Update main.py

main.py

@@ -1,11 +1,123 @@
-# main.py
+# # main.py
+# from fastapi import FastAPI, HTTPException
+# from pydantic import BaseModel
+# from typing import Dict
+# import os
+# from groq import Groq
+
+# app = FastAPI()
+
+# # Pydantic model for request
+# class ScoreInput(BaseModel):
+#     score_percentages: Dict[str, float]
+#     time_percentages: Dict[str, float]
+
+# # Helper functions
+# def get_final_score(score_percentages: Dict[str, float], time_percentages: Dict[str, float]) -> Dict[str, float]:
+#     final_score = {}
+#     for skill in score_percentages:
+#         score_avg = (score_percentages[skill] + time_percentages[skill]) / 2
+#         final_score[skill] = score_avg
+#     return final_score
+
+# def get_strengths_and_weaknesses(final_score: Dict[str, float]):
+#     sorted_skills = sorted(
+#         [(skill, score) for skill, score in final_score.items()],
+#         key=lambda item: item[1],
+#         reverse=True
+#     )
+#     num_skills = len(sorted_skills)
+#     if num_skills == 0:
+#         return [], [], []
+    
+#     split1 = num_skills // 3
+#     split2 = 2 * (num_skills // 3)
+    
+#     strengths = sorted_skills[:split1]
+#     opportunities = sorted_skills[split1:split2]
+#     challenges = sorted_skills[split2:]
+    
+#     return strengths, opportunities, challenges
+
+# # FastAPI route
+# @app.post("/analyze")
+# async def analyze_scores(input_data: ScoreInput):
+#     final_score = get_final_score(input_data.score_percentages, input_data.time_percentages)
+#     strengths, opportunities, challenges = get_strengths_and_weaknesses(final_score)
+
+#     # Groq API call
+#     api_key = os.getenv("GROQ_API_KEY")
+#     if not api_key:
+#         raise HTTPException(status_code=500, detail="Groq API key not found")
+
+#     client = Groq(api_key=api_key)
+#     sys_prompt = f"""You are an advanced language model trained to analyze student responses from a questionnaire on Academic, Cognitive, and Study Profile aspects related to JEE Mains preparation. Your task is to generate a personalized SCO (Strengths, Challenges, Opportunities) analysis and an Action Plan section based on the user's inputs.
+#     You have been provided with the strengths {strengths}, Opportunities {opportunities} and Challenges {challenges} skills of the user
+#     Output Structure:
+#     SCO Analysis:
+#     Strengths:
+#     - List the student's strengths based on their {strengths} skills
+#     - Let the student now how they can use these strengths in their JEE preparation and exam to improve their score.
+#     - Also tell them how do they improve their score more.
+#     Opportunities:
+#     - List the student's strengths based on their {opportunities} skills
+#     - Suggest opportunities for improvement by leveraging the student's strengths and addressing their challenges.
+#     - Recommend ways to enhance their score in the {opportunities} skills.
+#     - Also tell them if they improve in these skills what opportunities they have in improving their scores
+#     Challenges:
+#     - List the student's strengths based on their {challenges} skills
+#     - Guide the student that these skills are basically the core area where they are lacking
+#     - Tell them that if they continue not focusing upon them they might get far away from their JEE goal.
+#     Action Plan:
+#     - Provide a detailed plan to the student to improve in the {challenges} skills.
+#     - Recommend targeted strategies, resources, and techniques to improve their {challenges} skills.
+#     - Let them know if they improve these areas how it can help boost their scores and make their preparation more effective.
+#     - Incorporate time management, revision, and test-taking strategies specific to JEE Mains and the identified subjects/topics/subtopics.
+
+#     Things that LLM need to make sure:
+#     1) Your analysis and action plan should be comprehensive, consistent, and tailored to the individual student's responses while leveraging your knowledge of the JEE Mains exam context, the mapping of subjects/topics to general cognitive traits and skills, and the ability to identify overarching trends across related subjects/topics.
+#     2) Make sure you give the output that extracts the student.
+#     3) Make sure you give out output in bullet points.
+#     4) While entering a new line in the output use "\n" new line character.
+#     5) Make the output very much JEE (Joint Entrance Examination) based and give everything with context to Physics , Chemistry and Maths JEE syllabus.
+#     6) Use Italics, Bold and underline appropriately to improve the output more.
+#     7) Bold text where you are taking chapter names from Physics , Chemsitry and Maths only which are in syllabus of Joint Entrance Examination.
+#     8) Dont use "+" or any other special symbol whenever you want to break a line use "\n" to do it in the output.
+#     """
+    
+
+#     try:
+#         chat_completion = client.chat.completions.create(
+#             messages=[
+#                 {"role": "system", "content": sys_prompt},
+#                 {"role": "user", "content": f"Generate the SOCA analysis based on the system prompt and {strengths}, {opportunities} and {challenges}. MAKE SURE WE STRICTLY FOLLOW THE STRUCTURE."},
+#             ],
+#             model="llama3-70b-8192",
+#         )
+#         analysis = chat_completion.choices[0].message.content
+#     except Exception as e:
+#         raise HTTPException(status_code=500, detail=f"Error calling Groq API: {str(e)}")
+
+#     return {"analysis": analysis}
+
+# if __name__ == "__main__":
+#     import uvicorn
+#     uvicorn.run(app, host="0.0.0.0", port=8000)
+
+
+
+
+# Merger of SOCA v1 and SOCA v2
+from embedchain import App
 from fastapi import FastAPI, HTTPException
+from mangum import Mangum
 from pydantic import BaseModel
 from typing import Dict
 import os
 from groq import Groq
 
 app = FastAPI()
+handler = Mangum(app)
 
 # Pydantic model for request
 class ScoreInput(BaseModel):
@@ -46,11 +158,11 @@ async def analyze_scores(input_data: ScoreInput):
     strengths, opportunities, challenges = get_strengths_and_weaknesses(final_score)
 
     # Groq API call
-    api_key = os.getenv("GROQ_API_KEY")
+    api_key2 = os.getenv("GROQ_API_KEY")
     if not api_key:
         raise HTTPException(status_code=500, detail="Groq API key not found")
 
-    client = Groq(api_key=api_key)
+    client2 = Groq(api_key=api_key2)
     sys_prompt = f"""You are an advanced language model trained to analyze student responses from a questionnaire on Academic, Cognitive, and Study Profile aspects related to JEE Mains preparation. Your task is to generate a personalized SCO (Strengths, Challenges, Opportunities) analysis and an Action Plan section based on the user's inputs.
     You have been provided with the strengths {strengths}, Opportunities {opportunities} and Challenges {challenges} skills of the user
     Output Structure:
@@ -87,7 +199,7 @@ async def analyze_scores(input_data: ScoreInput):
     
 
     try:
-        chat_completion = client.chat.completions.create(
+        chat_completion = client2.chat.completions.create(
             messages=[
                 {"role": "system", "content": sys_prompt},
                 {"role": "user", "content": f"Generate the SOCA analysis based on the system prompt and {strengths}, {opportunities} and {challenges}. MAKE SURE WE STRICTLY FOLLOW THE STRUCTURE."},