Sip, Swig, and Search With Playwright, OpenAI, and MongoDB Atlas Search

1
!pip install playwright
2
!playwright install

1
import asyncio
2
from playwright.async_api import async_playwright

1
async def swigScraper():
2
 async with async_playwright() as playwright:
3
  
4
   browser = await playwright.chromium.launch(headless=True)
5
   page = await browser.new_page()
6
  
7
   # make sure to have the correct URL
8
   await page.goto('https://swig-orders.crispnow.com/tabs/locations/menu')

1
await page.wait_for_selector('ion-card-content', state='attached', timeout=60000)
2
3
4
# our items names and descriptions are all located in this area
5
items = await page.query_selector_all('ion-card-content')

1
   menu = []
2
3
   for item in items:
4
     result = {}
5
6
     name = await item.query_selector('p.text-h3')
7
     description = await item.query_selector('p.text-b2')
8
9
     # use inner text to extract our info
10
     if name and description:
11
       result = {}
12
       result['name'] = await name.inner_text()
13
       result['description'] = await description.inner_text()
14
       menu.append(result)
15
16
   for item in menu:
17
       print(f"Name: {item['name']}, Description: {item['description']}")
18
19
   await browser.close()
20
   return menu
21
22
scraped_menu = await swigScraper()
23
print(scraped_menu)

1
!pip install openai

1
import openai
2
import json
3
import getpass

1
# put in your OpenAI API key here
2
openai_api_key = getpass.getpass(prompt= "Put in OpenAI API Key here")

1
def swigJoined(scraped_menu):
2
 drink_list = []
3
4
 # just formatting our menu from above
5
 for drink in scraped_menu:
6
   drink_format = f"{drink['name']}: {drink['description']}]"
7
   drink_list.append(drink_format)
8
9
 # put all the drinks into a single string for OpenAI to understand it
10
 drink_string = "\n".join(drink_list)
11
12
 # we have to tell OpenAI which drinks/combinations are available
13
 prompt = (
14
     "You are the best soda mixologist Utah has ever seen! This is a list of sodas and their descriptions, or ingredients:\n"
15
     f"{drink_string}\n\n Please sort each and every drink provided into spring, summer, fall, or winter seasons based on their ingredients\n"
16
     "and give me reasonings as to why by stating which ingredients make it best for each season. For example, cinnamon is more fall, but peach\n"
17
     "is more summer."
18
 )
19
20
 return prompt

1
my_prompt = swigJoined(scraped_menu)
2
openai.api_key = openai_api_key

1
POST /v1/chat/completions
2
{
3
  "model": "gpt-4o-2024-08-06",
4
  "messages": [
5
    {
6
      "role": "system",
7
      "content": "Extract action items, due dates, and owners from meeting notes."
8
    },
9
    {
10
      "role": "user",
11
      "content": "...meeting notes go here..."
12
    }
13
  ],
14
  "response_format": {
15
    "type": "json_schema",
16
    "json_schema": {
17
      "name": "action_items",
18
      "strict": true,
19
      "schema": {
20
        "type": "object",
21
        "properties": {
22
          "action_items": {
23
            "type": "array",
24
            "items": {
25
              "type": "object",
26
              "properties": {
27
                "description": {
28
                  "type": "string",
29
                  "description": "Description of the action item."
30
                },
31
                "due_date": {
32
                  "type": ["string", "null"],
33
                  "description": "Due date for the action item, can be null if not specified."
34
                },
35
                "owner": {
36
                  "type": ["string", "null"],
37
                  "description": "Owner responsible for the action item, can be null if not specified."
38
                }
39
              },
40
              "required": ["description", "due_date", "owner"],
41
              "additionalProperties": false
42
            },
43
            "description": "List of action items from the meeting."
44
          }
45
        },
46
        "required": ["action_items"],
47
        "additionalProperties": false
48
      }
49
    }
50
  }
51
}

1
response = openai.chat.completions.create(
2
   model="gpt-4o-2024-08-06",
3
   messages=[
4
       {"role": "system", "content": "You are the best soda mixologist Utah has ever seen!"},
5
       {"role": "user", "content": my_prompt}
6
   ],
7
   response_format={
8
       "type": "json_schema",
9
       "json_schema": {
10
           "name": "drink_response",
11
           "strict": True,
12
           "schema": {
13
               "type": "object",
14
               "properties": {
15
                   "seasonal_drinks": {
16
                       "type": "array",
17
                       "items": {
18
                           "type": "object",
19
                           "properties": {
20
                               "drink": {"type": "string"},
21
                               "reason": {"type": "string"}
22
                           },
23
                           "required": ["drink", "reason"],
24
                           "additionalProperties": False
25
                       }
26
                   }
27
               },
28
               "required": ["seasonal_drinks"],
29
               "additionalProperties": False
30
           }
31
       }
32
   }
33
)

1
print(json.dumps(response.model_dump(), indent=2))

1
content = response.model_dump()['choices'][0]['message']['content']
2
print(content)

1
parsed_drinks = json.loads(content)
2
seasonal_drinks_pretty = parsed_drinks['seasonal_drinks']
3
print(json.dumps(seasonal_drinks_pretty, indent=2))

1
!pip install pymongo

1
from pymongo import MongoClient
2
3
# set up your MongoDB connection
4
connection_string = getpass.getpass(prompt= "Enter connection string WITH USER + PASS here")
5
client = MongoClient(connection_string, appname = "devrel.showcase.swig_menu")
6
7
# name your database and collection anything you want since it will be created when you enter your data
8
database = client['swig_menu']
9
collection = database['seasonal_drinks']
10
11
# insert our fall drinks
12
collection.insert_many(seasonal_drinks_pretty)

1
{
2
    "text": {
3
      "query": "fall",
4
      "path": "reason"   
5
    }
6
}

1
{
2
  "compound": {
3
    "must": [
4
      {
5
        "text": {
6
          "query": "fall",
7
          "path": "reason" 
8
        }
9
      },
10
      {
11
        "text": {
12
          "query": "apple",
13
          "path": "reason" 
14
          
15
        }
16
      }
17
    ],
18
  }
19
}