File size: 4,680 Bytes
6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 c281ef0 6680c14 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import sys\n",
"import os\n",
"sys.path.append(os.path.dirname(os.path.dirname(os.getcwd())))\n",
"\n",
"%load_ext autoreload\n",
"%autoreload 2\n",
"\n",
"from climateqa.engine.talk_to_data.main import ask_vanna\n",
"\n",
"import sqlite3\n",
"import os\n",
"import pandas as pd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Imports"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from climateqa.engine.talk_to_data.myVanna import MyVanna\n",
"from climateqa.engine.talk_to_data.utils import loc2coords, detect_location_with_openai, detectTable, nearestNeighbourSQL, detect_relevant_tables, replace_coordonates\n",
"\n",
"from climateqa.engine.llm import get_llm"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Vanna Ask\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()\n",
"\n",
"llm = get_llm(provider=\"openai\")\n",
"\n",
"OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')\n",
"PC_API_KEY = os.getenv('VANNA_PINECONE_API_KEY')\n",
"INDEX_NAME = os.getenv('VANNA_INDEX_NAME')\n",
"VANNA_MODEL = os.getenv('VANNA_MODEL')\n",
"\n",
"ROOT_PATH = os.path.dirname(os.path.dirname(os.getcwd()))\n",
"\n",
"#Vanna object\n",
"vn = MyVanna(config = {\"temperature\": 0, \"api_key\": OPENAI_API_KEY, 'model': VANNA_MODEL, 'pc_api_key': PC_API_KEY, 'index_name': INDEX_NAME, \"top_k\" : 4})\n",
"db_vanna_path = ROOT_PATH + \"/data/drias/drias.db\"\n",
"vn.connect_to_sqlite(db_vanna_path)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# User query"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# query = \"Quelle sera la température à Marseille sur les prochaines années ?\"\n",
"query = \"Comment vont évoluer les températures à marseille ?\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Detect location"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"location = detect_location_with_openai(OPENAI_API_KEY, query)\n",
"print(location)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Convert location to longitude, latitude coordonate"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"coords = loc2coords(location)\n",
"user_input = query.lower().replace(location.lower(), f\"lat, long : {coords}\")\n",
"print(user_input)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Find closest coordonates and replace lat,lon\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"relevant_tables = detect_relevant_tables(user_input, llm) \n",
"coords_tables = [nearestNeighbourSQL(db_vanna_path, coords, relevant_tables[i]) for i in range(len(relevant_tables))]\n",
"user_input_with_coords = replace_coordonates(coords, user_input, coords_tables)\n",
"print(user_input_with_coords)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Ask Vanna with correct coordonates"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sql_query, result_dataframe, figure = vn.ask(user_input_with_coords, print_results=False, allow_llm_to_see_data=True, auto_train=False)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"result_dataframe"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"figure"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "climateqa",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|