cookbook/self_query_hotel_search.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f2605a68-4ec8-40c5-aefc-e5ae7b23b884",
   "metadata": {},
   "source": [
    "# Building hotel room search with self-querying retrieval\n",
    "\n",
    "In this example we'll walk through how to build and iterate on a hotel room search service that leverages an LLM to generate structured filter queries that can then be passed to a vector store.\n",
    "\n",
    "For an introduction to self-querying retrieval [check out the docs](https://python.langchain.com/docs/modules/data_connection/retrievers/self_query)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d621de99-d993-4f4b-b94a-d02b2c7ad4e0",
   "metadata": {},
   "source": [
    "## Imports and data prep\n",
    "\n",
    "In this example we use `ChatOpenAI` for the model and `ElasticsearchStore` for the vector store, but these can be swapped out with an LLM/ChatModel and [any VectorStore that support self-querying](https://python.langchain.com/docs/integrations/retrievers/self_query/).\n",
    "\n",
    "Download data from: https://www.kaggle.com/datasets/keshavramaiah/hotel-recommendation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8ecd1fbb-bdba-420b-bcc7-5ea8a232ab11",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install langchain lark openai elasticsearch pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "14d48ff6-2552-4b95-95a9-42dd444471d9",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b852ec6e-7bf6-405e-ae7f-f457eb6e17f1",
   "metadata": {},
   "outputs": [],
   "source": [
    "details = (\n",
    "    pd.read_csv(\"~/Downloads/archive/Hotel_details.csv\")\n",
    "    .drop_duplicates(subset=\"hotelid\")\n",
    "    .set_index(\"hotelid\")\n",
    ")\n",
    "attributes = pd.read_csv(\n",
    "    \"~/Downloads/archive/Hotel_Room_attributes.csv\", index_col=\"id\"\n",
    ")\n",
    "price = pd.read_csv(\"~/Downloads/archive/hotels_RoomPrice.csv\", index_col=\"id\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "35a32177-2ca5-4d10-b8dc-f34c25795630",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>roomtype</th>\n",
       "      <th>onsiterate</th>\n",
       "      <th>roomamenities</th>\n",
       "      <th>maxoccupancy</th>\n",
       "      <th>roomdescription</th>\n",
       "      <th>hotelname</th>\n",
       "      <th>city</th>\n",
       "      <th>country</th>\n",
       "      <th>starrating</th>\n",
       "      <th>mealsincluded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Vacation Home</td>\n",
       "      <td>636.09</td>\n",
       "      <td>Air conditioning: ;Closet: ;Fireplace: ;Free W...</td>\n",
       "      <td>4</td>\n",
       "      <td>Shower, Kitchenette, 2 bedrooms, 1 double bed ...</td>\n",
       "      <td>Pantlleni</td>\n",
       "      <td>Beddgelert</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>3</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Vacation Home</td>\n",
       "      <td>591.74</td>\n",
       "      <td>Air conditioning: ;Closet: ;Dishwasher: ;Firep...</td>\n",
       "      <td>4</td>\n",
       "      <td>Shower, Kitchenette, 2 bedrooms, 1 double bed ...</td>\n",
       "      <td>Willow Cottage</td>\n",
       "      <td>Beverley</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>3</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Guest room, Queen or Twin/Single Bed(s)</td>\n",
       "      <td>0.00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AC Hotel Manchester Salford Quays</td>\n",
       "      <td>Manchester</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>4</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Bargemaster King Accessible Room</td>\n",
       "      <td>379.08</td>\n",
       "      <td>Air conditioning: ;Free Wi-Fi in all rooms!: ;...</td>\n",
       "      <td>2</td>\n",
       "      <td>Shower</td>\n",
       "      <td>Lincoln Plaza London, Curio Collection by Hilton</td>\n",
       "      <td>London</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>4</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Twin Room</td>\n",
       "      <td>156.17</td>\n",
       "      <td>Additional toilet: ;Air conditioning: ;Blackou...</td>\n",
       "      <td>2</td>\n",
       "      <td>Room size: 15 m²/161 ft², Non-smoking, Shower,...</td>\n",
       "      <td>Ibis London Canning Town</td>\n",
       "      <td>London</td>\n",
       "      <td>United Kingdom</td>\n",
       "      <td>3</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  roomtype  onsiterate  \\\n",
       "0                            Vacation Home      636.09   \n",
       "1                            Vacation Home      591.74   \n",
       "2  Guest room, Queen or Twin/Single Bed(s)        0.00   \n",
       "3         Bargemaster King Accessible Room      379.08   \n",
       "4                                Twin Room      156.17   \n",
       "\n",
       "                                       roomamenities  maxoccupancy  \\\n",
       "0  Air conditioning: ;Closet: ;Fireplace: ;Free W...             4   \n",
       "1  Air conditioning: ;Closet: ;Dishwasher: ;Firep...             4   \n",
       "2                                                NaN             2   \n",
       "3  Air conditioning: ;Free Wi-Fi in all rooms!: ;...             2   \n",
       "4  Additional toilet: ;Air conditioning: ;Blackou...             2   \n",
       "\n",
       "                                     roomdescription  \\\n",
       "0  Shower, Kitchenette, 2 bedrooms, 1 double bed ...   \n",
       "1  Shower, Kitchenette, 2 bedrooms, 1 double bed ...   \n",
       "2                                                NaN   \n",
       "3                                             Shower   \n",
       "4  Room size: 15 m²/161 ft², Non-smoking, Shower,...   \n",
       "\n",
       "                                          hotelname        city  \\\n",
       "0                                         Pantlleni  Beddgelert   \n",
       "1                                    Willow Cottage    Beverley   \n",
       "2                 AC Hotel Manchester Salford Quays  Manchester   \n",
       "3  Lincoln Plaza London, Curio Collection by Hilton      London   \n",
       "4                          Ibis London Canning Town      London   \n",
       "\n",
       "          country  starrating  mealsincluded  \n",
       "0  United Kingdom           3          False  \n",
       "1  United Kingdom           3          False  \n",
       "2  United Kingdom           4          False  \n",
       "3  United Kingdom           4           True  \n",
       "4  United Kingdom           3           True  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "latest_price = price.drop_duplicates(subset=\"refid\", keep=\"last\")[\n",
    "    [\n",
    "        \"hotelcode\",\n",
    "        \"roomtype\",\n",
    "        \"onsiterate\",\n",
    "        \"roomamenities\",\n",
    "        \"maxoccupancy\",\n",
    "        \"mealinclusiontype\",\n",
    "    ]\n",
    "]\n",
    "latest_price[\"ratedescription\"] = attributes.loc[latest_price.index][\"ratedescription\"]\n",
    "latest_price = latest_price.join(\n",
    "    details[[\"hotelname\", \"city\", \"country\", \"starrating\"]], on=\"hotelcode\"\n",
    ")\n",
    "latest_price = latest_price.rename({\"ratedescription\": \"roomdescription\"}, axis=1)\n",
    "latest_price[\"mealsincluded\"] = ~latest_price[\"mealinclusiontype\"].isnull()\n",
    "latest_price.pop(\"hotelcode\")\n",
    "latest_price.pop(\"mealinclusiontype\")\n",
    "latest_price = latest_price.reset_index(drop=True)\n",
    "latest_price.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e4742af-c178-4cf7-a548-b97b3e37bd55",
   "metadata": {},
   "source": [
    "## Describe data attributes\n",
    "\n",
    "We'll use a self-query retriever, which requires us to describe the metadata we can filter on.\n",
    "\n",
    "Or if we're feeling lazy we can have a model write a draft of the descriptions for us :)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "5e2cb352-9111-47b8-9808-37228ba81f87",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "\n",
    "model = ChatOpenAI(model=\"gpt-4\")\n",
    "res = model.predict(\n",
    "    \"Below is a table with information about hotel rooms. \"\n",
    "    \"Return a JSON list with an entry for each column. Each entry should have \"\n",
    "    '{\"name\": \"column name\", \"description\": \"column description\", \"type\": \"column data type\"}'\n",
    "    f\"\\n\\n{latest_price.head()}\\n\\nJSON:\\n\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d831664d-68cd-4dba-aad2-9248f10c7663",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'name': 'roomtype', 'description': 'The type of the room', 'type': 'string'},\n",
       " {'name': 'onsiterate',\n",
       "  'description': 'The rate of the room',\n",
       "  'type': 'float'},\n",
       " {'name': 'roomamenities',\n",
       "  'description': 'Amenities available in the room',\n",
       "  'type': 'string'},\n",
       " {'name': 'maxoccupancy',\n",
       "  'description': 'Maximum number of people that can occupy the room',\n",
       "  'type': 'integer'},\n",
       " {'name': 'roomdescription',\n",
       "  'description': 'Description of the room',\n",
       "  'type': 'string'},\n",
       " {'name': 'hotelname', 'description': 'Name of the hotel', 'type': 'string'},\n",
       " {'name': 'city',\n",
       "  'description': 'City where the hotel is located',\n",
       "  'type': 'string'},\n",
       " {'name': 'country',\n",
       "  'description': 'Country where the hotel is located',\n",
       "  'type': 'string'},\n",
       " {'name': 'starrating',\n",
       "  'description': 'Star rating of the hotel',\n",
       "  'type': 'integer'},\n",
       " {'name': 'mealsincluded',\n",
       "  'description': 'Whether meals are included or not',\n",
       "  'type': 'boolean'}]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import json\n",
    "\n",
    "attribute_info = json.loads(res)\n",
    "attribute_info"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aadb16c5-9f70-4bcc-b4fa-1af31bc8e38a",
   "metadata": {},
   "source": [
    "For low cardinality features, let's include the valid values in the description"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "cce77f43-980a-4ab6-923a-0f9d70a093d6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "maxoccupancy     19\n",
       "country          29\n",
       "starrating        3\n",
       "mealsincluded     2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "latest_price.nunique()[latest_price.nunique() < 40]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "2db33ed8-4f91-4a2d-9613-9dd6c9fcdbcb",
   "metadata": {},
   "outputs": [],
   "source": [
    "attribute_info[-2][\n",
    "    \"description\"\n",
    "] += f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
    "attribute_info[3][\n",
    "    \"description\"\n",
    "] += f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
    "attribute_info[-3][\n",
    "    \"description\"\n",
    "] += f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "89c7461b-e6f7-4608-9929-ae952fb3348c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'name': 'roomtype', 'description': 'The type of the room', 'type': 'string'},\n",
       " {'name': 'onsiterate',\n",
       "  'description': 'The rate of the room',\n",
       "  'type': 'float'},\n",
       " {'name': 'roomamenities',\n",
       "  'description': 'Amenities available in the room',\n",
       "  'type': 'string'},\n",
       " {'name': 'maxoccupancy',\n",
       "  'description': 'Maximum number of people that can occupy the room. Valid values are [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 20, 24]',\n",
       "  'type': 'integer'},\n",
       " {'name': 'roomdescription',\n",
       "  'description': 'Description of the room',\n",
       "  'type': 'string'},\n",
       " {'name': 'hotelname', 'description': 'Name of the hotel', 'type': 'string'},\n",
       " {'name': 'city',\n",
       "  'description': 'City where the hotel is located',\n",
       "  'type': 'string'},\n",
       " {'name': 'country',\n",
       "  'description': \"Country where the hotel is located. Valid values are ['Austria', 'Belgium', 'Bulgaria', 'Croatia', 'Cyprus', 'Czech Republic', 'Denmark', 'Estonia', 'Finland', 'France', 'Germany', 'Greece', 'Hungary', 'Ireland', 'Italy', 'Latvia', 'Lithuania', 'Luxembourg', 'Malta', 'Netherlands', 'Poland', 'Portugal', 'Romania', 'Slovakia', 'Slovenia', 'Spain', 'Sweden', 'Switzerland', 'United Kingdom']\",\n",
       "  'type': 'string'},\n",
       " {'name': 'starrating',\n",
       "  'description': 'Star rating of the hotel. Valid values are [2, 3, 4]',\n",
       "  'type': 'integer'},\n",
       " {'name': 'mealsincluded',\n",
       "  'description': 'Whether meals are included or not',\n",
       "  'type': 'boolean'}]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "attribute_info"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "81c75a25-9c64-4da6-87ae-580bd47962bb",
   "metadata": {},
   "source": [
    "## Creating a query constructor chain\n",
    "\n",
    "Let's take a look at the chain that will convert natural language requests into structured queries.\n",
    "\n",
    "To start we can just load the prompt and see what it looks like"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "b960f5f4-75f7-4a93-959f-b5293986b864",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains.query_constructor.base import (\n",
    "    get_query_constructor_prompt,\n",
    "    load_query_constructor_runnable,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "bc85c90d-08fc-444f-b912-c6b2ac089bfd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Your goal is to structure the user's query to match the request schema provided below.\n",
      "\n",
      "<< Structured Request Schema >>\n",
      "When responding use a markdown code snippet with a JSON object formatted in the following schema:\n",
      "\n",
      "```json\n",
      "{\n",
      "    \"query\": string \\ text string to compare to document contents\n",
      "    \"filter\": string \\ logical condition statement for filtering documents\n",
      "}\n",
      "```\n",
      "\n",
      "The query string should contain only text that is expected to match the contents of documents. Any conditions in the filter should not be mentioned in the query as well.\n",
      "\n",
      "A logical condition statement is composed of one or more comparison and logical operation statements.\n",
      "\n",
      "A comparison statement takes the form: `comp(attr, val)`:\n",
      "- `comp` (eq | ne | gt | gte | lt | lte | contain | like | in | nin): comparator\n",
      "- `attr` (string):  name of attribute to apply the comparison to\n",
      "- `val` (string): is the comparison value\n",
      "\n",
      "A logical operation statement takes the form `op(statement1, statement2, ...)`:\n",
      "- `op` (and | or | not): logical operator\n",
      "- `statement1`, `statement2`, ... (comparison statements or logical operation statements): one or more statements to apply the operation to\n",
      "\n",
      "Make sure that you only use the comparators and logical operators listed above and no others.\n",
      "Make sure that filters only refer to attributes that exist in the data source.\n",
      "Make sure that filters only use the attributed names with its function names if there are functions applied on them.\n",
      "Make sure that filters only use format `YYYY-MM-DD` when handling timestamp data typed values.\n",
      "Make sure that filters take into account the descriptions of attributes and only make comparisons that are feasible given the type of data being stored.\n",
      "Make sure that filters are only used as needed. If there are no filters that should be applied return \"NO_FILTER\" for the filter value.\n",
      "\n",
      "<< Example 1. >>\n",
      "Data Source:\n",
      "```json\n",
      "{\n",
      "    \"content\": \"Lyrics of a song\",\n",
      "    \"attributes\": {\n",
      "        \"artist\": {\n",
      "            \"type\": \"string\",\n",
      "            \"description\": \"Name of the song artist\"\n",
      "        },\n",
      "        \"length\": {\n",
      "            \"type\": \"integer\",\n",
      "            \"description\": \"Length of the song in seconds\"\n",
      "        },\n",
      "        \"genre\": {\n",
      "            \"type\": \"string\",\n",
      "            \"description\": \"The song genre, one of \"pop\", \"rock\" or \"rap\"\"\n",
      "        }\n",
      "    }\n",
      "}\n",
      "```\n",
      "\n",
      "User Query:\n",
      "What are songs by Taylor Swift or Katy Perry about teenage romance under 3 minutes long in the dance pop genre\n",
      "\n",
      "Structured Request:\n",
      "```json\n",
      "{\n",
      "    \"query\": \"teenager love\",\n",
      "    \"filter\": \"and(or(eq(\\\"artist\\\", \\\"Taylor Swift\\\"), eq(\\\"artist\\\", \\\"Katy Perry\\\")), lt(\\\"length\\\", 180), eq(\\\"genre\\\", \\\"pop\\\"))\"\n",
      "}\n",
      "```\n",
      "\n",
      "\n",
      "<< Example 2. >>\n",
      "Data Source:\n",
      "```json\n",
      "{\n",
      "    \"content\": \"Lyrics of a song\",\n",
      "    \"attributes\": {\n",
      "        \"artist\": {\n",
      "            \"type\": \"string\",\n",
      "            \"description\": \"Name of the song artist\"\n",
      "        },\n",
      "        \"length\": {\n",
      "            \"type\": \"integer\",\n",
      "            \"description\": \"Length of the song in seconds\"\n",
      "        },\n",
      "        \"genre\": {\n",
      "            \"type\": \"string\",\n",
      "            \"description\": \"The song genre, one of \"pop\", \"rock\" or \"rap\"\"\n",
      "        }\n",
      "    }\n",
      "}\n",
      "```\n",
      "\n",
      "User Query:\n",
      "What are songs that were not published on Spotify\n",
      "\n",
      "Structured Request:\n",
      "```json\n",
      "{\n",
      "    \"query\": \"\",\n",
      "    \"filter\": \"NO_FILTER\"\n",
      "}\n",
      "```\n",
      "\n",
      "\n",
      "<< Example 3. >>\n",
      "Data Source:\n",
      "```json\n",
      "{\n",
      "    \"content\": \"Detailed description of a hotel room\",\n",
      "    \"attributes\": {\n",
      "    \"roomtype\": {\n",
      "        \"description\": \"The type of the room\",\n",
      "        \"type\": \"string\"\n",
      "    },\n",
      "    \"onsiterate\": {\n",
      "        \"description\": \"The rate of the room\",\n",
      "        \"type\": \"float\"\n",
      "    },\n",
      "    \"roomamenities\": {\n",
      "        \"description\": \"Amenities available in the room\",\n",
      "        \"type\": \"string\"\n",
      "    },\n",
      "    \"maxoccupancy\": {\n",
      "        \"description\": \"Maximum number of people that can occupy the room. Valid values are [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 20, 24]\",\n",
      "        \"type\": \"integer\"\n",
      "    },\n",
      "    \"roomdescription\": {\n",
      "        \"description\": \"Description of the room\",\n",
      "        \"type\": \"string\"\n",
      "    },\n",
      "    \"hotelname\": {\n",
      "        \"description\": \"Name of the hotel\",\n",
      "        \"type\": \"string\"\n",
      "    },\n",
      "    \"city\": {\n",
      "        \"description\": \"City where the hotel is located\",\n",
      "        \"type\": \"string\"\n",
      "    },\n",
      "    \"country\": {\n",
      "        \"description\": \"Country where the hotel is located. Valid values are ['Austria', 'Belgium', 'Bulgaria', 'Croatia', 'Cyprus', 'Czech Republic', 'Denmark', 'Estonia', 'Finland', 'France', 'Germany', 'Greece', 'Hungary', 'Ireland', 'Italy', 'Latvia', 'Lithuania', 'Luxembourg', 'Malta', 'Netherlands', 'Poland', 'Portugal', 'Romania', 'Slovakia', 'Slovenia', 'Spain', 'Sweden', 'Switzerland', 'United Kingdom']\",\n",
      "        \"type\": \"string\"\n",
      "    },\n",
      "    \"starrating\": {\n",
      "        \"description\": \"Star rating of the hotel. Valid values are [2, 3, 4]\",\n",
      "        \"type\": \"integer\"\n",
      "    },\n",
      "    \"mealsincluded\": {\n",
      "        \"description\": \"Whether meals are included or not\",\n",
      "        \"type\": \"boolean\"\n",
      "    }\n",
      "}\n",
      "}\n",
      "```\n",
      "\n",
      "User Query:\n",
      "{query}\n",
      "\n",
      "Structured Request:\n",
      "\n"
     ]
    }
   ],
   "source": [
    "doc_contents = \"Detailed description of a hotel room\"\n",
    "prompt = get_query_constructor_prompt(doc_contents, attribute_info)\n",
    "print(prompt.format(query=\"{query}\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "1e7efcae-7943-4200-be43-5c5117ba1c9d",
   "metadata": {},
   "outputs": [],
   "source": [
    "chain = load_query_constructor_runnable(\n",
    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0), doc_contents, attribute_info\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "74bf0cb2-84a5-45ef-8fc3-cbcffcaf0bbf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "StructuredQuery(query='hotel', filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Italy'), Comparison(comparator=<Comparator.LTE: 'lte'>, attribute='onsiterate', value=200)]), limit=None)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.invoke({\"query\": \"I want a hotel in Southern Europe and my budget is 200 bucks.\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "3ad704f3-679b-4dd2-b6c3-b4469ba60848",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "StructuredQuery(query='2-person room', filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Operation(operator=<Operator.OR: 'or'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='city', value='Vienna'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='city', value='London')]), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='maxoccupancy', value=2), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='mealsincluded', value=True), Comparison(comparator=<Comparator.CONTAIN: 'contain'>, attribute='roomamenities', value='AC')]), limit=None)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.invoke(\n",
    "    {\n",
    "        \"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"\n",
    "    }\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "109591d0-758a-48ab-b337-41092c6d289f",
   "metadata": {},
   "source": [
    "## Refining attribute descriptions\n",
    "\n",
    "We can see that at least two issues above. First is that when we ask for a Southern European destination we're only getting a filter for Italy, and second when we ask for AC we get a literal string lookup for AC (which isn't so bad but will miss things like 'Air conditioning').\n",
    "\n",
    "As a first step, let's try to update our description of the 'country' attribute to emphasize that equality should only be used when a specific country is mentioned."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "07b6a751-5122-4283-aa32-0f3bbc5e4354",
   "metadata": {},
   "outputs": [],
   "source": [
    "attribute_info[-3][\n",
    "    \"description\"\n",
    "] += \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
    "chain = load_query_constructor_runnable(\n",
    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
    "    doc_contents,\n",
    "    attribute_info,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "ca33b44c-29bd-4d63-bb3e-ff8eabe1e86c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "StructuredQuery(query='hotel', filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='mealsincluded', value=False), Comparison(comparator=<Comparator.LTE: 'lte'>, attribute='onsiterate', value=200), Operation(operator=<Operator.OR: 'or'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Italy'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Spain'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Greece'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Portugal'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Croatia'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Cyprus'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Malta'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Bulgaria'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Romania'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Slovenia'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Czech Republic'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Slovakia'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Hungary'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Poland'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Estonia'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Latvia'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='country', value='Lithuania')])]), limit=None)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.invoke({\"query\": \"I want a hotel in Southern Europe and my budget is 200 bucks.\"})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eb793908-ea10-4a55-96b8-ab6915262c50",
   "metadata": {},
   "source": [
    "## Refining which attributes to filter on\n",
    "\n",
    "This seems to have helped! Now let's try to narrow the attributes we're filtering on. More freeform attributes we can leave to the main query, which is better for capturing semantic meaning than searching for specific substrings."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "7ca32075-9361-48c1-b349-511a1dd4f908",
   "metadata": {},
   "outputs": [],
   "source": [
    "content_attr = [\"roomtype\", \"roomamenities\", \"roomdescription\", \"hotelname\"]\n",
    "doc_contents = \"A detailed description of a hotel room, including information about the room type and room amenities.\"\n",
    "filter_attribute_info = tuple(\n",
    "    ai for ai in attribute_info if ai[\"name\"] not in content_attr\n",
    ")\n",
    "chain = load_query_constructor_runnable(\n",
    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
    "    doc_contents,\n",
    "    filter_attribute_info,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "8eb956af-a799-4267-a098-d443c975ee0f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "StructuredQuery(query='2-person room', filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Operation(operator=<Operator.OR: 'or'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='city', value='Vienna'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='city', value='London')]), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='maxoccupancy', value=2), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='mealsincluded', value=True)]), limit=None)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.invoke(\n",
    "    {\n",
    "        \"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"\n",
    "    }\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b0263ad4-aef9-48ce-be66-eabd1999beb3",
   "metadata": {},
   "source": [
    "## Adding examples specific to our use case\n",
    "\n",
    "We've removed the strict filter for 'AC' but it's still not being included in the query string. Our chain prompt is a few-shot prompt with some default examples. Let's see if adding use case-specific examples will help:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "62b903c1-3861-4aef-9ea6-1666eeee503c",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Your goal is to structure the user's query to match the request schema provided below.\n",
      "\n",
      "<< Structured Request Schema >>\n",
      "When responding use a markdown code snippet with a JSON object formatted in the following schema:\n",
      "\n",
      "```json\n",
      "{\n",
      "    \"query\": string \\ text string to compare to document contents\n",
      "    \"filter\": string \\ logical condition statement for filtering documents\n",
      "}\n",
      "```\n",
      "\n",
      "The query string should contain only text that is expected to match the contents of documents. Any conditions in the filter should not be mentioned in the query as well.\n",
      "\n",
      "A logical condition statement is composed of one or more comparison and logical operation statements.\n",
      "\n",
      "A comparison statement takes the form: `comp(attr, val)`:\n",
      "- `comp` (eq | ne | gt | gte | lt | lte | contain | like | in | nin): comparator\n",
      "- `attr` (string):  name of attribute to apply the comparison to\n",
      "- `val` (string): is the comparison value\n",
      "\n",
      "A logical operation statement takes the form `op(statement1, statement2, ...)`:\n",
      "- `op` (and | or | not): logical operator\n",
      "- `statement1`, `statement2`, ... (comparison statements or logical operation statements): one or more statements to apply the operation to\n",
      "\n",
      "Make sure that you only use the comparators and logical operators listed above and no others.\n",
      "Make sure that filters only refer to attributes that exist in the data source.\n",
      "Make sure that filters only use the attributed names with its function names if there are functions applied on them.\n",
      "Make sure that filters only use format `YYYY-MM-DD` when handling timestamp data typed values.\n",
      "Make sure that filters take into account the descriptions of attributes and only make comparisons that are feasible given the type of data being stored.\n",
      "Make sure that filters are only used as needed. If there are no filters that should be applied return \"NO_FILTER\" for the filter value.\n",
      "\n",
      "<< Data Source >>\n",
      "```json\n",
      "{\n",
      "    \"content\": \"A detailed description of a hotel room, including information about the room type and room amenities.\",\n",
      "    \"attributes\": {\n",
      "    \"onsiterate\": {\n",
      "        \"description\": \"The rate of the room\",\n",
      "        \"type\": \"float\"\n",
      "    },\n",
      "    \"maxoccupancy\": {\n",
      "        \"description\": \"Maximum number of people that can occupy the room. Valid values are [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 20, 24]\",\n",
      "        \"type\": \"integer\"\n",
      "    },\n",
      "    \"city\": {\n",
      "        \"description\": \"City where the hotel is located\",\n",
      "        \"type\": \"string\"\n",
      "    },\n",
      "    \"country\": {\n",
      "        \"description\": \"Country where the hotel is located. Valid values are ['Austria', 'Belgium', 'Bulgaria', 'Croatia', 'Cyprus', 'Czech Republic', 'Denmark', 'Estonia', 'Finland', 'France', 'Germany', 'Greece', 'Hungary', 'Ireland', 'Italy', 'Latvia', 'Lithuania', 'Luxembourg', 'Malta', 'Netherlands', 'Poland', 'Portugal', 'Romania', 'Slovakia', 'Slovenia', 'Spain', 'Sweden', 'Switzerland', 'United Kingdom']. NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\",\n",
      "        \"type\": \"string\"\n",
      "    },\n",
      "    \"starrating\": {\n",
      "        \"description\": \"Star rating of the hotel. Valid values are [2, 3, 4]\",\n",
      "        \"type\": \"integer\"\n",
      "    },\n",
      "    \"mealsincluded\": {\n",
      "        \"description\": \"Whether meals are included or not\",\n",
      "        \"type\": \"boolean\"\n",
      "    }\n",
      "}\n",
      "}\n",
      "```\n",
      "\n",
      "\n",
      "<< Example 1. >>\n",
      "User Query:\n",
      "I want a hotel in the Balkans with a king sized bed and a hot tub. Budget is $300 a night\n",
      "\n",
      "Structured Request:\n",
      "```json\n",
      "{\n",
      "    \"query\": \"king-sized bed, hot tub\",\n",
      "    \"filter\": \"and(in(\\\"country\\\", [\\\"Bulgaria\\\", \\\"Greece\\\", \\\"Croatia\\\", \\\"Serbia\\\"]), lte(\\\"onsiterate\\\", 300))\"\n",
      "}\n",
      "```\n",
      "\n",
      "\n",
      "<< Example 2. >>\n",
      "User Query:\n",
      "A room with breakfast included for 3 people, at a Hilton\n",
      "\n",
      "Structured Request:\n",
      "```json\n",
      "{\n",
      "    \"query\": \"Hilton\",\n",
      "    \"filter\": \"and(eq(\\\"mealsincluded\\\", true), gte(\\\"maxoccupancy\\\", 3))\"\n",
      "}\n",
      "```\n",
      "\n",
      "\n",
      "<< Example 3. >>\n",
      "User Query:\n",
      "{query}\n",
      "\n",
      "Structured Request:\n",
      "\n"
     ]
    }
   ],
   "source": [
    "examples = [\n",
    "    (\n",
    "        \"I want a hotel in the Balkans with a king sized bed and a hot tub. Budget is $300 a night\",\n",
    "        {\n",
    "            \"query\": \"king-sized bed, hot tub\",\n",
    "            \"filter\": 'and(in(\"country\", [\"Bulgaria\", \"Greece\", \"Croatia\", \"Serbia\"]), lte(\"onsiterate\", 300))',\n",
    "        },\n",
    "    ),\n",
    "    (\n",
    "        \"A room with breakfast included for 3 people, at a Hilton\",\n",
    "        {\n",
    "            \"query\": \"Hilton\",\n",
    "            \"filter\": 'and(eq(\"mealsincluded\", true), gte(\"maxoccupancy\", 3))',\n",
    "        },\n",
    "    ),\n",
    "]\n",
    "prompt = get_query_constructor_prompt(\n",
    "    doc_contents, filter_attribute_info, examples=examples\n",
    ")\n",
    "print(prompt.format(query=\"{query}\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "0f27f3eb-7261-4362-8060-58fbdc8beece",
   "metadata": {},
   "outputs": [],
   "source": [
    "chain = load_query_constructor_runnable(\n",
    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
    "    doc_contents,\n",
    "    filter_attribute_info,\n",
    "    examples=examples,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "5808741d-971a-4bb1-a8f0-c403059df842",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "StructuredQuery(query='2-person room, meals included, AC', filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Operation(operator=<Operator.OR: 'or'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='city', value='Vienna'), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='city', value='London')]), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='mealsincluded', value=True)]), limit=None)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.invoke(\n",
    "    {\n",
    "        \"query\": \"Find a 2-person room in Vienna or London, preferably with meals included and AC\"\n",
    "    }\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8d66439f-4a4f-44c7-8b9a-8b2d5d6a3683",
   "metadata": {},
   "source": [
    "This seems to have helped! Let's try another complex query:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "29ed9602-8950-44c9-aaf8-32b69235eb8c",
   "metadata": {},
   "outputs": [
    {
     "ename": "OutputParserException",
     "evalue": "Parsing text\n```json\n{\n    \"query\": \"highly rated, coast, patio, fireplace\",\n    \"filter\": \"and(eq(\\\"starrating\\\", 4), contain(\\\"description\\\", \\\"coast\\\"), contain(\\\"description\\\", \\\"patio\\\"), contain(\\\"description\\\", \\\"fireplace\\\"))\"\n}\n```\n raised following error:\nReceived invalid attributes description. Allowed attributes are ['onsiterate', 'maxoccupancy', 'city', 'country', 'starrating', 'mealsincluded']",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/chains/query_constructor/base.py:53\u001b[0m, in \u001b[0;36mStructuredQueryOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     52\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m---> 53\u001b[0m     parsed[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfilter\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mast_parse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mparsed\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfilter\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     54\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m parsed\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlimit\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/lark.py:652\u001b[0m, in \u001b[0;36mLark.parse\u001b[0;34m(self, text, start, on_error)\u001b[0m\n\u001b[1;32m    635\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Parse the given text, according to the options provided.\u001b[39;00m\n\u001b[1;32m    636\u001b[0m \n\u001b[1;32m    637\u001b[0m \u001b[38;5;124;03mParameters:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    650\u001b[0m \n\u001b[1;32m    651\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m--> 652\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstart\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstart\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mon_error\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mon_error\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/parser_frontends.py:101\u001b[0m, in \u001b[0;36mParsingFrontend.parse\u001b[0;34m(self, text, start, on_error)\u001b[0m\n\u001b[1;32m    100\u001b[0m stream \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_lexer_thread(text)\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mchosen_start\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkw\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/parsers/lalr_parser.py:41\u001b[0m, in \u001b[0;36mLALR_Parser.parse\u001b[0;34m(self, lexer, start, on_error)\u001b[0m\n\u001b[1;32m     40\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 41\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlexer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstart\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     42\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m UnexpectedInput \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/parsers/lalr_parser.py:171\u001b[0m, in \u001b[0;36m_Parser.parse\u001b[0;34m(self, lexer, start, value_stack, state_stack, start_interactive)\u001b[0m\n\u001b[1;32m    170\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m InteractiveParser(\u001b[38;5;28mself\u001b[39m, parser_state, parser_state\u001b[38;5;241m.\u001b[39mlexer)\n\u001b[0;32m--> 171\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_from_state\u001b[49m\u001b[43m(\u001b[49m\u001b[43mparser_state\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/parsers/lalr_parser.py:184\u001b[0m, in \u001b[0;36m_Parser.parse_from_state\u001b[0;34m(self, state, last_token)\u001b[0m\n\u001b[1;32m    183\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m token \u001b[38;5;129;01min\u001b[39;00m state\u001b[38;5;241m.\u001b[39mlexer\u001b[38;5;241m.\u001b[39mlex(state):\n\u001b[0;32m--> 184\u001b[0m     \u001b[43mstate\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfeed_token\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtoken\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    186\u001b[0m end_token \u001b[38;5;241m=\u001b[39m Token\u001b[38;5;241m.\u001b[39mnew_borrow_pos(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m$END\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m'\u001b[39m, token) \u001b[38;5;28;01mif\u001b[39;00m token \u001b[38;5;28;01melse\u001b[39;00m Token(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m$END\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m1\u001b[39m)\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/parsers/lalr_parser.py:150\u001b[0m, in \u001b[0;36mParserState.feed_token\u001b[0;34m(self, token, is_end)\u001b[0m\n\u001b[1;32m    148\u001b[0m     s \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m--> 150\u001b[0m value \u001b[38;5;241m=\u001b[39m \u001b[43mcallbacks\u001b[49m\u001b[43m[\u001b[49m\u001b[43mrule\u001b[49m\u001b[43m]\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    152\u001b[0m _action, new_state \u001b[38;5;241m=\u001b[39m states[state_stack[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]][rule\u001b[38;5;241m.\u001b[39morigin\u001b[38;5;241m.\u001b[39mname]\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/parse_tree_builder.py:153\u001b[0m, in \u001b[0;36mChildFilterLALR_NoPlaceholders.__call__\u001b[0;34m(self, children)\u001b[0m\n\u001b[1;32m    152\u001b[0m         filtered\u001b[38;5;241m.\u001b[39mappend(children[i])\n\u001b[0;32m--> 153\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnode_builder\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfiltered\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/parse_tree_builder.py:325\u001b[0m, in \u001b[0;36mapply_visit_wrapper.<locals>.f\u001b[0;34m(children)\u001b[0m\n\u001b[1;32m    323\u001b[0m \u001b[38;5;129m@wraps\u001b[39m(func)\n\u001b[1;32m    324\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mf\u001b[39m(children):\n\u001b[0;32m--> 325\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapper\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mchildren\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/visitors.py:501\u001b[0m, in \u001b[0;36m_vargs_inline\u001b[0;34m(f, _data, children, _meta)\u001b[0m\n\u001b[1;32m    500\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_vargs_inline\u001b[39m(f, _data, children, _meta):\n\u001b[0;32m--> 501\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mchildren\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/.venv/lib/python3.9/site-packages/lark/visitors.py:479\u001b[0m, in \u001b[0;36m_VArgsWrapper.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    478\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m--> 479\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbase_func\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/chains/query_constructor/parser.py:79\u001b[0m, in \u001b[0;36mQueryTransformer.func_call\u001b[0;34m(self, func_name, args)\u001b[0m\n\u001b[1;32m     78\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallowed_attributes \u001b[38;5;129;01mand\u001b[39;00m args[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallowed_attributes:\n\u001b[0;32m---> 79\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m     80\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mReceived invalid attributes \u001b[39m\u001b[38;5;132;01m{\u001b[39;00margs[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. Allowed attributes are \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     81\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallowed_attributes\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     82\u001b[0m     )\n\u001b[1;32m     83\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m Comparison(comparator\u001b[38;5;241m=\u001b[39mfunc, attribute\u001b[38;5;241m=\u001b[39margs[\u001b[38;5;241m0\u001b[39m], value\u001b[38;5;241m=\u001b[39margs[\u001b[38;5;241m1\u001b[39m])\n",
      "\u001b[0;31mValueError\u001b[0m: Received invalid attributes description. Allowed attributes are ['onsiterate', 'maxoccupancy', 'city', 'country', 'starrating', 'mealsincluded']",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mOutputParserException\u001b[0m                     Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[21], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mchain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mquery\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mI want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/schema/runnable/base.py:1113\u001b[0m, in \u001b[0;36mRunnableSequence.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m   1111\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m   1112\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m i, step \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msteps):\n\u001b[0;32m-> 1113\u001b[0m         \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mstep\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1114\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1115\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;66;43;03m# mark each step as a child run\u001b[39;49;00m\n\u001b[1;32m   1116\u001b[0m \u001b[43m            \u001b[49m\u001b[43mpatch_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1117\u001b[0m \u001b[43m                \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseq:step:\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mi\u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1118\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1119\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1120\u001b[0m \u001b[38;5;66;03m# finish the root run\u001b[39;00m\n\u001b[1;32m   1121\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/schema/output_parser.py:173\u001b[0m, in \u001b[0;36mBaseOutputParser.invoke\u001b[0;34m(self, input, config)\u001b[0m\n\u001b[1;32m    169\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m    170\u001b[0m     \u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mstr\u001b[39m, BaseMessage], config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    171\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m T:\n\u001b[1;32m    172\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28minput\u001b[39m, BaseMessage):\n\u001b[0;32m--> 173\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_with_config\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    174\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43;01mlambda\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43minner_input\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_result\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    175\u001b[0m \u001b[43m                \u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatGeneration\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmessage\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minner_input\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m    176\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    177\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    178\u001b[0m \u001b[43m            \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    179\u001b[0m \u001b[43m            \u001b[49m\u001b[43mrun_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mparser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    180\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    181\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    182\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_with_config(\n\u001b[1;32m    183\u001b[0m             \u001b[38;5;28;01mlambda\u001b[39;00m inner_input: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparse_result([Generation(text\u001b[38;5;241m=\u001b[39minner_input)]),\n\u001b[1;32m    184\u001b[0m             \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m    185\u001b[0m             config,\n\u001b[1;32m    186\u001b[0m             run_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparser\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    187\u001b[0m         )\n",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/schema/runnable/base.py:633\u001b[0m, in \u001b[0;36mRunnable._call_with_config\u001b[0;34m(self, func, input, config, run_type, **kwargs)\u001b[0m\n\u001b[1;32m    626\u001b[0m run_manager \u001b[38;5;241m=\u001b[39m callback_manager\u001b[38;5;241m.\u001b[39mon_chain_start(\n\u001b[1;32m    627\u001b[0m     dumpd(\u001b[38;5;28mself\u001b[39m),\n\u001b[1;32m    628\u001b[0m     \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m    629\u001b[0m     run_type\u001b[38;5;241m=\u001b[39mrun_type,\n\u001b[1;32m    630\u001b[0m     name\u001b[38;5;241m=\u001b[39mconfig\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m),\n\u001b[1;32m    631\u001b[0m )\n\u001b[1;32m    632\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 633\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[43mcall_func_with_variable_args\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    634\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m    635\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    636\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    637\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/schema/runnable/config.py:173\u001b[0m, in \u001b[0;36mcall_func_with_variable_args\u001b[0;34m(func, input, run_manager, config, **kwargs)\u001b[0m\n\u001b[1;32m    171\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m accepts_run_manager(func):\n\u001b[1;32m    172\u001b[0m     kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_manager\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m run_manager\n\u001b[0;32m--> 173\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/schema/output_parser.py:174\u001b[0m, in \u001b[0;36mBaseOutputParser.invoke.<locals>.<lambda>\u001b[0;34m(inner_input)\u001b[0m\n\u001b[1;32m    169\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21minvoke\u001b[39m(\n\u001b[1;32m    170\u001b[0m     \u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Union[\u001b[38;5;28mstr\u001b[39m, BaseMessage], config: Optional[RunnableConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    171\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m T:\n\u001b[1;32m    172\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28minput\u001b[39m, BaseMessage):\n\u001b[1;32m    173\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_with_config(\n\u001b[0;32m--> 174\u001b[0m             \u001b[38;5;28;01mlambda\u001b[39;00m inner_input: \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_result\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    175\u001b[0m \u001b[43m                \u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatGeneration\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmessage\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minner_input\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m    176\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m    177\u001b[0m             \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m    178\u001b[0m             config,\n\u001b[1;32m    179\u001b[0m             run_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparser\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    180\u001b[0m         )\n\u001b[1;32m    181\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    182\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_with_config(\n\u001b[1;32m    183\u001b[0m             \u001b[38;5;28;01mlambda\u001b[39;00m inner_input: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparse_result([Generation(text\u001b[38;5;241m=\u001b[39minner_input)]),\n\u001b[1;32m    184\u001b[0m             \u001b[38;5;28minput\u001b[39m,\n\u001b[1;32m    185\u001b[0m             config,\n\u001b[1;32m    186\u001b[0m             run_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparser\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    187\u001b[0m         )\n",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/schema/output_parser.py:225\u001b[0m, in \u001b[0;36mBaseOutputParser.parse_result\u001b[0;34m(self, result, partial)\u001b[0m\n\u001b[1;32m    212\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mparse_result\u001b[39m(\u001b[38;5;28mself\u001b[39m, result: List[Generation], \u001b[38;5;241m*\u001b[39m, partial: \u001b[38;5;28mbool\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m T:\n\u001b[1;32m    213\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Parse a list of candidate model Generations into a specific format.\u001b[39;00m\n\u001b[1;32m    214\u001b[0m \n\u001b[1;32m    215\u001b[0m \u001b[38;5;124;03m    The return value is parsed from only the first Generation in the result, which\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    223\u001b[0m \u001b[38;5;124;03m        Structured output.\u001b[39;00m\n\u001b[1;32m    224\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 225\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/langchain/libs/langchain/langchain/chains/query_constructor/base.py:60\u001b[0m, in \u001b[0;36mStructuredQueryOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     56\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m StructuredQuery(\n\u001b[1;32m     57\u001b[0m         \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m{k: v \u001b[38;5;28;01mfor\u001b[39;00m k, v \u001b[38;5;129;01min\u001b[39;00m parsed\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m allowed_keys}\n\u001b[1;32m     58\u001b[0m     )\n\u001b[1;32m     59\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m---> 60\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m OutputParserException(\n\u001b[1;32m     61\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mParsing text\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00mtext\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m raised following error:\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     62\u001b[0m     )\n",
      "\u001b[0;31mOutputParserException\u001b[0m: Parsing text\n```json\n{\n    \"query\": \"highly rated, coast, patio, fireplace\",\n    \"filter\": \"and(eq(\\\"starrating\\\", 4), contain(\\\"description\\\", \\\"coast\\\"), contain(\\\"description\\\", \\\"patio\\\"), contain(\\\"description\\\", \\\"fireplace\\\"))\"\n}\n```\n raised following error:\nReceived invalid attributes description. Allowed attributes are ['onsiterate', 'maxoccupancy', 'city', 'country', 'starrating', 'mealsincluded']"
     ]
    }
   ],
   "source": [
    "chain.invoke(\n",
    "    {\n",
    "        \"query\": \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"\n",
    "    }\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c845a5e3-9a4c-4f8d-b5af-6493fd0186cb",
   "metadata": {},
   "source": [
    "## Automatically ignoring invalid queries\n",
    "\n",
    "It seems our model get's tripped up on this more complex query and tries to search over an attribute ('description') that doesn't exist. By setting `fix_invalid=True` in our query constructor chain, we can automatically remove any parts of the filter that is invalid (meaning it's using disallowed operations, comparisons or attributes)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "fff986c4-ba52-4619-afdb-b0545834c0f8",
   "metadata": {},
   "outputs": [],
   "source": [
    "chain = load_query_constructor_runnable(\n",
    "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
    "    doc_contents,\n",
    "    filter_attribute_info,\n",
    "    examples=examples,\n",
    "    fix_invalid=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "bdafa338-ca2f-4587-9457-472a6b9a9b27",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "StructuredQuery(query='highly rated, coast, patio, fireplace', filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='starrating', value=4), limit=None)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.invoke(\n",
    "    {\n",
    "        \"query\": \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"\n",
    "    }\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8251d117-8406-48b1-b331-0fe597b57051",
   "metadata": {},
   "source": [
    "## Using with a self-querying retriever\n",
    "\n",
    "Now that our query construction chain is in a decent place, let's try using it with an actual retriever. For this example we'll use the [ElasticsearchStore](https://python.langchain.com/docs/integrations/vectorstores/elasticsearch)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "06f30efe-f96a-4baa-9571-1de01596a5ac",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.embeddings import OpenAIEmbeddings\n",
    "from langchain.schema import Document\n",
    "from langchain.vectorstores import ElasticsearchStore\n",
    "\n",
    "embeddings = OpenAIEmbeddings()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e468e0f6-fc1b-42ab-bf88-7088d8e1aad0",
   "metadata": {},
   "source": [
    "## Populating vectorstore\n",
    "\n",
    "The first time you run this, uncomment the below cell to first index the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "1f73c1ff-bdb4-4c27-bfa3-c15a1b886244",
   "metadata": {},
   "outputs": [],
   "source": [
    "# docs = []\n",
    "# for _, room in latest_price.fillna(\"\").iterrows():\n",
    "#     doc = Document(\n",
    "#         page_content=json.dumps(room.to_dict(), indent=2),\n",
    "#         metadata=room.to_dict()\n",
    "#     )\n",
    "#     docs.append(doc)\n",
    "# vecstore = ElasticsearchStore.from_documents(\n",
    "#     docs,\n",
    "#     embeddings,\n",
    "#     es_url=\"http://localhost:9200\",\n",
    "#     index_name=\"hotel_rooms\",\n",
    "#     # strategy=ElasticsearchStore.ApproxRetrievalStrategy(\n",
    "#     #     hybrid=True,\n",
    "#     # )\n",
    "# )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "411af3ff-29e2-4042-9060-15f75c4fa0e9",
   "metadata": {},
   "outputs": [],
   "source": [
    "vecstore = ElasticsearchStore(\n",
    "    \"hotel_rooms\",\n",
    "    embedding=embeddings,\n",
    "    es_url=\"http://localhost:9200\",\n",
    "    # strategy=ElasticsearchStore.ApproxRetrievalStrategy(hybrid=True) # seems to not be available in community version\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "309490df-5a5f-4ff6-863b-5a85b8811b44",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.retrievers import SelfQueryRetriever\n",
    "\n",
    "retriever = SelfQueryRetriever(\n",
    "    query_constructor=chain, vectorstore=vecstore, verbose=True\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "3e6aaca9-dd22-403b-8714-23b20137f483",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\n",
      "  \"roomtype\": \"Three-Bedroom House With Sea View\",\n",
      "  \"onsiterate\": 341.75,\n",
      "  \"roomamenities\": \"Additional bathroom: ;Additional toilet: ;Air conditioning: ;Closet: ;Clothes dryer: ;Coffee/tea maker: ;Dishwasher: ;DVD/CD player: ;Fireplace: ;Free Wi-Fi in all rooms!: ;Full kitchen: ;Hair dryer: ;Heating: ;High chair: ;In-room safe box: ;Ironing facilities: ;Kitchenware: ;Linens: ;Microwave: ;Private entrance: ;Refrigerator: ;Seating area: ;Separate dining area: ;Smoke detector: ;Sofa: ;Towels: ;TV [flat screen]: ;Washing machine: ;\",\n",
      "  \"maxoccupancy\": 6,\n",
      "  \"roomdescription\": \"Room size: 125 m\\u00b2/1345 ft\\u00b2, 2 bathrooms, Shower and bathtub, Shared bathroom, Kitchenette, 3 bedrooms, 1 double bed or 2 single beds or 1 double bed\",\n",
      "  \"hotelname\": \"Downings Coastguard Cottages - Type B-E\",\n",
      "  \"city\": \"Downings\",\n",
      "  \"country\": \"Ireland\",\n",
      "  \"starrating\": 4,\n",
      "  \"mealsincluded\": false\n",
      "}\n",
      "\n",
      "--------------------\n",
      "\n",
      "{\n",
      "  \"roomtype\": \"Three-Bedroom House With Sea View\",\n",
      "  \"onsiterate\": 774.05,\n",
      "  \"roomamenities\": \"Additional bathroom: ;Additional toilet: ;Air conditioning: ;Closet: ;Clothes dryer: ;Coffee/tea maker: ;Dishwasher: ;DVD/CD player: ;Fireplace: ;Free Wi-Fi in all rooms!: ;Full kitchen: ;Hair dryer: ;Heating: ;High chair: ;In-room safe box: ;Ironing facilities: ;Kitchenware: ;Linens: ;Microwave: ;Private entrance: ;Refrigerator: ;Seating area: ;Separate dining area: ;Smoke detector: ;Sofa: ;Towels: ;TV [flat screen]: ;Washing machine: ;\",\n",
      "  \"maxoccupancy\": 6,\n",
      "  \"roomdescription\": \"Room size: 125 m\\u00b2/1345 ft\\u00b2, 2 bathrooms, Shower and bathtub, Shared bathroom, Kitchenette, 3 bedrooms, 1 double bed or 2 single beds or 1 double bed\",\n",
      "  \"hotelname\": \"Downings Coastguard Cottages - Type B-E\",\n",
      "  \"city\": \"Downings\",\n",
      "  \"country\": \"Ireland\",\n",
      "  \"starrating\": 4,\n",
      "  \"mealsincluded\": false\n",
      "}\n",
      "\n",
      "--------------------\n",
      "\n",
      "{\n",
      "  \"roomtype\": \"Four-Bedroom Apartment with Sea View\",\n",
      "  \"onsiterate\": 501.24,\n",
      "  \"roomamenities\": \"Additional toilet: ;Air conditioning: ;Carpeting: ;Cleaning products: ;Closet: ;Clothes dryer: ;Clothes rack: ;Coffee/tea maker: ;Dishwasher: ;DVD/CD player: ;Fireplace: ;Free Wi-Fi in all rooms!: ;Full kitchen: ;Hair dryer: ;Heating: ;High chair: ;In-room safe box: ;Ironing facilities: ;Kitchenware: ;Linens: ;Microwave: ;Private entrance: ;Refrigerator: ;Seating area: ;Separate dining area: ;Smoke detector: ;Sofa: ;Toiletries: ;Towels: ;TV [flat screen]: ;Wake-up service: ;Washing machine: ;\",\n",
      "  \"maxoccupancy\": 9,\n",
      "  \"roomdescription\": \"Room size: 110 m\\u00b2/1184 ft\\u00b2, Balcony/terrace, Shower and bathtub, Kitchenette, 4 bedrooms, 1 single bed or 1 queen bed or 1 double bed or 2 single beds\",\n",
      "  \"hotelname\": \"1 Elliot Terrace\",\n",
      "  \"city\": \"Plymouth\",\n",
      "  \"country\": \"United Kingdom\",\n",
      "  \"starrating\": 4,\n",
      "  \"mealsincluded\": false\n",
      "}\n",
      "\n",
      "--------------------\n",
      "\n",
      "{\n",
      "  \"roomtype\": \"Three-Bedroom Holiday Home with Terrace and Sea View\",\n",
      "  \"onsiterate\": 295.83,\n",
      "  \"roomamenities\": \"Air conditioning: ;Dishwasher: ;Free Wi-Fi in all rooms!: ;Full kitchen: ;Heating: ;In-room safe box: ;Kitchenware: ;Private entrance: ;Refrigerator: ;Satellite/cable channels: ;Seating area: ;Separate dining area: ;Sofa: ;Washing machine: ;\",\n",
      "  \"maxoccupancy\": 1,\n",
      "  \"roomdescription\": \"Room size: 157 m\\u00b2/1690 ft\\u00b2, Balcony/terrace, 3 bathrooms, Shower, Kitchenette, 3 bedrooms, 1 queen bed or 1 queen bed or 1 queen bed or 1 sofa bed\",\n",
      "  \"hotelname\": \"Seaside holiday house Artatore (Losinj) - 17102\",\n",
      "  \"city\": \"Mali Losinj\",\n",
      "  \"country\": \"Croatia\",\n",
      "  \"starrating\": 4,\n",
      "  \"mealsincluded\": false\n",
      "}\n",
      "\n",
      "--------------------\n",
      "\n"
     ]
    }
   ],
   "source": [
    "results = retriever.get_relevant_documents(\n",
    "    \"I want to stay somewhere highly rated along the coast. I want a room with a patio and a fireplace.\"\n",
    ")\n",
    "for res in results:\n",
    "    print(res.page_content)\n",
    "    print(\"\\n\" + \"-\" * 20 + \"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8adec291-5853-4d2d-ab5d-294164f07f73",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "poetry-venv",
   "language": "python",
   "name": "poetry-venv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}