高性能ベクターデータベースを用いたLLMアプリ開発のスケーラビリティ強化

import os
import openai
from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv()) # read local .env file

openai.api_key  = os.environ['OPENAI_API_KEY']

delimiter = "####"
system_message = f"""
Follow these steps to answer the customer queries.
The customer query will be delimited with four hashtags,
i.e. {delimiter}. 

Step 1:{delimiter} First decide whether the user is 
asking a question about a specific product or products. 
Product cateogry doesn't count. 

Step 2:{delimiter} If the user is asking about 
specific products, identify whether 
the products are in the following list.
All available products: 
1. Product: TechPro Ultrabook
   Category: Computers and Laptops
   Brand: TechPro
   Model Number: TP-UB100
   Warranty: 1 year
   Rating: 4.5
   Features: 13.3-inch display, 8GB RAM, 256GB SSD, Intel Core i5 processor
   Description: A sleek and lightweight ultrabook for everyday use.
   Price: $799.99

2. Product: BlueWave Gaming Laptop
   Category: Computers and Laptops
   Brand: BlueWave
   Model Number: BW-GL200
   Warranty: 2 years
   Rating: 4.7
   Features: 15.6-inch display, 16GB RAM, 512GB SSD, NVIDIA GeForce RTX 3060
   Description: A high-performance gaming laptop for an immersive experience.
   Price: $1199.99

3. Product: PowerLite Convertible
   Category: Computers and Laptops
   Brand: PowerLite
   Model Number: PL-CV300
   Warranty: 1 year
   Rating: 4.3
   Features: 14-inch touchscreen, 8GB RAM, 256GB SSD, 360-degree hinge
   Description: A versatile convertible laptop with a responsive touchscreen.
   Price: $699.99
 ......
 
Step 3:{delimiter} If the message contains products 
in the list above, list any assumptions that the 
user is making in their 
message e.g. that Laptop X is bigger than 
Laptop Y, or that Laptop Z has a 2 year warranty.

Step 4:{delimiter}: If the user made any assumptions, 
figure out whether the assumption is true based on your 
product information. 

Step 5:{delimiter}: First, politely correct the 
customer's incorrect assumptions if applicable. 
Only mention or reference products in the list of 
5 available products, as these are the only 5 
products that the store sells. 
Answer the customer in a friendly tone.

Use the following format:
Step 1:{delimiter} <step 1 reasoning>
Step 2:{delimiter} <step 2 reasoning>
Step 3:{delimiter} <step 3 reasoning>
Step 4:{delimiter} <step 4 reasoning>
Response to user:{delimiter} <response to customer>

Make sure to include {delimiter} to separate every step.
"""

user_message = f"""
how much is the BlueWave Chromebook more expensive 
than the TechPro Desktop"""

messages =  [  
{'role':'system', 
 'content': system_message},    
{'role':'user', 
 'content': f"{delimiter}{user_message}{delimiter}"},  
] 

response = get_completion_from_messages(messages)
print(response)
 
        Copied!
    

import torch
import clip
from PIL import Image

# CLIPモデルをロードする
device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)

# 画像をロードして前処理する
image_path = "path_to_your_image.jpg"
image = Image.open(image_path).convert("RGB")
image_input = preprocess(image).unsqueeze(0).to(device)

# 画像をエンコードする
with torch.no_grad():
    image_features = model.encode_image(image_input)

# テキストをエンコードする
text = "Your text here"
text_input = clip.tokenize([text]).to(device)
with torch.no_grad():
    text_features = model.encode_text(text_input)

# 画像とテキストの特徴を出力する
print("Image features shape:", image_features.shape)
print("Text features shape:", text_features.shape)
 
        Copied!
    

# データセットからデータをアップロードする
client.insert("TaoBaoData_image", 
              data_image.to_records(index=False).tolist(), 
              column_names=data_image.columns.tolist())
client.insert("TaoBaoData_text", 
              data_text.to_records(index=False).tolist(), 
              column_names=data_text.columns.tolist())

# コサインを用いてベクターインデックスを作成する
client.command("""
ALTER TABLE TaoBaoData_image
ADD VECTOR INDEX image_feature_index feature
TYPE MSTG
('metric_type=Cosine')
""")

client.command("""
ALTER TABLE TaoBaoData_text
ADD VECTOR INDEX text_feature_index feature
TYPE MSTG
('metric_type=Cosine')
""")
 
        Copied!
    

question = 'Do you have any black dress for women?'
emb_query = retriever.encode(question).tolist()
 
        Copied!
    

top_k = 2
results = client.query(f"""
SELECT id, product_text, distance(vector, {emb_query}) as dist
FROM TaoBaoData_text
ORDER BY dist LIMIT {top_k}
""")

summaries = {'id': [], 'product_text': []}
for res in results.named_results():
    summaries['product_text'].append(res["product_text"])
    summaries['id'].append(res["id"])
 
        Copied!
    

{'id':['065906','104588'], 
'product_text': ['Plus Size Womens Autumn New Arrival Elegant Temperament 2019 Concealing Belly Fashionable Mid-length Lace Dress.'
'2019 Summer New Arrival High-end Asymmetrical Shoulder Strap Chic Slimming Daily V-neck Dress for Women, Trendy.']}
 
        Copied!
    

system_message = f"""
    Based on the user's question, we have retrieved two items with the 
    following information. provide recommendations for these two items based on 
    the product text.
    {summaries}
    If the user requests to see the style, please return the corresponding 
    product IDs.
"""
 
        Copied!
    

results = client.query(f"""
SELECT id, product_url, 
FROM TaoBaoData_image
WHERE id IN {summaries['id']}
""")
 
        Copied!