ds_sabaproject/names_collection.py

from openai import OpenAI
import os
import requests
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from tavily import TavilyClient
from langchain_core.prompts.prompt import PromptTemplate
from langchain_core.output_parsers import StrOutputParser, JsonOutputParser
import concurrent.futures
import json
from loguru import logger
load_dotenv()

os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
llm = ChatOpenAI(model="gpt-4o")

API_KEY = os.getenv('PERPLEXITY_AI_API')

def perplexity_data(prompt, api_key=API_KEY):
    url = "https://api.perplexity.ai/chat/completions"

    payload = {
        "model": "llama-3.1-sonar-huge-128k-online",
        "messages": [
            {
                "role": "system",
                "content": "Be precise and concise."
            },
            {
                "role": "user",
                "content": prompt
            }
        ],
        "temperature": 0.2,
        "top_p": 0.9,
        "return_citations": True,
        "search_domain_filter": ["perplexity.ai"],
        "return_images": False,
        "return_related_questions": False,
        "search_recency_filter": "month",
        "top_k": 0,
        "stream": False,
        "presence_penalty": 0,
        "frequency_penalty": 1
    }
    
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    }
    
    response = requests.post(url, json=payload, headers=headers)
    
    # Check if the request was successful
    if response.status_code == 200:
        response_data = response.json()
        try:
            # Extract the message content
            message_content = response_data['choices'][0]['message']['content']
            return message_content
        except (KeyError, IndexError):
            return "Unexpected response format."
    else:
        return f"Request failed with status code: {response.status_code}"
    
def extract_names(influencer_names:str) -> dict:
    logger.info(f"Formatting Influencer Data")
    initiator_prompt = PromptTemplate(
        template="""<|begin_of_text|><|start_header_id|>system<|end_header_id|>
        You are a Influencer Data Extractor AI Agent tasked with extracting information from a search result\n
        You are provided with three informations: \n
            1. Search result of influencers names
        
        Your job is to extract all the influencers names\n
        Make sure to extract all the names there \n
        You are to return this as a JSON output. The key should be 'names' in the JSON \n
        Do not add to the search result, just return the JSON data of all the influencer names as expected.\n

    <|eot_id|><|start_header_id|>user<|end_header_id|>
    INFLUENCER_NAMEs: {influencer_names}\n
    
    <|eot_id|><|start_header_id|>assistant<|end_header_id|>""",
            input_variables=["influencer_names"],
        )

    initiator_router = initiator_prompt | llm | JsonOutputParser()
    output = initiator_router.invoke({"influencer_names":influencer_names})
    return output

def get_category_influencers(product_category: str):
    logger.info("Search for influencers names")
    names_prompt = f"Give me a list of the names of the all the top and popular {product_category} influencers in USA. People that are known across the internet. I only need their names. Give me all that's available as much as possible."
    search_names = perplexity_data(names_prompt)
    logger.info("Extracting influencers names")
    influencers_names = extract_names(search_names)
    return influencers_names
    
    
# This is the function to get influencers for all product categories using multithreading concurrency
def get_all_names(product_categories: list):
    all_influencers = {}

    # Using ThreadPoolExecutor for multithreading concurrency
    with concurrent.futures.ThreadPoolExecutor() as executor:
        # Create a dictionary where futures map to their category name
        future_to_category = {executor.submit(get_category_influencers, category): category for category in product_categories}

        for future in concurrent.futures.as_completed(future_to_category):
            category = future_to_category[future]
            try:
                influencers = future.result()  # Get result of the completed future
                all_influencers[category] = influencers
            except Exception as exc:
                logger.error(f"{category} generated an exception: {exc}")
    
    return all_influencers


# test = get_all_names(['Beauty'])
# print(test['Beauty']['names'])