app.py

from io import BytesIO
from dotenv import load_dotenv
import os
from utils import google_search,split_text_into_chunks,insert_embeddings_into_pinecone_database,query_vector_database,generate_embedding_for_user_resume,delete_vector_namespace,create_user,login_user
from fastapi import FastAPI, File, UploadFile
from fastapi.responses import JSONResponse
import docx
import fitz
from scraper import scrapeCourse
import asyncio
from google import genai 
from pydantic import BaseModel
load_dotenv()

CX = os.getenv("SEARCH_ENGINE_ID")
API_KEY = os.getenv("GOOGLE_API_KEY")
PINECONE_API_KEY=os.getenv("PINECONE_API_KEY")
GEMINI_API_KEY=os.getenv("GEMINI_API_KEY")
MONGO_URI=os.getenv("MONGO_URI")
app = FastAPI()

import re

class UserBody(BaseModel):
    Email:str
    Password:str
    
class AiAnalysis(BaseModel):
    UserId:str
    Query:str

class UserCourse(BaseModel):
    EmploymentStatus:str
    InterimRole:str
    DesiredRole:str
    Motivation:str
    LearningPreference:str
    HoursSpentLearning:str
    Challenges:str
    TimeframeToAchieveDreamRole:str
    userId:str


class CourseRecommendation(BaseModel):
    CourseName: str
    CompletionTime: str

def extract_course_info(text: str) -> CourseRecommendation:
    # Example regex patterns – adjust these as needed based on the response format.
    course_pattern =r'"coursename":\s*"([^"]+)"'
    time_pattern = r"(\d+\s*-\s*\d+\s*months)"

    course_match = re.search(course_pattern, text)
    time_match = re.search(time_pattern, text)

    coursename = course_match.group(1).strip() if course_match else "Unknown"
    completiontime = time_match.group(0).strip() if time_match else "Unknown"

    return CourseRecommendation(CourseName=coursename, CompletionTime=completiontime)




@app.get("/get/course")
def get_course(query):
# Example search query
    results = google_search(query, API_KEY, CX)
    content=[]
   
    if results:
        for item in results.get('items', []):
            title = item.get('title')
            link = item.get('link')
            snippet = item.get('snippet')
            content_structure={}
            
            content_structure["Course_Title"]=title
            content_structure["Course_Link"]=link
            content_structure["Course_Snippet"]= snippet
            content_structure["Scraped_Course_Details"]= scrapeCourse(url=link)
            content.append(content_structure)
        
    
    return JSONResponse(content,status_code=200) 
            



def get_course_func(query):
# Example search query
    results = google_search(query, API_KEY, CX)
    content=[]
   
    if results:
        for item in results.get('items', []):
            title = item.get('title')
            link = item.get('link')
            snippet = item.get('snippet')
            content_structure={}
            content_structure["Course_Title"]=title
            content_structure["Course_Link"]=link
            content_structure["Course_Snippet"]= snippet
            content_structure["Scraped_Course_Details"]= scrapeCourse(url=link)
            content.append(content_structure)
        
    
    return content
            






@app.post("/upload")
async def upload_file(user_id,file: UploadFile = File(...)):
    content = await file.read()  # Read the file content (this will return bytes)
    sentences=[]

    print(f"File name: {file.filename}")
    print(f"File content type: {file.content_type}")
    print(f"File size: {file.size} bytes")
    
    
    if "pdf" == file.filename.split('.')[1]:
        pdf_document = fitz.open(stream=BytesIO(content), filetype="pdf")
        extracted_text = ""
        for page_num in range(pdf_document.page_count):
            page = pdf_document.load_page(page_num)
            extracted_text += page.get_text()
            
    elif "docx" == file.filename.split('.')[1]:
        docx_file = BytesIO(content)
        doc = docx.Document(docx_file)
        extracted_text = ""
        for para in doc.paragraphs:
            extracted_text += para.text + "\n"
            
    sentences = split_text_into_chunks(extracted_text,chunk_size=200)
    docs = generate_embedding_for_user_resume(data=sentences,user_id=file.filename)
    response= insert_embeddings_into_pinecone_database(doc=docs,api_key=PINECONE_API_KEY,name_space=user_id)
    
    return {"filename": file.filename,"response":str(response) }    



@app.post("/ask")
def ask_ai_about_resume(req:AiAnalysis):
    # Retrieve context from your vector database
    context = query_vector_database(query=req.Query, api_key=PINECONE_API_KEY, name_space=req.UserId)
    
    # Ensure that an event loop is present in this thread.
    try:
        loop = asyncio.get_event_loop()
    except RuntimeError:
        loop = asyncio.new_event_loop()
        asyncio.set_event_loop(loop)
    
    # Create the Gemini client after the event loop is set up
    client = genai.Client(api_key=GEMINI_API_KEY)
    
    response = client.models.generate_content(
        model="gemini-2.0-flash", 
        contents=f"""
        Answer this question using the context provided:
        question: {req.Query}
        context: {context}
        """
    )
    
    return {"Ai_Response":response.text}

@app.post("/recommend/courses")
def ask_ai_about_resume(request:UserCourse):
    """
User Profile Information for Career Development

This section defines the parameters used to gather information from the user to understand their current employment situation, learning preferences, challenges, and goals related to achieving their dream role.

Parameters:

    employment_status (str): 
        A description of the user's current employment situation (e.g., "unemployed", "part-time", "full-time").
    
    interim_role (str): 
        Indicates whether the user is willing to prepare for an interim role to gain experience and income while pursuing their dream role (e.g., "yes" or "no").
    
    desired_role (str): 
        The role the user ultimately wishes to obtain (e.g., "Full-Stack Developer", "Data Scientist").
    
    motivation (str): 
        The user's reasons or motivations for pursuing the desired role.
    
    learning_preference (str): 
        Describes how the user prefers to learn new skills (e.g., "online courses", "self-study", "bootcamp").
    
    hours_spent_learning (str or int): 
        The number of hours per day the user can dedicate to learning.
    
    challenges (str): 
        Outlines any obstacles or challenges the user faces in reaching their dream role.
    
    timeframe_to_achieve_dream_role (str): 
        The ideal timeframe the user has in mind for achieving their dream role (e.g., "6-12 months").
    
    user_id (str): 
        A unique identifier for the user; used to query personalized data from a vector database or other services.

    """
    

    # Retrieve context from your vector database
    
    # Ensure that an event loop is present in this thread.
    try:
        loop = asyncio.get_event_loop()
    except RuntimeError:
        loop = asyncio.new_event_loop()
        asyncio.set_event_loop(loop)
    
    # Create the Gemini client after the event loop is set up
    client = genai.Client(api_key=GEMINI_API_KEY)
    
    response = client.models.generate_content(
        model="gemini-2.0-flash", 
        contents=f"""
        please respond with a JSON object that contains the following keys as a response:
        - "coursename": the name of the recommended course,
        - "completiontime": an estimate of how long it would take to complete the course.
        Do not include any extra text.
        Recommend a course using this information below :
        Which of the following best describes you?: {request.EmploymentStatus}
        Would you like to prepare for an interim role to gain experience and income while pursuing your dream job?: {request.InterimRole}
        What is your desired role?: {request.DesiredRole}
        Why do you want to achieve this desired role?: {request.Motivation}
        How do you prefer to learn new skills?: {request.LearningPreference}
        How many hours per day can you dedicate to learning?: {request.HoursSpentLearning}
        What are the biggest challenges or obstacles you face in reaching your dream role?: {request.Challenges}
        What is your ideal timeframe for achieving your dream role?: {request.TimeframeToAchieveDreamRole}
        
    
        """
    )
    course_info = extract_course_info(response.text)
    courses = get_course_func(query=course_info.CourseName)
    return {"CourseInfo":course_info,"Courses":courses}



@app.post("/login")
def login(user:UserBody):
    user ={"email":user.Email,"password":user.Password}
    user_id= login_user(db_uri=MONGO_URI,db_name="crayonics",collection_name="users",document=user)
    return {"user_id":user_id}


@app.post("/signup")
def signUp(user:UserBody):
    user ={"email":user.Email,"password":user.Password}
    user_id= create_user(db_uri=MONGO_URI,db_name="crayonics",collection_name="users",document=user)
    return {"user_id":user_id}