job_recommendation_Chat_Bot/main.py
2025-02-28 11:49:03 +05:30

105 lines
4.3 KiB
Python

import streamlit as st
import faiss
import numpy as np
import os
import pandas as pd
from dotenv import load_dotenv
from sentence_transformers import SentenceTransformer
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings
from groq import Groq
class JobRecommender:
def __init__(self, data_path: str, faiss_index_path: str, embeddings_path: str):
"""Initialize the job recommender system."""
load_dotenv()
self.client = Groq(api_key=os.getenv("GROQ_API_KEY"))
self.embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
self.data_path = data_path
self.faiss_index_path = faiss_index_path
self.embeddings_path = embeddings_path
self.df = self._load_data()
self.faiss_index, self.job_metadata = self._load_or_build_faiss_index()
def _load_data(self):
"""Load job data from CSV."""
df = pd.read_csv(self.data_path).head(5000)
return df
def _load_or_build_faiss_index(self):
"""Load precomputed FAISS index or build it if it doesn't exist."""
if os.path.exists(self.faiss_index_path) and os.path.exists(self.embeddings_path):
print("Loading precomputed FAISS index and embeddings.")
faiss_index = faiss.read_index(self.faiss_index_path)
job_embeddings = np.load(self.embeddings_path)
job_metadata = {i: self.df.iloc[i].to_dict() for i in range(len(self.df))}
else:
print("Building FAISS index and embeddings.")
job_texts = self.df.apply(lambda row: f"{row['Job Title']} - {row['Job Description']}", axis=1).tolist()
job_embeddings = self.embedding_model.embed_documents(job_texts)
dimension = len(job_embeddings[0])
faiss_index = faiss.IndexFlatL2(dimension)
faiss_index.add(np.array(job_embeddings))
# Save the FAISS index and embeddings
faiss.write_index(faiss_index, self.faiss_index_path)
np.save(self.embeddings_path, np.array(job_embeddings))
job_metadata = {i: self.df.iloc[i].to_dict() for i in range(len(self.df))}
return faiss_index, job_metadata
def find_similar_jobs(self, query: str, top_k=3):
"""Retrieve similar jobs using FAISS."""
query_embedding = np.array([self.embedding_model.embed_query(query)])
distances, indices = self.faiss_index.search(query_embedding, top_k)
return [self.job_metadata[idx] for idx in indices[0]]
def generate_response(self, user_query: str):
"""Generate AI-powered job recommendations using Groq API."""
jobs = self.find_similar_jobs(user_query)
if not jobs:
return "No matching jobs found."
job_details = "\n".join([f"{job['Job Title']}: {job['Job Description']}" for job in jobs])
prompt = f"""
You are a job recommendation assistant. A user is looking for a job related to: {user_query}.
Here are some recommended jobs:
{job_details}
Provide a detailed recommendation with insights on why these jobs are relevant.
"""
completion = self.client.chat.completions.create(
model="mixtral-8x7b-32768",
messages=[{"role": "user", "content": prompt}],
temperature=1,
max_tokens=1024,
top_p=1,
stream=True,
)
response_text = "".join(chunk.choices[0].delta.content or "" for chunk in completion)
return response_text
# Streamlit UI
def main():
st.title("💼 Job Recommendation Chatbot")
st.write("Enter your job preferences below, and the AI will suggest relevant jobs!")
recommender = JobRecommender(
data_path="job_desc.csv",
faiss_index_path="faiss_index.index",
embeddings_path="job_embeddings.npy"
)
user_input = st.text_input("Enter job title, skills, or interests:", "")
if st.button("Find Jobs"):
if user_input:
response = recommender.generate_response(user_input)
st.subheader("📌 Job Recommendations")
st.write(response)
else:
st.warning("Please enter a job-related query.")
if __name__ == "__main__":
main()