LangChain_AI_Image_Recognition.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyOchX5gTlFsmwSKIkcaRitG",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/sugarforever/LangChain-Tutorials/blob/main/LangChain_AI_Image_Recognition.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install langchain openai transformers"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "f9iqJ8-RM_2Q",
        "outputId": "e50ca756-99ca-4bb5-c169-c8fb8df181dd"
      },
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: langchain in /usr/local/lib/python3.9/dist-packages (0.0.150)\n",
            "Requirement already satisfied: openai in /usr/local/lib/python3.9/dist-packages (0.27.4)\n",
            "Requirement already satisfied: transformers in /usr/local/lib/python3.9/dist-packages (4.28.1)\n",
            "Requirement already satisfied: openapi-schema-pydantic<2.0,>=1.2 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.2.4)\n",
            "Requirement already satisfied: requests<3,>=2 in /usr/local/lib/python3.9/dist-packages (from langchain) (2.27.1)\n",
            "Requirement already satisfied: pydantic<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.10.7)\n",
            "Requirement already satisfied: SQLAlchemy<3,>1.3 in /usr/local/lib/python3.9/dist-packages (from langchain) (2.0.10)\n",
            "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /usr/local/lib/python3.9/dist-packages (from langchain) (8.2.2)\n",
            "Requirement already satisfied: numexpr<3.0.0,>=2.8.4 in /usr/local/lib/python3.9/dist-packages (from langchain) (2.8.4)\n",
            "Requirement already satisfied: dataclasses-json<0.6.0,>=0.5.7 in /usr/local/lib/python3.9/dist-packages (from langchain) (0.5.7)\n",
            "Requirement already satisfied: async-timeout<5.0.0,>=4.0.0 in /usr/local/lib/python3.9/dist-packages (from langchain) (4.0.2)\n",
            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /usr/local/lib/python3.9/dist-packages (from langchain) (3.8.4)\n",
            "Requirement already satisfied: tqdm>=4.48.0 in /usr/local/lib/python3.9/dist-packages (from langchain) (4.65.0)\n",
            "Requirement already satisfied: numpy<2,>=1 in /usr/local/lib/python3.9/dist-packages (from langchain) (1.22.4)\n",
            "Requirement already satisfied: PyYAML>=5.4.1 in /usr/local/lib/python3.9/dist-packages (from langchain) (6.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from transformers) (3.12.0)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from transformers) (23.1)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers) (2022.10.31)\n",
            "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.9/dist-packages (from transformers) (0.13.3)\n",
            "Requirement already satisfied: huggingface-hub<1.0,>=0.11.0 in /usr/local/lib/python3.9/dist-packages (from transformers) (0.14.1)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.3)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (23.1.0)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (1.9.2)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (6.0.4)\n",
            "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp<4.0.0,>=3.8.3->langchain) (2.0.12)\n",
            "Requirement already satisfied: typing-inspect>=0.4.0 in /usr/local/lib/python3.9/dist-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (0.8.0)\n",
            "Requirement already satisfied: marshmallow<4.0.0,>=3.3.0 in /usr/local/lib/python3.9/dist-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (3.19.0)\n",
            "Requirement already satisfied: marshmallow-enum<2.0.0,>=1.5.1 in /usr/local/lib/python3.9/dist-packages (from dataclasses-json<0.6.0,>=0.5.7->langchain) (1.5.1)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.9/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (2023.4.0)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (4.5.0)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (1.26.15)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (2022.12.7)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2->langchain) (3.4)\n",
            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.9/dist-packages (from SQLAlchemy<3,>1.3->langchain) (2.0.2)\n",
            "Requirement already satisfied: mypy-extensions>=0.3.0 in /usr/local/lib/python3.9/dist-packages (from typing-inspect>=0.4.0->dataclasses-json<0.6.0,>=0.5.7->langchain) (1.0.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents import load_tools\n",
        "from langchain.agents import initialize_agent\n",
        "from langchain.agents import AgentType\n",
        "from langchain.llms import OpenAI\n",
        "from langchain.chat_models import ChatOpenAI\n",
        "from langchain.chains.conversation.memory import ConversationBufferWindowMemory\n",
        "\n",
        "import os"
      ],
      "metadata": {
        "id": "vWAHCTE7oa8F"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "OPENAI_API_KEY = os.environ['OPENAI_API_KEY'] or 'Your OPENAI API Key'"
      ],
      "metadata": {
        "id": "Ojv0fTD_oqxj"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY, temperature=0, model_name='gpt-3.5-turbo')"
      ],
      "metadata": {
        "id": "VVwq0-yHoczv"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# CUDA\n",
        "\n",
        "CUDA is a parallel computing platform and programming model created by NVIDIA. With more than 20 million downloads to date, CUDA helps developers speed up their applications by harnessing the power of GPU accelerators. \n",
        "\n",
        "https://blogs.nvidia.com/blog/2012/09/10/what-is-cuda-2/\n",
        "\n",
        "# BLIP\n",
        "\n",
        "The BLIP model was proposed in BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation by Junnan Li, Dongxu Li, Caiming Xiong, Steven Hoi.\n",
        "\n",
        "BLIP is a model that is able to perform various multi-modal tasks including\n",
        "\n",
        "    Visual Question Answering\n",
        "    Image-Text retrieval (Image-text matching)\n",
        "    Image Captioning\n",
        "\n",
        "https://huggingface.co/docs/transformers/model_doc/blip\n",
        "\n",
        "# Image to Text HuggingFace Model\n",
        "\n",
        "Model card for image captioning pretrained on COCO dataset - base architecture (with ViT large backbone).\n",
        "\n",
        "https://huggingface.co/Salesforce/blip-image-captioning-large"
      ],
      "metadata": {
        "id": "QKk388MbGLKs"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "from transformers import BlipProcessor, BlipForConditionalGeneration\n",
        "\n",
        "image_to_text_model = \"Salesforce/blip-image-captioning-large\"\n",
        "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
        "\n",
        "processor = BlipProcessor.from_pretrained(image_to_text_model)\n",
        "model = BlipForConditionalGeneration.from_pretrained(image_to_text_model).to(device)"
      ],
      "metadata": {
        "id": "b4L90-HwuH5V"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from transformers.models.oneformer.modeling_oneformer import OneFormerModelOutput\n",
        "import requests\n",
        "from PIL import Image\n",
        "\n",
        "def describeImage(image_url):\n",
        "  image_object = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')\n",
        "  # image\n",
        "  inputs = processor(image_object, return_tensors=\"pt\").to(device)\n",
        "  outputs = model.generate(**inputs)\n",
        "  return processor.decode(outputs[0], skip_special_tokens=True)"
      ],
      "metadata": {
        "id": "R-HRSdY_HsbE"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "description = describeImage('https://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80')"
      ],
      "metadata": {
        "id": "DxxvzqttuOZG"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "description"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 36
        },
        "id": "qTL13DM1uU3e",
        "outputId": "35111030-38be-40f6-9e9f-0dbd55ea7744"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'porsche 911 carros parked in a parking lot with a house in the background'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.tools import BaseTool\n",
        "\n",
        "class DescribeImageTool(BaseTool):\n",
        "    name = \"Describe Image Tool\"\n",
        "    description = 'use this tool to describe an image.'\n",
        "\n",
        "    def _run(self, url: str):\n",
        "        description = describeImage(url)\n",
        "        return description\n",
        "    \n",
        "    def _arun(self, query: str):\n",
        "        raise NotImplementedError(\"Async operation not supported yet\")\n",
        "\n",
        "tools = [DescribeImageTool()]"
      ],
      "metadata": {
        "id": "qFPyDKY0ufLs"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# LangChain Agent Types\n",
        "\n",
        "https://python.langchain.com/en/latest/modules/agents/agents/agent_types.html\n",
        "\n",
        "## chat-conversational-react-description\n",
        "\n",
        "a specific type of agent (chat-conversational-react-description) which expects to be used with a memory component.\n",
        "\n",
        "https://python.langchain.com/en/latest/modules/agents/agents/examples/chat_conversation_agent.html"
      ],
      "metadata": {
        "id": "2HLzqZbzMHwH"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "agent = initialize_agent(\n",
        "    agent='chat-conversational-react-description',\n",
        "    tools=tools,\n",
        "    llm=llm,\n",
        "    verbose=True,\n",
        "    max_iterations=3,\n",
        "    early_stopping_method='generate',\n",
        "    memory=ConversationBufferWindowMemory(\n",
        "        memory_key='chat_history',\n",
        "        k=5,\n",
        "        return_messages=True\n",
        "    )\n",
        ")"
      ],
      "metadata": {
        "id": "fkUISONKCMGQ"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "image_url = 'https://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80'\n",
        "agent(f\"Describe the following image:\\n{image_url}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wJPk8RebvGC3",
        "outputId": "6e3f3bff-fbcd-4289-f30b-c2dc9c4915ef"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m{\n",
            "    \"action\": \"Describe Image Tool\",\n",
            "    \"action_input\": \"https://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80\"\n",
            "}\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mporsche 911 carros parked in a parking lot with a house in the background\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m{\n",
            "    \"action\": \"Final Answer\",\n",
            "    \"action_input\": \"The image is of a parking lot with several Porsche 911 cars parked in it. There is a house visible in the background.\"\n",
            "}\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'input': 'Describe the following image:\\nhttps://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80',\n",
              " 'chat_history': [],\n",
              " 'output': 'The image is of a parking lot with several Porsche 911 cars parked in it. There is a house visible in the background.'}"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent(f\"What is the brand of car in the following image:\\n{image_url}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SBPVaqbIQpoG",
        "outputId": "12bb59a8-0c68-4def-9628-c0224ba54dad"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m{\n",
            "    \"action\": \"Describe Image Tool\",\n",
            "    \"action_input\": \"https://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80\"\n",
            "}\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mporsche 911 carros parked in a parking lot with a house in the background\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m{\n",
            "    \"action\": \"Final Answer\",\n",
            "    \"action_input\": \"The brand of car in the image is Porsche 911.\"\n",
            "}\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'input': 'What is the brand of car in the following image:\\nhttps://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80',\n",
              " 'chat_history': [HumanMessage(content='Describe the following image:\\nhttps://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80', additional_kwargs={}),\n",
              "  AIMessage(content='The image is of a parking lot with several Porsche 911 cars parked in it. There is a house visible in the background.', additional_kwargs={})],\n",
              " 'output': 'The brand of car in the image is Porsche 911.'}"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "image_url = 'https://images.unsplash.com/photo-1682228287072-5e23cbffd487?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=987&q=80'\n",
        "agent(f\"Please describe the following image:\\n{image_url}\")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JlJvM2UrhkWT",
        "outputId": "25b4bc7f-4209-4df7-bbfe-75b27971a404"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3m```json\n",
            "{\n",
            "    \"action\": \"Describe Image Tool\",\n",
            "    \"action_input\": \"https://images.unsplash.com/photo-1682228287072-5e23cbffd487?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=987&q=80\"\n",
            "}\n",
            "```\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3ma close up of a bunch of red lanterns hanging from a ceiling\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m```json\n",
            "{\n",
            "    \"action\": \"Final Answer\",\n",
            "    \"action_input\": \"The image is a close up of a bunch of red lanterns hanging from a ceiling.\"\n",
            "}\n",
            "```\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'input': 'Please describe the following image:\\nhttps://images.unsplash.com/photo-1682228287072-5e23cbffd487?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=987&q=80',\n",
              " 'chat_history': [HumanMessage(content='Describe the following image:\\nhttps://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80', additional_kwargs={}),\n",
              "  AIMessage(content='The image is of a parking lot with several Porsche 911 cars parked in it. There is a house visible in the background.', additional_kwargs={}),\n",
              "  HumanMessage(content='What is the brand of car in the following image:\\nhttps://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80', additional_kwargs={}),\n",
              "  AIMessage(content='The brand of car in the image is Porsche 911.', additional_kwargs={}),\n",
              "  HumanMessage(content='What is the brand of car in the following image:\\nhttps://images.unsplash.com/photo-1679707883439-117608837612?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80', additional_kwargs={}),\n",
              "  AIMessage(content='The brand of car in the image is BMW.', additional_kwargs={})],\n",
              " 'output': 'The image is a close up of a bunch of red lanterns hanging from a ceiling.'}"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.memory.buffer"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6g0ri68KEC0q",
        "outputId": "299ca2f3-0845-4cdf-fcc2-fa537bdf4169"
      },
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[HumanMessage(content='Describe the following image:\\nhttps://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80', additional_kwargs={}),\n",
              " AIMessage(content='The image is of a parking lot with several Porsche 911 cars parked in it. There is a house visible in the background.', additional_kwargs={}),\n",
              " HumanMessage(content='What is the brand of car in the following image:\\nhttps://images.unsplash.com/photo-1673207520321-c27d09eb0955?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80', additional_kwargs={}),\n",
              " AIMessage(content='The brand of car in the image is Porsche 911.', additional_kwargs={}),\n",
              " HumanMessage(content='What is the brand of car in the following image:\\nhttps://images.unsplash.com/photo-1679707883439-117608837612?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1035&q=80', additional_kwargs={}),\n",
              " AIMessage(content='The brand of car in the image is BMW.', additional_kwargs={}),\n",
              " HumanMessage(content='Please describe the following image:\\nhttps://images.unsplash.com/photo-1682228287072-5e23cbffd487?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=987&q=80', additional_kwargs={}),\n",
              " AIMessage(content='The image is a close up of a bunch of red lanterns hanging from a ceiling.', additional_kwargs={})]"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    }
  ]
}