from langchain_groq import ChatGroq import json import streamlit as st import requests from bs4 import BeautifulSoup from utils import embedding_model, get_pinecone_index, save_application # ---------- Groq LLM ---------- llm = ChatGroq( model="llama-3.3-70b-versatile", temperature=0.3, groq_api_key=st.secrets["GROQ_API_KEY"] ) class ProfileParserAgent: def run(self, resume_text): prompt = f"""Extract structured candidate profile. Return JSON: {{ "full_name": "...", "skills": ["skill1", "skill2"], "experience_years": number, "education": "degree", "certifications": [...] }} Resume: {resume_text} """ resp = llm.invoke(prompt) try: return json.loads(resp.content) except: return {"full_name": "Candidate", "skills": ["Python", "AI"], "experience_years": 2, "education": "BSc CS", "certifications": []} class JobSearchAgent: def run(self, job_titles, locations): """ Real-time job search: 1. Try SERP API if API key exists 2. Fallback to free job APIs (Arbeitnow, RemoteOK) 3. Final fallback to mock data """ jobs = [] serp_key = st.secrets.get("SERPAPI_API_KEY", None) # Option 1: Use SERP API if serp_key: try: for title in job_titles: params = { "api_key": serp_key, "engine": "google_jobs", "q": title, "location": locations[0] if locations else "Remote" } response = requests.get("https://serpapi.com/search", params=params) data = response.json() if "jobs_results" in data: for job in data["jobs_results"]: jobs.append({ "title": job.get("title", title), "company": job.get("company_name", "Unknown"), "location": job.get("location", "Remote"), "description": job.get("description", "No description"), "url": job.get("link", "#") }) except Exception as e: st.warning(f"SERP API failed: {e}. Trying free APIs...") # Option 2: Free APIs (if no SERP or SERP failed) if not jobs: # Arbeitnow API try: resp = requests.get("https://arbeitnow.com/api/job-board-api", timeout=10) if resp.status_code == 200: data = resp.json() for job in data.get("data", []): if any(t.lower() in job.get("title", "").lower() for t in job_titles): jobs.append({ "title": job.get("title", ""), "company": job.get("company", ""), "location": job.get("location", "Remote"), "description": job.get("description", ""), "url": job.get("url", "#") }) except: pass # RemoteOK API (if needed) if len(jobs) < 3: try: resp = requests.get("https://remoteok.com/api", timeout=10) if resp.status_code == 200: data = resp.json() for job in data[:20]: if any(t.lower() in job.get("position", "").lower() for t in job_titles): jobs.append({ "title": job.get("position", ""), "company": job.get("company", ""), "location": "Remote", "description": job.get("description", ""), "url": job.get("url", "#") }) except: pass # Option 3: Mock data (final fallback) if not jobs: mock_jobs = [ {"title": "AI Engineer", "company": "HuggingFace", "location": "Remote", "description": "Build AI agents using Transformers, LangChain, Groq. Requires Python, LLMs.", "url": "https://huggingface.co/jobs"}, {"title": "Machine Learning Engineer", "company": "Google", "location": "Remote", "description": "LLM fine-tuning, deployment. Python, TensorFlow.", "url": "https://careers.google.com"}, {"title": "Data Scientist", "company": "Amazon", "location": "Remote", "description": "NLP, transformers, AWS.", "url": "https://amazon.jobs"} ] jobs = mock_jobs return jobs[:10] # limit to 10 jobs class EmbeddingGenerator: def generate(self, text): return embedding_model.encode(text).tolist() class VectorDBStorage: def __init__(self): self.index = get_pinecone_index() def store_jobs(self, jobs): vectors = [] for i, job in enumerate(jobs): job_text = f"{job['title']} {job['company']} {job['description']}" vec = embedding_model.encode(job_text).tolist() vectors.append((f"job_{i}", vec, {"title": job['title'], "company": job['company'], "description": job['description'], "url": job['url']})) self.index.upsert(vectors=vectors) def search(self, query_vec, top_k=5): results = self.index.query(vector=query_vec, top_k=top_k, include_metadata=True) return results['matches'] class MatchingRankingAgent: def run(self, candidate_profile, jobs_with_metadata): profile_text = f"Skills: {', '.join(candidate_profile.get('skills',[]))}. Experience: {candidate_profile.get('experience_years',0)} years." profile_vec = embedding_model.encode(profile_text).tolist() vdb = VectorDBStorage() vdb.store_jobs(jobs_with_metadata) matches = vdb.search(profile_vec, top_k=len(jobs_with_metadata)) ranked = [] for m in matches: ranked.append({ "job": m['metadata'], "score": m['score'] * 100, "match_percent": round(m['score']*100, 1) }) ranked.sort(key=lambda x: x['score'], reverse=True) return ranked class CompanyResearchAgent: def run(self, company_name): prompt = f"Provide a concise summary of company '{company_name}': culture, tech stack, mission. Keep 80 words." resp = llm.invoke(prompt) return resp.content class ResumeTailoringAgent: def run(self, original_resume_text, job_description, job_title): prompt = f"""Tailor the following resume to the job: {job_title}. Job description: {job_description} Original resume: {original_resume_text} Output a revised resume (text format) highlighting relevant skills and achievements.""" resp = llm.invoke(prompt) return resp.content class CoverLetterAgent: def run(self, candidate_name, job_title, company_name, job_description, skills): prompt = f"""Write a professional cover letter for {candidate_name} applying to {job_title} at {company_name}. Skills: {', '.join(skills)}. Job description: {job_description} Letter should be 150 words.""" resp = llm.invoke(prompt) return resp.content class ApplicationAgent: def run(self, job_url, tailored_resume, cover_letter): # Simulated submission – in production, use browser automation return {"status": "simulated_submitted", "submission_id": "hf_demo"} class InterviewPrepAgent: def run(self, job_title, job_description, company_name): prompt = f"""Generate 5 likely interview questions and suggested answers for a {job_title} role at {company_name}. Job description: {job_description} Format: Q1: ... A1: ...""" resp = llm.invoke(prompt) return resp.content class NotificationAgent: def run(self, message, channel="ui"): st.info(f"📢 {message}") return f"Sent: {message}" class AnalyticsAgent: def run(self): from utils import get_metrics df = get_metrics() if df.empty: return {"total_applications": 0, "avg_match_score": 0, "submitted_count": 0} total = len(df) avg_score = df['match_score'].mean() submitted = len(df[df['status']=='simulated_submitted']) return {"total_applications": total, "avg_match_score": avg_score, "submitted_count": submitted}