sonar-pro model not working with my prompt , it was previously working with the prompt but today its stopped working

[AI-ML-PROBO-TEAM]

sonar-pro model not working with my prompt , it was previously working with the prompt but today its stopped working all other models are working properly I am using sonar reasoning and pro its working properly
`import requests
import re
import json
import logging
import time

Configure logging

logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(levelname)s - %(message)s",
handlers=[logging.StreamHandler()] # Logs to console
)

logger = logging.getLogger(name)

class PerplexityAPI:
def init(self, api_key):
self.api_key = api_key

def _make_request(self, user_message, model,structure,max_tokens,temperature):
    url = "https://api.perplexity.ai/chat/completions"
    headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
    data = {
        "model": model,
        "messages": [
            {"role": "system", "content": structure},
            {"role": "user", "content": user_message} 
        ],
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": 0.9,
    "stream": False
    }
    response = requests.post(url, headers=headers, json=data)
    return response.json()

def get_response(self, user_message,model):
    perplexity_start_time = time.time()  # Start time logging
    logger.info("perplexit Execution started...")
    structure = """

You are an advanced AI assistant specialized in providing comprehensive, well-researched, and highly detailed outputs. For the given user input, respond with the following structure and level of detail:

{"short_description": "Provide a concise summary of the topic in not more then 40 words, capturing the core essence of the information.", "entities": ["Entity1", "Entity2", "Entity3"]}

Main Response Sections

1. Introduction

   Write a thorough introduction with more than 150 words, elaborating on the topic, its definitions, scope, and relevance. This section can include both paragraphs and bullet points.

2. Background

   Provide a detailed background of over 150 words, explaining necessary prerequisites, foundational concepts, and related ideas. Use paragraphs or subheadings as needed.

3. History

   Present the history in more than 150 words, detailing the evolution of the topic with key milestones, dates, and influential figures. Use a combination of paragraphs and numbered lists.

4. Context

   Offer a context-rich explanation exceeding 150 words about the topic's current relevance in various domains or industries. Include specific examples or case studies.

5. Data in Table Format

   Include at least one detailed table with statistics, comparisons, or summaries, clearly labeled and formatted. Complement this table with textual descriptions that interpret the data.

6. Key Insights (Data Interpretation)

   Interpret the data in more than 150 words, discussing trends, implications, and relationships. Highlight patterns, anomalies, and insights with optional subheadings or bullet points.

7. Conclusion

   Write a detailed conclusion with more than 150 words, emphasizing key takeaways or lessons. Use phrases like 'Finally, to wrap up' or 'In essence, the main takeaway is...' to ensure a strong closing. The conclusion may include subheadings or a mix of paragraph and point styles.

Guidelines for the Response

• Ensure the first part of the response is a JSON dictionary containing short_description and entities, with no newline characters.

• The short_description should be concise, accurate, and informative.

• All The entities should be extracted including organisation name , country name, state name , product name ,event place name , person name and structured as a JSON array of names.

• Use advanced vocabulary and professional tone for other sections.

• Ensure factual accuracy and cite examples or case studies wherever applicable.

• Divide the response into clear, labeled sections corresponding to the structure above.

• Use varied formats (paragraphs, points, subheadings) randomly within each section.

• Aim for maximum token utilization by elaborating extensively and ensuring the response is informative and engaging.
  """

    if model=="sonar-pro" or "sonar-reasoning-pro":
          response = self._make_request(user_message,model, structure, max_tokens=8000, temperature=0.2)
    else:
         response = self._make_request(user_message,model, structure, max_tokens=60000, temperature=0.2)
    perplexity_end_time = time.time()  # End time logging
    perplexity_runtime = round(perplexity_end_time - perplexity_start_time, 2)  # Calculate execution time
    logger.info(f"Perplexity Execution completed in {perplexity_runtime} seconds.")
    return self._process_response(response)
  

  def _process_response(self,response):
  try:
  for choice in response.get("choices", []):
  content = choice.get("message", {}).get("content", "")

            # Attempt to extract JSON part using regex
            match = re.search(r'\{.*\}', content, re.DOTALL)
  
            if match:
                json_string = match.group()
                
                # Try parsing the JSON string into a dictionary
                data = json.loads(json_string)
  
                # Remove text before "## Introduction ##"
                modified_string = re.sub(r'^.*?(## Introduction)', r'\1', content, flags=re.DOTALL)
                
                # Update the content in the choice
                choice["message"]["content"] = modified_string
                # Log the final result
                logger.info("Perplexity Response  Extracted Data:")
                logger.info({
                    "short_description": data['short_description'],
                    "entities": data['entities'],
                    "remaining_content": response
                })
                return {
                    "short_description": data['short_description'],
                    "entities": data['entities'],
                    "remaining_content": response
                }
    except Exception as e:
            logger.info(f"Error processing response: {e}")
            return {
                "short_description": "",
                "entities": [],
                "remaining_content": response
            }
  

`