File size: 6,160 Bytes
99573a1 ff1f54d 99573a1 88bd624 99573a1 62bc52b 0437ab7 8facc5a 99573a1 41a6188 471ea72 f82cef4 116a743 f82cef4 41a6188 f82cef4 99573a1 f82cef4 471ea72 e4ca5be 092a44d e4ca5be 99573a1 e4ca5be d185d0b 99573a1 |
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 |
import os
import wget
import sys
import bs4
import json
import pandas as pd
from huggingface_hub import InferenceClient
import urllib.request
import gradio as gr
def get_menu():
fp = urllib.request.urlopen("https://www.sw-ka.de/en/hochschulgastronomie/speiseplan/mensa_adenauerring/")
mybytes = fp.read()
html_content = mybytes.decode("utf8")
#html_content = "".join(open('index.html',mode='r',encoding='utf-8').readlines())
# Parse the HTML content
# Parse the HTML using BeautifulSoup
soup = bs4.BeautifulSoup(html_content, 'html.parser')
canteen_div = soup.find('div', id='canteen_day_1')
# Find all tables within the canteen_div
tables = canteen_div.find_all('table')
foods = []
prices = []
nutri = []
line_names = []
cnt = 0
canteen_div = soup.find('div', id='canteen_day_1')
# Find all tables within the canteen_div
tables = canteen_div.find_all('table')
# Iterate over each table
for table in tables:
# Extract food name
# Find all table rows with a class starting with "mt-"
menu_items = table.find_all('tr', class_=lambda class_name: class_name and class_name.startswith('mt-'))
# Iterate through each menu item
for item in menu_items:
food_name = item.find('span', class_='bg').text.strip()
# Extract price
price = item.find('span', class_='bgp price_1').text.strip()
# Extract nutritional information
nutritional_info = {}
nutritional_data = item.find('div', class_='nutrition_facts')
if nutritional_data:
for element in nutritional_data.find_all('div', class_=['energie', 'proteine', 'kohlenhydrate', 'zucker', 'fett', 'gesaettigt', 'salz']):
key = element.find('div').text.strip()
value = element.find_all('div')[1].text.strip()
nutritional_info[key] = value
# Print extracted information
#print(f"\nFood Name: {food_name}")
foods.append(food_name)
prices.append(price)
try:
nutri.append(json.dumps(nutritional_info['Energie'], indent=4))
except:
nutri.append("")
#print(f"Price: {price}")
if nutritional_info:
#print("Nutritional Information:")
for key, value in nutritional_info.items():
pass
#print(f"- {key}: {value}")
else:
pass
#print("No nutritional information available.")
cnt+=1
break
# Iterate over each row
# Find all rows (tr) with class 'mensatype_rows'
#rows = table.find_all('tr', class_='mensatype_rows')
# Find all menu items within the table
# Find all rows with class 'mensatype_rows'
canteen_div = soup.find('div', id='canteen_day_1')
# Find all tables within the canteen_div
tables = canteen_div.find_all('table')
# Iterate over each table
for table in tables:
# Iterate over each row
# Find all rows (tr) with class 'mensatype_rows'
rows = table.find_all('tr', class_='mensatype_rows')
# Iterate over each row
for row in rows:
# Extract the row name
row_name = row.find('div').get_text(strip=True)
menu_titles = row.find_all('td', class_='menu-title')
# Iterate over each food item
for menu_title in menu_titles:
line_names.append(row_name)
menu = ""
df = pd.DataFrame(zip(line_names,foods,prices,nutri),columns=['line','food','price','nutri'])
#df = df[~df['line'].str.contains("Abendessen")]
#df = df[~df['line'].str.contains("pizza")]
#df = df[~df['line'].str.contains("werk")]
df_line = df.groupby('line', sort=False)
for line, df_group in df_line:
menu+= "Line Name: " + line + "\n"
for idx,row in df_group.iterrows():
menu+=row['food'] + "\n"
menu+= "Price: " + row['price'] + "\n"
menu+= "Calories: " + row['nutri'] + "\n"
return menu
def reply_bot(message, history):
menu = get_menu()
client = InferenceClient(model="https://8cc9-141-3-25-29.ngrok-free.app")
system_prompt = "<s>[INST] <<SYS>>\nYou are multilingual chat bot that helps deciding what to eat in a german canteen. In the canteen, there are different lines with names and each line may offer several food people can choose from or only one. Based on the menu and question, you suggest the user which line they should go to. You respond really briefly and do not generate long responses. You can only suggest them from the menu and which line they can go to. Nothing else!\n<</SYS>>\n\nMenu:\n" + menu + "\n"
curr_prompt = system_prompt + message + " [/INST]"
if len(history) != 0:
for human, ai in history:
system_prompt += human + " [/INST]" + ai + "<s>[INST]\n"
curr_prompt = system_prompt + message + " [/INST]"
else:
curr_prompt = "<s>[INST] <<SYS>>\nYou are multilingual chat bot that helps deciding what to eat in a german canteen. In the canteen, there are different lines with names and each line may offer several food people can choose from or only one. Based on the menu and question, you suggest the user which line they should go to. You respond really briefly and do not generate long responses. You can only suggest them from the menu and which line they can go to. Nothing else!\n<</SYS>>\n\nMenu:\n" + menu + "\n" + message + " [/INST]"
try:
print(curr_prompt)
#answer = client.text_generation(prompt=prompt, max_new_tokens=512)
answer = ""
for token in client.text_generation(prompt=curr_prompt, max_new_tokens=512, stream=True):
answer+=token
yield answer
except:
return "Clear History or ask FR to increase Context Window. Current capacity only 4k tokens"
#return answer
gr.ChatInterface(reply_bot).launch()
|