From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
63 lines
2.3 KiB
63 lines
2.3 KiB
# imports |
|
|
|
import os |
|
import re |
|
import math |
|
import json |
|
from typing import List |
|
from openai import OpenAI |
|
from sentence_transformers import SentenceTransformer |
|
from datasets import load_dataset |
|
import chromadb |
|
from items import Item |
|
from testing import Tester |
|
|
|
class FrontierAgent: |
|
|
|
MODEL = "gpt-4o-mini" |
|
|
|
def __init__(self, collection): |
|
self.openai = OpenAI() |
|
self.collection = collection |
|
self.model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2') |
|
|
|
def make_context(self, similars: List[str], prices: List[float]): |
|
message = "To provide some context, here are some other items that might be similar to the item you need to estimate.\n\n" |
|
for similar, price in zip(similars, prices): |
|
message += f"Potentially related product:\n{similar}\nPrice is ${price:.2f}\n\n" |
|
return message |
|
|
|
def messages_for(self, description: str, similars: List[str], prices: List[float]): |
|
system_message = "You estimate prices of items. Reply only with the price, no explanation" |
|
user_prompt = self.make_context(similars, prices) |
|
user_prompt += "And now the question for you:\n\n" |
|
user_prompt += "How much does this cost?\n\n" + description |
|
return [ |
|
{"role": "system", "content": system_message}, |
|
{"role": "user", "content": user_prompt}, |
|
{"role": "assistant", "content": "Price is $"} |
|
] |
|
|
|
def find_similars(self, description: str): |
|
vector = self.model.encode([description]) |
|
results = self.collection.query(query_embeddings=vector.astype(float).tolist(), n_results=5) |
|
documents = results['documents'][0][:] |
|
prices = [m['price'] for m in results['metadatas'][0][:]] |
|
return documents, prices |
|
|
|
def get_price(self, s) -> float: |
|
s = s.replace('$','').replace(',','') |
|
match = re.search(r"[-+]?\d*\.\d+|\d+", s) |
|
return float(match.group()) if match else 0.0 |
|
|
|
def price(self, description: str) -> float: |
|
documents, prices = self.find_similars(description) |
|
response = self.openai.chat.completions.create( |
|
model=self.MODEL, |
|
messages=self.messages_for(description, documents, prices), |
|
seed=42, |
|
max_tokens=5 |
|
) |
|
reply = response.choices[0].message.content |
|
return self.get_price(reply) |
|
|