import sqlite3 import pandas as pd import pdfplumber from sentence_transformers import SentenceTransformer from pinecone import Pinecone, ServerlessSpec import streamlit as st # ---------- Embedding Model ---------- @st.cache_resource def get_embedding_model(): return SentenceTransformer('all-MiniLM-L6-v2') embedding_model = get_embedding_model() # ---------- Pinecone Setup ---------- PINECONE_API_KEY = st.secrets["PINECONE_API_KEY"] PINECONE_INDEX_NAME = st.secrets.get("PINECONE_INDEX_NAME", "job-hunt-index") @st.cache_resource def get_pinecone_index(): pc = Pinecone(api_key=PINECONE_API_KEY) index_name = PINECONE_INDEX_NAME if index_name not in pc.list_indexes().names(): pc.create_index( name=index_name, dimension=384, metric="cosine", spec=ServerlessSpec(cloud="aws", region="us-east-1") ) return pc.Index(index_name) # ---------- PDF Extraction ---------- def extract_text_from_pdf(pdf_file): text = "" with pdfplumber.open(pdf_file) as pdf: for page in pdf.pages: text += page.extract_text() or "" return text # ---------- SQLite ---------- DB_PATH = "/tmp/applications.db" def init_db(): conn = sqlite3.connect(DB_PATH) c = conn.cursor() c.execute('''CREATE TABLE IF NOT EXISTS applications (id INTEGER PRIMARY KEY, job_title TEXT, company TEXT, match_score REAL, status TEXT, tailored_resume_path TEXT, cover_letter_path TEXT)''') conn.commit() conn.close() def save_application(job_title, company, match_score, status, tailored_path="", cover_path=""): conn = sqlite3.connect(DB_PATH) c = conn.cursor() c.execute("INSERT INTO applications (job_title, company, match_score, status, tailored_resume_path, cover_letter_path) VALUES (?,?,?,?,?,?)", (job_title, company, match_score, status, tailored_path, cover_path)) conn.commit() conn.close() def get_metrics(): conn = sqlite3.connect(DB_PATH) df = pd.read_sql_query("SELECT * FROM applications", conn) conn.close() return df