Upload 4 files

groq_client.py

@@ -0,0 +1,78 @@
+from groq import Groq
+from typing import List, Dict
+
+client = Groq()
+
+async def generate_questions(career: str, qualifications: str) -> Dict:
+    # Use JSON mode to ensure we get structured data
+    system_prompt = (
+        "You are a helpful assistant that generates a JSON object containing 5 psychological questions as an array of objects."
+         "Each object has a question string and four choices labeled A, B, C, D."
+          "The questions should assess capability for the career as per the qualification"
+           "and should be psychological not anyhting related to the career . Respond ONLY with valid JSON."
+            " The question should be understandable by the qualifications."
+             " It should always follow the json schema."
+              "{ \"$schema\": \"http://json-schema.org/draft-07/schema#\", \"$id\": \"http://example.com/schemas/questions.schema.json\", \"title\": \"Questions Schema\", \"description\": \"A schema describing a list of questions and their choices.\", \"type\": \"object\", \"properties\": { \"questions\": { \"type\": \"array\", \"description\": \"An array of questions.\", \"items\": { \"type\": \"object\", \"properties\": { \"question\": { \"type\": \"string\", \"description\": \"The text of the question.\" }, \"choices\": { \"type\": \"object\", \"description\": \"An object containing multiple choice options.\", \"properties\": { \"A\": { \"type\": \"string\", \"description\": \"Option A answer text.\" }, \"B\": { \"type\": \"string\", \"description\": \"Option B answer text.\" }, \"C\": { \"type\": \"string\", \"description\": \"Option C answer text.\" }, \"D\": { \"type\": \"string\", \"description\": \"Option D answer text.\" } }, \"required\": [\"A\", \"B\", \"C\", \"D\"] } }, \"required\": [\"question\", \"choices\"] } } }, \"required\": [\"questions\"] } "
+    )
+
+    response = client.chat.completions.create(
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {
+                "role": "user", 
+                "content": f"Career: {career}\nQualifications: {qualifications}\n"
+                           f"Generate 5 psychological questions to determine if capable. make the question understable as per the qualification"
+            }
+        ],
+        model="llama-3.3-70b-versatile",
+        temperature=0.5,
+        max_tokens=1024,
+        top_p=1,
+        stop=None,
+        stream=False,
+        response_format={"type": "json_object"}  # Ensures JSON response
+    )
+    print(response.choices[0].message.content)
+    return response.choices[0].message.content
+
+async def evaluate_answers(career: str, qualifications: str, answers: Dict[str, str]) -> Dict:
+    # answers is a dict mapping question_index to chosen answer, e.g. {"0": "A", "1": "C", ...}
+    
+
+    system_prompt = (
+       "You are a helpful assistant. You receive a career, qualifications, and "
+    "user answers to previously generated psychological questions. Your primary goal is to assess "
+    "the user's psychological readiness for the career based on their answers. If psychologically capable, "
+    "provide a roadmap tailored to their current qualifications and stage in life to help them achieve the career. "
+    "If they are not psychologically ready, explain the challenges they might face and suggest alternative careers "
+    "aligned with their strengths, along with motivational guidance."
+    "career options and provide motivation."
+        "in a structured JSON: { 'capable': true, 'roadmap':  ['Step 1: Gain experience', 'Step 2: Apply for jobs'], }. If not capable, "
+        "suggest alternative careers: { 'capable': false, 'alternatives': [list_of_careers...] }."
+        "and also details evaluation report as statement and also provide some motivation even if capability is false"
+        "Respond ONLY with valid JSON.with following json schema"
+        '{"$schema": "http://json-schema.org/draft-04/schema#", "type": "object", "properties": {"capable": {"type": "boolean"}, "alternatives": {"type": "array", "items": [{"type": "string"}, {"type": "string"}, {"type": "string"}]}, "roadmap": {"type": "array", "items": [{"type": "string"}, {"type": "string"}]}, "evaluation_report": {"type": "string"}, "motivation": {"type": "string"}}, "required": ["capable", "alternatives", "roadmap", "evaluation_report", "motivation"]}'
+
+    )
+
+    user_input = {
+        "career": career,
+        "qualifications": qualifications,
+        "answers": answers
+    }
+    print(answers)
+    response = client.chat.completions.create(
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": f"evaluation should be based on answers {answers} not by qualifications {qualifications} and guide them to achive that as per the qualifations {qualifications} to achieve {career}"}
+        ],
+        model="llama-3.3-70b-versatile",
+        temperature=0.5,
+        max_tokens=1024,
+        top_p=1,
+        stop=None,
+        stream=False,
+        response_format={"type": "json_object"}  # Ensures JSON response
+    )
+    print(response.choices[0].message.content)
+    return response.choices[0].message.content

main.py

@@ -0,0 +1,43 @@
+from fastapi import FastAPI, Form, Request
+from fastapi.responses import JSONResponse, FileResponse
+from fastapi.staticfiles import StaticFiles
+from starlette.middleware.sessions import SessionMiddleware
+from groq_client import generate_questions, evaluate_answers
+import json
+import uvicorn
+
+app = FastAPI()
+
+# Serve static files (HTML, CSS, JS)
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+# Add session middleware
+app.add_middleware(SessionMiddleware, secret_key="vhjh64@$t4#$%yhgxt45ljo##")
+
+
+@app.get("/", response_class=FileResponse)
+async def index():
+    return FileResponse("static/index.html")
+
+
+@app.post("/start", response_class=JSONResponse)
+async def start(career: str = Form(...), qualifications: str = Form(...)):
+    # Mock question generation
+    questions_str = await generate_questions(career, qualifications)
+    questions_data = json.loads(questions_str)
+    return {"questions": questions_data["questions"]}
+
+
+@app.post("/evaluate", response_class=JSONResponse)
+async def evaluate(payload: dict):
+    # Mock evaluation logic
+    career = payload.get("career")
+    qualifications = payload.get("qualifications")
+    answers = payload.get("answers")
+    result = await evaluate_answers(career, qualifications, answers)
+    result_data=json.loads(result)
+    return {"result": result_data}
+
+
+if __name__ == "__main__":
+    uvicorn.run("main:app", host="0.0.0.0", port=8000, reload=True)

models.py

@@ -0,0 +1,9 @@
+from pydantic import BaseModel
+from typing import Dict, List
+
+class UserInput(BaseModel):
+    career: str
+    qualifications: str
+
+class UserAnswers(BaseModel):
+    answers: Dict[int, str]

requirements.txt

@@ -0,0 +1,10 @@
+fastapi==0.103.2
+uvicorn==0.22.0
+jinja2==3.1.2
+groq==0.13.0
+python-dotenv==1.0.0 
+requests==2.31.0     
+itsdangerous==2.1.2
+aiofiles==23.1.0
+python-multipart==0.0.19
+uvicorn