added questions generator

src/services/questions_generator.py

@@ -0,0 +1,66 @@
+import os
+import json
+from openai import OpenAI
+from pydantic import BaseModel, Field
+from typing import List, Dict, Optional
+from src.prompts.sops import *
+from src.models.questions_response import *
+from src.services.sop_document_parser import DocumentParser
+from src.prompts.questions import get_questions_prompt
+from dotenv import load_dotenv
+load_dotenv()
+
+class QuestionsGenerator:
+    def __init__(self):
+        self.api_key = os.getenv("OPENAI_API_KEY")
+        self.client = OpenAI(api_key=self.api_key)
+        self.model = "gpt-4o-mini"
+    
+    def generate_questions(self, input_data):
+        try:
+            sops = input_data['sops']
+            assessment_type = input_data['assessment_type']
+            frequency_type = input_data['frequency_type']
+            total_duration = input_data['duration']
+            
+            # Chunk the SOPs into smaller pieces
+            chunk_size = 1000  # Define your chunk size
+            docs_text = [sops[i:i + chunk_size] for i in range(0, len(sops), chunk_size)]
+            # Create a list of documents
+            docs = [{"type": "text", "text": text} for text in docs_text]
+
+            prompt = get_questions_prompt()  # Get the questions prompt for the SOP
+
+            all_questions = []
+
+            # Iterate through each frequency number (e.g., week 1, week 2, etc.)
+            for frequency_number in range(1, total_duration + 1):
+                frequency_label = f"{frequency_type} {frequency_number}"  # e.g., week 1, daily 3
+
+                # Generate questions for the current frequency number
+                response = self.client.beta.chat.completions.parse(
+                    model=self.model,
+                    messages=[
+                        {"role": "system", "content": prompt},
+                        {"role": "user", "content": f"The SOPs are provided below."},
+                        {"role": "user", "content": docs},  # Use the chunked documents
+                        {"role": "user", "content": f"Assessment Type: {assessment_type}"},
+                        {"role": "user", "content": f"Frequency Type: {frequency_type}"},
+                        {"role": "user", "content": f"Current Frequency Number to generate : {frequency_label}"},
+                        {"role": "user", "content": f"Duration: {total_duration}"}
+                    ],
+                    response_format=AssementQuestion,  # Use the updated response schema
+                    max_tokens=4096,
+                    temperature=0.1
+                )
+                
+                questions = json.loads(response.choices[0].message.content)
+                all_questions.append({
+                    "frequency_number": frequency_label,
+                    "questions": questions
+                })
+            
+            return all_questions
+        
+        except json.JSONDecodeError:
+            return False