LangChain_Basic_Conversation_Chatbot_with_Memory_Demo.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "e01acd08af8c49e9a157304f854a2dee": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_443ef22d1c75447ba102691484be9834",
              "IPY_MODEL_5a991f346ca94bfe9c6b81d00a9a7f5d",
              "IPY_MODEL_7b32196b6803467ab588d42ff3f09a80"
            ],
            "layout": "IPY_MODEL_0a670fca265945fe87396b415232e526"
          }
        },
        "443ef22d1c75447ba102691484be9834": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_ccbf5cf9e32f422c97cf7a7fb02c7629",
            "placeholder": "​",
            "style": "IPY_MODEL_e9560ca48182474496be72c3d8a40389",
            "value": "Downloading (…)olve/main/vocab.json: 100%"
          }
        },
        "5a991f346ca94bfe9c6b81d00a9a7f5d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_76994b445a264815b6c39dd0f2de2906",
            "max": 1042301,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_66b8a9376e154d96b711067a076a75b0",
            "value": 1042301
          }
        },
        "7b32196b6803467ab588d42ff3f09a80": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_95e21de8f619459bafb719aa1d4cc714",
            "placeholder": "​",
            "style": "IPY_MODEL_294d40e209fa47d3aa6357df45d1ceb7",
            "value": " 1.04M/1.04M [00:00&lt;00:00, 7.92MB/s]"
          }
        },
        "0a670fca265945fe87396b415232e526": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "ccbf5cf9e32f422c97cf7a7fb02c7629": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e9560ca48182474496be72c3d8a40389": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "76994b445a264815b6c39dd0f2de2906": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "66b8a9376e154d96b711067a076a75b0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "95e21de8f619459bafb719aa1d4cc714": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "294d40e209fa47d3aa6357df45d1ceb7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "ab8f3eb40e3d4f2da3793fd07347709e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_d4d8bfaaf29841af9f61a74ff7a739ce",
              "IPY_MODEL_006a8a6fc4f8474ba2063a116ddc963f",
              "IPY_MODEL_71581e44ed1b47829bea8a80a94880b4"
            ],
            "layout": "IPY_MODEL_dce89c2933004b689c4b29b8e42cdecf"
          }
        },
        "d4d8bfaaf29841af9f61a74ff7a739ce": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_6f100dc6ac184f4d8fe4dea27191c406",
            "placeholder": "​",
            "style": "IPY_MODEL_5100925d892348cc89623b3d3ea992d6",
            "value": "Downloading (…)olve/main/merges.txt: 100%"
          }
        },
        "006a8a6fc4f8474ba2063a116ddc963f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_c8154b1c216c498ab7d6978606bf611d",
            "max": 456318,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_4e6c419b295f400ea6323c610b5e2c4a",
            "value": 456318
          }
        },
        "71581e44ed1b47829bea8a80a94880b4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_e167df20187a41e69992b7f03ab2ec20",
            "placeholder": "​",
            "style": "IPY_MODEL_1664ded6d6b14a7fad1a18da32d47894",
            "value": " 456k/456k [00:00&lt;00:00, 3.37MB/s]"
          }
        },
        "dce89c2933004b689c4b29b8e42cdecf": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "6f100dc6ac184f4d8fe4dea27191c406": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "5100925d892348cc89623b3d3ea992d6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "c8154b1c216c498ab7d6978606bf611d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4e6c419b295f400ea6323c610b5e2c4a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "e167df20187a41e69992b7f03ab2ec20": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "1664ded6d6b14a7fad1a18da32d47894": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "6bbe81ae24c145738afa1db70df4edd9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_4a6e90173c674da8a145cdf27a6dd9d9",
              "IPY_MODEL_35e0054d0438413c9bbaa10c018d85d3",
              "IPY_MODEL_a0b9cd7c7f2346d486f58c28a878456b"
            ],
            "layout": "IPY_MODEL_ce377f4c56964e13a6f9b1b42c671aaf"
          }
        },
        "4a6e90173c674da8a145cdf27a6dd9d9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_371e23a9a1424398805b583a4088f83d",
            "placeholder": "​",
            "style": "IPY_MODEL_4c4ec72e580d49808266ea565a31df54",
            "value": "Downloading (…)/main/tokenizer.json: 100%"
          }
        },
        "35e0054d0438413c9bbaa10c018d85d3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_534bb68419fb4fe4bb377850e3b8a830",
            "max": 1355256,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_bf60abc24b6a4e1db4c383c952842fd1",
            "value": 1355256
          }
        },
        "a0b9cd7c7f2346d486f58c28a878456b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_8af2c451765e45a6af54eef59464dba6",
            "placeholder": "​",
            "style": "IPY_MODEL_23f215959688415b8582853ac96f1144",
            "value": " 1.36M/1.36M [00:00&lt;00:00, 9.88MB/s]"
          }
        },
        "ce377f4c56964e13a6f9b1b42c671aaf": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "371e23a9a1424398805b583a4088f83d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4c4ec72e580d49808266ea565a31df54": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "534bb68419fb4fe4bb377850e3b8a830": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "bf60abc24b6a4e1db4c383c952842fd1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "8af2c451765e45a6af54eef59464dba6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "23f215959688415b8582853ac96f1144": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "9c49455f7f8a4b68b79a5ce2347f308e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_53448a30fa6b4618a8f2371e27335cfb",
              "IPY_MODEL_832454f6fd694d7eb94059006ac652eb",
              "IPY_MODEL_3d96be2040d54e5a8abda678435f6f0d"
            ],
            "layout": "IPY_MODEL_588ca8e6340349c88329bdf36aae75d6"
          }
        },
        "53448a30fa6b4618a8f2371e27335cfb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_e56d1dd2e4c945bca7ee594d17b4cdf6",
            "placeholder": "​",
            "style": "IPY_MODEL_1af10c8140ca45ca93d9d17c8838ad47",
            "value": "Downloading (…)lve/main/config.json: 100%"
          }
        },
        "832454f6fd694d7eb94059006ac652eb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_e4f51c7606d84a479e0cb1409708fe8d",
            "max": 665,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_69bfad76a96b4908ad84f52e6fd822a9",
            "value": 665
          }
        },
        "3d96be2040d54e5a8abda678435f6f0d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_832e4d537ce54ec791e29fee8a2ce3f6",
            "placeholder": "​",
            "style": "IPY_MODEL_dbc7933ed137433bab975298a70d953c",
            "value": " 665/665 [00:00&lt;00:00, 21.2kB/s]"
          }
        },
        "588ca8e6340349c88329bdf36aae75d6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e56d1dd2e4c945bca7ee594d17b4cdf6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "1af10c8140ca45ca93d9d17c8838ad47": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "e4f51c7606d84a479e0cb1409708fe8d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "69bfad76a96b4908ad84f52e6fd822a9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "832e4d537ce54ec791e29fee8a2ce3f6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "dbc7933ed137433bab975298a70d953c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/asotjrs/Langchain/blob/main/LangChain_Basic_Conversation_Chatbot_with_Memory_Demo.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Langchain: Conversation Demo"
      ],
      "metadata": {
        "id": "XoJ-RGiUo-uJ"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8RSTxnoIozRN",
        "outputId": "5bcee817-b8e5-4158-98f9-29c3a7cfa23b"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m70.1/70.1 KB\u001b[0m \u001b[31m1.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m344.0/344.0 KB\u001b[0m \u001b[31m8.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m190.3/190.3 KB\u001b[0m \u001b[31m10.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.3/6.3 MB\u001b[0m \u001b[31m46.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.6/7.6 MB\u001b[0m \u001b[31m23.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h"
          ]
        }
      ],
      "source": [
        "!pip -q install openai langchain huggingface_hub transformers"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "\n",
        "os.environ['OPENAI_API_KEY'] = ''\n"
      ],
      "metadata": {
        "id": "9iIacDfgpB2M"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "\n",
        "## Basic Conversation with ConversationBufferMemory"
      ],
      "metadata": {
        "id": "-KB9qA8bpxgJ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.chains.conversation.memory import ConversationBufferMemory\n",
        "from langchain import OpenAI\n",
        "from langchain.chains import ConversationChain"
      ],
      "metadata": {
        "id": "-lzO5PfUpwfv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = OpenAI(model_name='text-davinci-003', \n",
        "             temperature=0, \n",
        "             max_tokens = 256)"
      ],
      "metadata": {
        "id": "sTiEn3tKp7mZ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "memory = ConversationBufferMemory()\n"
      ],
      "metadata": {
        "id": "9EBuodi9wHwG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation = ConversationChain(\n",
        "    llm=llm, \n",
        "    verbose=True, \n",
        "    memory=memory\n",
        ")"
      ],
      "metadata": {
        "id": "eF2pCbWqry4a"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"Hi there! I am Sam\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 264
        },
        "id": "Lrf1bwKy-Vx9",
        "outputId": "acb9b9f6-2ba1-494a-ff6a-3dacd17dee73"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "Human: Hi there! I am Sam\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"How are you today?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 298
        },
        "id": "tENUfRYVFb4P",
        "outputId": "7d3673da-d850-467a-cada-c88697280842"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "Human: Hi there! I am Sam\n",
            "AI:  Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\n",
            "Human: How are you today?\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" I'm doing great, thanks for asking! How about you?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"I'm good thank you. Can you help me with some customer support?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 333
        },
        "id": "dB3NvFScsRGQ",
        "outputId": "0647b079-7ef0-41a9-a3fe-f63e77a6244a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "Human: Hi there! I am Sam\n",
            "AI:  Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\n",
            "Human: How are you today?\n",
            "AI:  I'm doing great, thanks for asking! How about you?\n",
            "Human: I'm good thank you. Can you help me with some customer support?\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' Absolutely! What kind of customer support do you need?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(conversation.memory.buffer)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8NeyECDc-l65",
        "outputId": "d9f6e8b8-ebab-4e88-a8df-bc2b19fe936f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Human: Hi there! I am Sam\n",
            "AI:  Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\n",
            "Human: How are you today?\n",
            "AI:  I'm doing great, thanks for asking! How about you?\n",
            "Human: I'm good thank you. Can you help me with some customer support?\n",
            "AI:  Absolutely! What kind of customer support do you need?\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Basic Conversation with ConversationSummaryMemory"
      ],
      "metadata": {
        "id": "tdR-2GM_sfEg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.chains.conversation.memory import ConversationSummaryMemory\n",
        "from langchain import OpenAI\n",
        "from langchain.chains import ConversationChain"
      ],
      "metadata": {
        "id": "LLNWdNCpsul3"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = OpenAI(model_name='text-davinci-003', \n",
        "             temperature=0, \n",
        "             max_tokens = 256)"
      ],
      "metadata": {
        "id": "kUbCneqQsumE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "summary_memory = ConversationSummaryMemory(llm=OpenAI())\n"
      ],
      "metadata": {
        "id": "VTaQpp2TsumE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation = ConversationChain(\n",
        "    llm=llm, \n",
        "    verbose=True, \n",
        "    memory=summary_memory\n",
        ")"
      ],
      "metadata": {
        "id": "wDXSZK7lsumE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"Hi there! I am Sam\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 264
        },
        "outputId": "7740a053-a8f0-4bb3-81e9-e288cd982c49",
        "id": "6QNnwCWCsumF"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "Human: Hi there! I am Sam\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"How are you today?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 281
        },
        "outputId": "5df78e6b-ea17-474b-94c0-fed1406e2046",
        "id": "pc26jL4utIOW"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "The human introduces themselves as Sam, and the AI introduces itself as AI. The AI then asks what brings Sam here today.\n",
            "Human: How are you today?\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" I'm doing great, thanks for asking! What brings you here today, Sam?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"Can you help me with some customer support?\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 281
        },
        "outputId": "3122093f-61e1-46cb-d1ae-d06910538055",
        "id": "YXAhBz1ntIOX"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "The human introduces themselves as Sam, and the AI introduces itself as AI. The AI then asks what brings Sam here today, and Sam asks how the AI is doing. The AI responds that it is doing great.\n",
            "Human: Can you help me with some customer support?\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Absolutely! I'm here to help. What kind of customer support do you need?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(conversation.memory.buffer)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6ffce944-2526-41c2-e0c9-ea5ab5cd0434",
        "id": "94erF8qRtIOX"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "The human introduces themselves as Sam, and the AI introduces itself as AI. The AI then asks what brings Sam here today, and Sam asks how the AI is doing. The AI responds that it is doing great, and when Sam asks for customer support, the AI responds positively and asks what kind of customer support Sam needs.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "MSYb5x3uJt8p"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Basic Conversation with ConversationBufferWindowMemory"
      ],
      "metadata": {
        "id": "5ovDKMUttXg5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.chains.conversation.memory import ConversationBufferWindowMemory\n",
        "from langchain import OpenAI\n",
        "from langchain.chains import ConversationChain"
      ],
      "metadata": {
        "id": "pyY4p8S1tXg6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = OpenAI(model_name='text-davinci-003', \n",
        "             temperature=0, \n",
        "             max_tokens = 256)"
      ],
      "metadata": {
        "id": "jnf_9Ni6tXg6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# We set a low k=2, to only keep the last 2 interactions in memory\n",
        "window_memory = ConversationBufferWindowMemory(k=2)\n"
      ],
      "metadata": {
        "id": "aZhRObxXtXg6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation = ConversationChain(\n",
        "    llm=llm, \n",
        "    verbose=True, \n",
        "    memory=window_memory\n",
        ")"
      ],
      "metadata": {
        "id": "qtv7iCSStXg6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"Hi there! I am Sam\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 264
        },
        "outputId": "5ef8193b-e28c-403e-e470-1c634bd16096",
        "id": "SU9hmumXtXg6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "Human: Hi there! I am Sam\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"I am looking for some customer support\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 281
        },
        "outputId": "8c24c0fd-33ab-4f43-91f0-6432d482c9d9",
        "id": "-ANI031otXg6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "Human: Hi there! I am Sam\n",
            "AI:  Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\n",
            "Human: I am looking for some customer support\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' Sure thing! I can help you with that. What kind of customer support do you need?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"My TV is not working.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 333
        },
        "outputId": "13ea1bbb-4176-430f-c0e7-082dac5489ae",
        "id": "xa_Y1vzotXg6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "Human: Hi there! I am Sam\n",
            "AI:  Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\n",
            "Human: I am looking for some customer support\n",
            "AI:  Sure thing! I can help you with that. What kind of customer support do you need?\n",
            "Human: My TV is not working.\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" I'm sorry to hear that. Can you tell me more about the issue you're having with your TV?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"When I turn it on it makes some weird sounds and then goes black\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 333
        },
        "id": "7A4QCtdOuC7D",
        "outputId": "81176ca8-e788-48f7-c283-626818e5021b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "Human: I am looking for some customer support\n",
            "AI:  Sure thing! I can help you with that. What kind of customer support do you need?\n",
            "Human: My TV is not working.\n",
            "AI:  I'm sorry to hear that. Can you tell me more about the issue you're having with your TV?\n",
            "Human: When I turn it on it makes some weird sounds and then goes black\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" That doesn't sound good. Have you tried unplugging the TV and plugging it back in? That can sometimes help reset the system.\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(conversation.memory.buffer)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "13a3dcc8-0237-4673-9b4c-5dcff08d601d",
        "id": "afMEzKtGtXg7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[\"Human: Hi there! I am Sam\\nAI:  Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\", 'Human: I am looking for some customer support\\nAI:  Sure thing! I can help you with that. What kind of customer support do you need?', \"Human: My TV is not working.\\nAI:  I'm sorry to hear that. Can you tell me more about the issue you're having with your TV?\", \"Human: When I turn it on it makes some weird sounds and then goes black\\nAI:  That doesn't sound good. Have you tried unplugging the TV and plugging it back in? That can sometimes help reset the system.\"]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "JaTXUBOzt-iT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Basic Conversation with ConversationSummaryBufferMemory\n",
        "\n",
        "\"It keeps a buffer of recent interactions in memory, but rather than just completely flushing old interactions it compiles them into a summary and uses both\""
      ],
      "metadata": {
        "id": "IG9kPvWHuQ6s"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.chains.conversation.memory import ConversationSummaryBufferMemory\n",
        "from langchain import OpenAI\n",
        "from langchain.chains import ConversationChain"
      ],
      "metadata": {
        "id": "alYXXicIuQ6t"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = OpenAI(model_name='text-davinci-003', \n",
        "             temperature=0, \n",
        "             max_tokens = 512)"
      ],
      "metadata": {
        "id": "-NFtobEBuQ6t"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Setting k=2, will only keep the last 2 interactions in memory\n",
        "# max_token_limit=40 - token limits needs transformers installed\n",
        "memory = ConversationSummaryBufferMemory(llm=OpenAI(), max_token_limit=40) \n"
      ],
      "metadata": {
        "id": "zz-5UGw6uQ6t"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_summary = ConversationChain(\n",
        "    llm=llm, \n",
        "    memory=memory, \n",
        "    verbose=True\n",
        ")"
      ],
      "metadata": {
        "id": "Bb2u6SQ6uQ6t"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_summary.predict(input=\"Hi there! I am Sam\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 476,
          "referenced_widgets": [
            "e01acd08af8c49e9a157304f854a2dee",
            "443ef22d1c75447ba102691484be9834",
            "5a991f346ca94bfe9c6b81d00a9a7f5d",
            "7b32196b6803467ab588d42ff3f09a80",
            "0a670fca265945fe87396b415232e526",
            "ccbf5cf9e32f422c97cf7a7fb02c7629",
            "e9560ca48182474496be72c3d8a40389",
            "76994b445a264815b6c39dd0f2de2906",
            "66b8a9376e154d96b711067a076a75b0",
            "95e21de8f619459bafb719aa1d4cc714",
            "294d40e209fa47d3aa6357df45d1ceb7",
            "ab8f3eb40e3d4f2da3793fd07347709e",
            "d4d8bfaaf29841af9f61a74ff7a739ce",
            "006a8a6fc4f8474ba2063a116ddc963f",
            "71581e44ed1b47829bea8a80a94880b4",
            "dce89c2933004b689c4b29b8e42cdecf",
            "6f100dc6ac184f4d8fe4dea27191c406",
            "5100925d892348cc89623b3d3ea992d6",
            "c8154b1c216c498ab7d6978606bf611d",
            "4e6c419b295f400ea6323c610b5e2c4a",
            "e167df20187a41e69992b7f03ab2ec20",
            "1664ded6d6b14a7fad1a18da32d47894",
            "6bbe81ae24c145738afa1db70df4edd9",
            "4a6e90173c674da8a145cdf27a6dd9d9",
            "35e0054d0438413c9bbaa10c018d85d3",
            "a0b9cd7c7f2346d486f58c28a878456b",
            "ce377f4c56964e13a6f9b1b42c671aaf",
            "371e23a9a1424398805b583a4088f83d",
            "4c4ec72e580d49808266ea565a31df54",
            "534bb68419fb4fe4bb377850e3b8a830",
            "bf60abc24b6a4e1db4c383c952842fd1",
            "8af2c451765e45a6af54eef59464dba6",
            "23f215959688415b8582853ac96f1144",
            "9c49455f7f8a4b68b79a5ce2347f308e",
            "53448a30fa6b4618a8f2371e27335cfb",
            "832454f6fd694d7eb94059006ac652eb",
            "3d96be2040d54e5a8abda678435f6f0d",
            "588ca8e6340349c88329bdf36aae75d6",
            "e56d1dd2e4c945bca7ee594d17b4cdf6",
            "1af10c8140ca45ca93d9d17c8838ad47",
            "e4f51c7606d84a479e0cb1409708fe8d",
            "69bfad76a96b4908ad84f52e6fd822a9",
            "832e4d537ce54ec791e29fee8a2ce3f6",
            "dbc7933ed137433bab975298a70d953c"
          ]
        },
        "outputId": "6e22fdfd-2642-4df5-c06a-5f92855253d4",
        "id": "dVHk9ONEuQ6t"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "Human: Hi there! I am Sam\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)olve/main/vocab.json:   0%|          | 0.00/1.04M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "e01acd08af8c49e9a157304f854a2dee"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)olve/main/merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "ab8f3eb40e3d4f2da3793fd07347709e"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)/main/tokenizer.json:   0%|          | 0.00/1.36M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "6bbe81ae24c145738afa1db70df4edd9"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)lve/main/config.json:   0%|          | 0.00/665 [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "9c49455f7f8a4b68b79a5ce2347f308e"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 35
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_summary.predict(input=\"I need help with my broken TV\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 281
        },
        "outputId": "c5ac5582-f1b8-4212-eb28-96f3dd2c8881",
        "id": "MwIWdc57uQ6u"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "Human: Hi there! I am Sam\n",
            "AI:  Hi Sam! My name is AI. It's nice to meet you. What brings you here today?\n",
            "Human: I need help with my broken TV\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' Oh no, that sounds like a bummer. What seems to be the problem with your TV?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_summary.predict(input=\"It makes weird sounds when i turn it on and then goes black\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 316
        },
        "outputId": "5e4b8cd9-144f-40ee-fc28-1253aafcb454",
        "id": "sGEjep9zuQ6u"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "The human, Sam, introduces themselves to the AI. The AI responds and asks what brings Sam to them today.\n",
            "Human: I need help with my broken TV\n",
            "AI:  Oh no, that sounds like a bummer. What seems to be the problem with your TV?\n",
            "Human: It makes weird sounds when i turn it on and then goes black\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Hmm, that doesn't sound good. Do you know if it's a hardware or software issue?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_summary.predict(input=\"It seems to be Hardware\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 316
        },
        "outputId": "f36cdac7-e84c-4721-9fa7-37e53555ad3d",
        "id": "vC9pHPgTuQ6u"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe 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",
            "\n",
            "The human, Sam, introduces themselves to the AI. The AI responds and asks what brings Sam to them today, and Sam responds that they need help with their broken TV. The AI expresses sympathy and asks what the problem with the TV is.\n",
            "Human: It makes weird sounds when i turn it on and then goes black\n",
            "AI:  Hmm, that doesn't sound good. Do you know if it's a hardware or software issue?\n",
            "Human: It seems to be Hardware\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' I see. Do you know what kind of hardware issue it is?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 38
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(conversation_with_summary.memory.moving_summary_buffer)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "76405031-64f7-4c02-a3b2-58cb405752b3",
        "id": "GfmR1ypNuQ6u"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "The human, Sam, introduces themselves to the AI. The AI responds and asks what brings Sam to them today, and Sam responds that they need help with their broken TV. The AI expresses sympathy and asks what the problem with the TV is, and Sam responds that it makes weird sounds when they turn it on and then goes black. The AI responds with \"Hmm, that doesn't sound good. Do you know if it's a hardware or software issue?\"\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "L1YTPxYSurZd"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Basic Conversation with Conversation Knowledge Graph Memory"
      ],
      "metadata": {
        "id": "cVFzMuHhvRd8"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.chains.conversation.memory import ConversationKGMemory\n",
        "from langchain import OpenAI\n",
        "from langchain.chains import ConversationChain\n",
        "from langchain.prompts.prompt import PromptTemplate"
      ],
      "metadata": {
        "id": "adK3Chv6vReJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "llm = OpenAI(model_name='text-davinci-003', \n",
        "             temperature=0, \n",
        "             max_tokens = 256)"
      ],
      "metadata": {
        "id": "MlhVMDbsvReJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "template = \"\"\"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. \n",
        "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
        "\n",
        "Relevant Information:\n",
        "\n",
        "{history}\n",
        "\n",
        "Conversation:\n",
        "Human: {input}\n",
        "AI:\"\"\"\n",
        "prompt = PromptTemplate(\n",
        "    input_variables=[\"history\", \"input\"], template=template\n",
        ")"
      ],
      "metadata": {
        "id": "9H3_AGhNvReJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_kg = ConversationChain(\n",
        "    llm=llm, \n",
        "    verbose=True, \n",
        "    prompt=prompt,\n",
        "    memory=ConversationKGMemory(llm=llm)\n",
        ")"
      ],
      "metadata": {
        "id": "bMRt3eMdvReJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_kg.predict(input=\"Hi there! I am Sam\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 333
        },
        "outputId": "7466181a-2b5f-4fd3-e4bd-35f597897acd",
        "id": "X6_ptbbCvReJ"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
            "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
            "\n",
            "Relevant Information:\n",
            "\n",
            "\n",
            "\n",
            "Conversation:\n",
            "Human: Hi there! I am Sam\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Hi Sam! My name is AI. It's nice to meet you. What can I do for you today?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 44
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_kg.predict(input=\"My TV is broken and I need some customer assistance\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 333
        },
        "outputId": "da6939b5-db7f-4b6c-99dd-1fba478dc407",
        "id": "6kZFM_YqvReJ"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
            "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
            "\n",
            "Relevant Information:\n",
            "\n",
            "\n",
            "\n",
            "Conversation:\n",
            "Human: My TV is broken and I need some customer assistance\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" I'm sorry to hear that. Do you know what the issue is?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 45
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_kg.predict(input=\"It makes weird sounds when i turn it on and then goes black\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 333
        },
        "outputId": "82b56e8a-ee24-4f27-fd52-be94a3d95827",
        "id": "1mYBMM3CvReK"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
            "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
            "\n",
            "Relevant Information:\n",
            "\n",
            "\n",
            "\n",
            "Conversation:\n",
            "Human: It makes weird sounds when i turn it on and then goes black\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' That sounds like a hardware issue. Is the device plugged in and receiving power?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation_with_kg.predict(input=\"Yes it is and it is still under warranty. my warranty number is A512423\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 350
        },
        "outputId": "0e0ba013-2f51-434c-92cc-7cca7c16dab5",
        "id": "bHaY4eQovReK"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
            "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
            "\n",
            "Relevant Information:\n",
            "\n",
            "\n",
            "\n",
            "Conversation:\n",
            "Human: Yes it is and it is still under warranty. my warranty number is A512423\n",
            "AI:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" That's great to hear! I'm glad you have a warranty for your product. Is there anything else I can help you with?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# NetworkX Entity graph\n",
        "import networkx as nx\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "# nx.draw(conversation_with_kg.memory.kg, with_labels=True)\n",
        "# plt.show()\n",
        "\n",
        "print(conversation_with_kg.memory.kg)\n",
        "print(conversation_with_kg.memory.kg.get_triples())\n",
        "\n",
        " "
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "43d96143-d98b-45bf-bfd8-c5559f28e21c",
        "id": "pc8XWyGIvReK"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<langchain.graphs.networkx_graph.NetworkxEntityGraph object at 0x7f2bc65fe5e0>\n",
            "[('Sam', 'Human', 'is'), ('TV', 'true', 'is broken'), ('TV', 'weird sounds', 'makes'), ('TV', 'black', 'goes'), ('TV', 'yes', 'is under warranty'), ('device', 'A512423', 'is under warranty')]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Entity Memory"
      ],
      "metadata": {
        "id": "fjqlw-Q2HDLc"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain import OpenAI, ConversationChain\n",
        "from langchain.chains.conversation.memory import ConversationEntityMemory\n",
        "from langchain.chains.conversation.prompt import ENTITY_MEMORY_CONVERSATION_TEMPLATE\n",
        "from pydantic import BaseModel\n",
        "from typing import List, Dict, Any"
      ],
      "metadata": {
        "id": "Ud227jNMHEtO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "## The propmpt\n",
        "ENTITY_MEMORY_CONVERSATION_TEMPLATE.template"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 226
        },
        "id": "hWZneigxHwd0",
        "outputId": "f5d26bce-4cb1-4198-b2ef-6ed96b4fd912"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'You are an assistant to a human, powered by a large language model trained by OpenAI.\\n\\nYou are 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, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\\n\\nYou are constantly learning and improving, and your capabilities are constantly evolving. You are 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. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.\\n\\nOverall, you are 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 the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\\n\\nContext:\\n{entities}\\n\\nCurrent conversation:\\n{history}\\nLast line:\\nHuman: {input}\\nYou:'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 51
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "llm = OpenAI(model_name='text-davinci-003', \n",
        "             temperature=0, \n",
        "             max_tokens = 256)"
      ],
      "metadata": {
        "id": "8bwvmRCtHPmD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "conversation = ConversationChain(\n",
        "    llm=llm, \n",
        "    verbose=True,\n",
        "    prompt=ENTITY_MEMORY_CONVERSATION_TEMPLATE,\n",
        "    memory=ConversationEntityMemory(llm=llm)\n",
        ")"
      ],
      "metadata": {
        "id": "cXd58z9dHVxQ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"Hi I am Sam. My TV is broken but it is under warranty.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 437
        },
        "id": "-PhxTkMuHWUN",
        "outputId": "0c6eeb84-c7d2-434c-ce58-1fc413d8e9d2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mYou are an assistant to a human, powered by a large language model trained by OpenAI.\n",
            "\n",
            "You are 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, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
            "\n",
            "You are constantly learning and improving, and your capabilities are constantly evolving. You are 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. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
            "\n",
            "Overall, you are 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 the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\n",
            "\n",
            "Context:\n",
            "{'Sam': '', 'TV': ''}\n",
            "\n",
            "Current conversation:\n",
            "\n",
            "Last line:\n",
            "Human: Hi I am Sam. My TV is broken but it is under warranty.\n",
            "You:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" Hi Sam, I'm sorry to hear that your TV is broken. Is there anything I can do to help?\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 65
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"How can I get it fixed. The warranty number is A512453\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 489
        },
        "id": "Osa-NHDtJxUW",
        "outputId": "4473e9b6-db23-4a1f-d688-191cf0eac8ce"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mYou are an assistant to a human, powered by a large language model trained by OpenAI.\n",
            "\n",
            "You are 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, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
            "\n",
            "You are constantly learning and improving, and your capabilities are constantly evolving. You are 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. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
            "\n",
            "Overall, you are 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 the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\n",
            "\n",
            "Context:\n",
            "{'A512453': ''}\n",
            "\n",
            "Current conversation:\n",
            "Human: Hi I am Sam. My TV is broken but it is under warranty.\n",
            "AI:  Hi Sam, I'm sorry to hear that your TV is broken. Is there anything I can do to help?\n",
            "Last line:\n",
            "Human: How can I get it fixed. The warranty number is A512453\n",
            "You:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\" It looks like your TV is still under warranty. To get it fixed, you'll need to contact the manufacturer and provide them with the warranty number A512453. They should be able to provide you with instructions on how to proceed.\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 66
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.memory.entity_cache"
      ],
      "metadata": {
        "id": "yKn0evo4KqnV",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "5dd52902-e597-47be-c5c3-652e041cac9b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['A512453']"
            ]
          },
          "metadata": {},
          "execution_count": 67
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.predict(input=\"Can you send the repair person call Dave to fix it?.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 507
        },
        "id": "H0VpELTyJ8Hn",
        "outputId": "b2b57c79-1325-444d-fd4b-3e7315e576b8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
            "Prompt after formatting:\n",
            "\u001b[32;1m\u001b[1;3mYou are an assistant to a human, powered by a large language model trained by OpenAI.\n",
            "\n",
            "You are 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, you are able to generate human-like text based on the input you receive, allowing you to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
            "\n",
            "You are constantly learning and improving, and your capabilities are constantly evolving. You are 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. You have access to some personalized information provided by the human in the Context section below. Additionally, you are able to generate your own text based on the input you receive, allowing you to engage in discussions and provide explanations and descriptions on a wide range of topics.\n",
            "\n",
            "Overall, you are 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 the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\n",
            "\n",
            "Context:\n",
            "{'Dave': ''}\n",
            "\n",
            "Current conversation:\n",
            "Human: Hi I am Sam. My TV is broken but it is under warranty.\n",
            "AI:  Hi Sam, I'm sorry to hear that your TV is broken. Is there anything I can do to help?\n",
            "Human: How can I get it fixed. The warranty number is A512453\n",
            "AI:  It looks like your TV is still under warranty. To get it fixed, you'll need to contact the manufacturer and provide them with the warranty number A512453. They should be able to provide you with instructions on how to proceed.\n",
            "Last line:\n",
            "Human: Can you send the repair person call Dave to fix it?.\n",
            "You:\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "' Sure, I can send Dave to fix your TV. Can you provide me with his contact information so I can arrange for him to come to your location?'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 68
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "conversation.memory.entity_cache"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bUQxtMWVKUCe",
        "outputId": "91365981-ceff-4860-ae0d-c05bc2274951"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['Dave']"
            ]
          },
          "metadata": {},
          "execution_count": 69
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from pprint import pprint\n",
        "pprint(conversation.memory.store)\n",
        "#notice that its extracting entities and putting them into an object and perfectly describing every single entity as if we did ourselves or even better"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "duh46CpJKyRz",
        "outputId": "3487d2e3-3133-4d8c-9fc2-f10f64237f6f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "{'A512453': \"A512453 is the warranty number for Sam's TV.\",\n",
            " 'Dave': 'Dave is a repair person.',\n",
            " 'Sam': 'Sam owns a TV that is currently broken and under warranty.',\n",
            " 'TV': 'TV is under warranty.'}\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "wmCSoJb9LnYY"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}