buy — how to save ..., link: https://www.tomsguide.com/computing/macbooks/m4-macbook-pro-is-already-up-to-usd150-off-at-best-buy-how-to-save-right-now, snippet: Find low everyday prices and buy online for delivery or in-store pick-up. Price Match Guarantee. ... CONNECT IT ALL—The 14-inch MacBook Pro features three Thunderbolt 4 ports, a MagSafe 3 charging port, SDXC card slot, HDMI port, and headphone jack. ... the current page will be refreshed. Get previous slide. 512GB. 1000GB. Get next slide. Color:, title: Apple MacBook Pro 14-inch Apple M4 chip Built for Apple ... - Best Buy, link: https://www.bestbuy.com/site/apple-macbook-pro-14-inch-apple-m4-chip-built-for-apple-intelligence-16gb-memory-1tb-ssd-space-black/6602742.p, snippet: This stellar MacBook deal knocks a staggering $300 off on the fan-favorite Apple MacBook Pro 14 with M3 Pro Chip. Launch date: October 2023 Price history: This is the lowest price we've ever seen ..., title: The MacBook Pro 14 with M3 Pro dips $300 to its all-time-low price ..., link: https://www.laptopmag.com/laptops/macbooks/the-macbook-pro-14-with-m3-pro-dips-dollar300-to-its-all-time-low-price-right-before-school-starts, snippet: We are big fans of the new entry-level M3 MacBook Pro, which replaces the 13-inch Pro and brings everything we love from the proper prosumer model to a lower price point. This discount makes it ..., title: Every M3 MacBook Pro model just crashed to their lowest prices ever ..., link: https://www.tomsguide.com/deals/m3-macbook-pro-deals-lowest-prices-ever\u001b[0m\u001b[32;1m\u001b[1;3mI found the current price of the MacBook Pro in USD. Now I will use a calculator to convert it to EUR.\n",
            "Action: Calculator\n",
            "Action Input: 3049 * 0.85\u001b[0m\u001b[36;1m\u001b[1;3mAnswer: 2591.65\u001b[0m\u001b[32;1m\u001b[1;3mI now know the final answer\n",
            "Final Answer: The current price of a MacBook Pro in USD is $3,049. It would cost approximately €2,591.65 in EUR based on the exchange rate of 0.85 EUR for 1 USD.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'input': 'What is the current price of a MacBook Pro in USD? How much would it cost in EUR if the exchange rate is 0.85 EUR for 1 USD?',\n",
              " 'output': 'The current price of a MacBook Pro in USD is $3,049. It would cost approximately €2,591.65 in EUR based on the exchange rate of 0.85 EUR for 1 USD.'}"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    }
  ]
}