Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 import os
+import re
 from openai import OpenAI
 
 client = OpenAI(
@@ -7,74 +8,146 @@ client = OpenAI(
     api_key=os.environ.get("Rejected_tk"),
 )
 
+# ---------- FILE READING ----------
+def read_file(file):
+    if file is None:
+        return ""
+    path = file.name if hasattr(file, "name") else file
+    try:
+        if path.lower().endswith(".pdf"):
+            from pypdf import PdfReader
+            reader = PdfReader(path)
+            return "\n".join((p.extract_text() or "") for p in reader.pages)
+        elif path.lower().endswith(".docx"):
+            import docx
+            d = docx.Document(path)
+            return "\n".join(p.text for p in d.paragraphs)
+        else:
+            with open(path, "r", encoding="utf-8", errors="ignore") as f:
+                return f.read()
+    except Exception as e:
+        return f"[Could not read file: {e}]"
+
+# ---------- DETERMINISTIC KEYWORD ENGINE ----------
+# Curated tech/skill vocabulary — deterministic, no LLM hallucination
+SKILL_VOCAB = [
+    "python","java","go","golang","rust","c++","scala","javascript","typescript","sql",
+    "kubernetes","docker","mlflow","airflow","spark","kafka","hadoop","terraform","jenkins",
+    "aws","gcp","azure","sagemaker","vertex ai","ec2","s3","lambda","bigquery",
+    "pytorch","tensorflow","keras","scikit-learn","sklearn","jax","onnx","tensorrt",
+    "horovod","deepspeed","ray","distributed training","quantization","fine-tuning",
+    "nlp","bert","transformers","llm","huggingface","computer vision","cnn","rnn","gan",
+    "pandas","numpy","data pipeline","etl","feature engineering","ci/cd","mlops","devops",
+    "rest api","grpc","microservices","redis","postgresql","mongodb","elasticsearch",
+    "git","linux","bash","unit testing","system design","production deployment","monitoring",
+]
+
+def extract_skills(text):
+    text_low = text.lower()
+    found = set()
+    for skill in SKILL_VOCAB:
+        if re.search(r"\b" + re.escape(skill) + r"\b", text_low):
+            found.add(skill)
+    return found
+
+def keyword_analysis(resume_text, jd_text):
+    resume_skills = extract_skills(resume_text)
+    jd_skills = extract_skills(jd_text)
+    matched = sorted(jd_skills & resume_skills)
+    missing = sorted(jd_skills - resume_skills)
+    match_pct = int(100 * len(matched) / len(jd_skills)) if jd_skills else 0
+    return matched, missing, match_pct, sorted(resume_skills), sorted(jd_skills)
+
+# ---------- LLM PROMPTS ----------
 SYSTEM_PROMPT = """You are a brutally honest but helpful senior hiring manager with 15 years of experience.
-Your job is to tell candidates EXACTLY why they will be rejected — not a vague match score, but a specific, actionable rejection explanation.
+Tell candidates EXACTLY why they will be rejected — a specific, actionable diagnosis, not a vague match score.
 
-You must output your response in this exact structure:
+Output in this exact structure:
 
 ## ❌ Why You Will Likely Be Rejected
 [2-3 specific, direct sentences about the core mismatch]
 
 ## 🔍 Top 3 Skill Gaps
-1. [Gap 1 — specific technology or skill missing]
-2. [Gap 2]
-3. [Gap 3]
+1. [Gap — specific technology]
+2. [Gap]
+3. [Gap]
 
-## 📂 Missing Projects/Experience
-- [What kind of project would fill this gap]
+## 📂 Missing Projects To Build
+- [Project that would fill the biggest gap]
 - [Another project]
 - [Another project]
 
-## 🔑 Missing Keywords (for ATS systems)
-[comma-separated list of keywords from the job description not present in the resume]
-
 ## 📅 30-Day Improvement Plan
 **Week 1:** [Specific action]
 **Week 2:** [Specific action]
 **Week 3:** [Specific action]
-**Week 4:** [Specific action — ideally a project to show]
+**Week 4:** [Specific action — a portfolio project]
 
-## 💡 One Honest Verdict
-[One sentence: should they apply now, in 3 months, or pivot entirely?]
+## 💡 Honest Verdict
+[One sentence: apply now, wait 3 months, or pivot?]
 
 Be specific. Name actual technologies. Do not be vague."""
 
+BULLET_PROMPT = """You are an expert resume writer. Given the candidate's gaps and the target role, write exactly 3 strong, quantified resume bullet points the candidate could truthfully add AFTER building the recommended projects. Each bullet starts with a strong action verb and includes a metric. Output only the 3 bullets, nothing else."""
 
-def analyze(resume_text, job_description):
-    if not resume_text.strip() or not job_description.strip():
-        return "⚠️ Please paste both your resume and the job description."
-    try:
-        response = client.chat.completions.create(
-            model="meta-llama/Llama-3.1-8B-Instruct",
-            messages=[
-                {"role": "system", "content": SYSTEM_PROMPT},
-                {"role": "user", "content": f"Resume:\n{resume_text}\n\nJob Description:\n{job_description}\n\nGive the full rejection report."}
-            ],
-            max_tokens=1024,
-            temperature=0.7,
-        )
-        return response.choices[0].message.content
-    except Exception as e:
-        return f"❌ Error: {str(e)}"
+def call_llm(system, user):
+    response = client.chat.completions.create(
+        model="meta-llama/Llama-3.1-8B-Instruct",
+        messages=[{"role": "system", "content": system}, {"role": "user", "content": user}],
+        max_tokens=1024, temperature=0.7,
+    )
+    return response.choices[0].message.content
+
+# ---------- MAIN PIPELINE ----------
+def analyze(resume_text, resume_file, jd_text, jd_file):
+    # File upload overrides text box if a file is provided
+    resume = read_file(resume_file) if resume_file else resume_text
+    jd = read_file(jd_file) if jd_file else jd_text
+
+    if not resume.strip() or not jd.strip():
+        return "⚠️ Please provide both a resume and a job description (paste or upload).", ""
+
+    # 1. Deterministic keyword engine
+    matched, missing, match_pct, resume_skills, jd_skills = keyword_analysis(resume, jd)
+
+    evidence = f"""## 📊 Evidence-Based Match Analysis
+
+**🎯 Skill Match Score: {match_pct}%**
+
+**✅ Skills found in BOTH resume & JD ({len(matched)}):**
+{', '.join(matched) if matched else 'None — major mismatch'}
 
+**❌ Required skills MISSING from your resume ({len(missing)}):**
+{', '.join(missing) if missing else 'None — strong overlap!'}
 
+---
+"""
+
+    # 2. LLM rejection report
+    user_msg = f"Resume:\n{resume}\n\nJob Description:\n{jd}\n\nDETERMINISTIC ANALYSIS — Missing skills: {', '.join(missing)}. Match score: {match_pct}%.\n\nGive the full rejection report grounded in these missing skills."
+    report = call_llm(SYSTEM_PROMPT, user_msg)
+
+    # 3. Resume bullet generator
+    bullet_msg = f"Target role skills missing: {', '.join(missing)}. Candidate background: {resume[:600]}. Write the 3 bullets."
+    bullets = call_llm(BULLET_PROMPT, bullet_msg)
+    bullets_section = f"\n\n---\n## ✍️ 'Fix My Resume' — 3 Bullets To Add After Building These Projects\n\n{bullets}"
+
+    return evidence + report, bullets_section
+
+# ---------- EXAMPLES ----------
 EXAMPLE_RESUME = """Name: Priya Sharma
 Education: M.S. Computer Science, 2024
-
 Skills: Python, PyTorch, NLP, Transformers, BERT fine-tuning, HuggingFace, scikit-learn, pandas, numpy
-
 Projects:
 - Sentiment analysis model on Twitter data using BERT
 - Named Entity Recognition system for biomedical text
 - Research paper: "Improving low-resource NER with cross-lingual transfer"
-
 Experience:
 - ML Research Intern, university NLP lab (6 months)
 - TA for Introduction to Machine Learning course"""
 
 EXAMPLE_JD = """Senior ML Engineer — Infrastructure
 Company: CloudScale Inc.
-
 Requirements:
 - 3+ years deploying ML models at scale in production
 - Strong knowledge of Kubernetes, Docker, MLflow
@@ -100,22 +173,28 @@ with gr.Blocks(title="Rejected Before Applying", css=css) as demo:
     <div id='title-block'>
         <h1>💔 Rejected Before Applying</h1>
         <p>Find out <b>exactly why</b> your resume won't make it — before you waste the application.</p>
-        <p style='color:#666; font-size:0.85em;'>⚡ Powered by Llama-3.1-8B &nbsp;•&nbsp; 🔒 No data stored &nbsp;•&nbsp; 🎯 Brutal honesty guaranteed</p>
+        <p style='color:#666; font-size:0.85em;'>📊 Evidence-based keyword engine + AI hiring manager &nbsp;•&nbsp; 🔒 No data stored</p>
     </div>
     """)
 
     with gr.Row(equal_height=True):
         with gr.Column():
-            resume_input = gr.Textbox(label="📄 Your Resume", placeholder="Paste your resume here...", lines=16, value=EXAMPLE_RESUME)
+            gr.HTML("<b style='color:#ccc;'>📄 Your Resume</b>")
+            resume_input = gr.Textbox(label="Paste resume text", lines=12, value=EXAMPLE_RESUME)
+            resume_file = gr.File(label="...or upload (PDF / DOCX / TXT)", file_types=[".pdf", ".docx", ".txt"])
         with gr.Column():
-            jd_input = gr.Textbox(label="💼 Job Description", placeholder="Paste the full job description here...", lines=16, value=EXAMPLE_JD)
+            gr.HTML("<b style='color:#ccc;'>💼 Job Description</b>")
+            jd_input = gr.Textbox(label="Paste JD text", lines=12, value=EXAMPLE_JD)
+            jd_file = gr.File(label="...or upload (PDF / DOCX / TXT)", file_types=[".pdf", ".docx", ".txt"])
 
     analyze_btn = gr.Button("🔍  Analyse My Rejection", variant="primary", size="lg")
-    gr.HTML("<div style='margin:10px 0 6px 0; color:#888; font-size:0.85em; text-align:center;'>⏳ Analysis takes ~15 seconds — hang tight</div>")
-    output = gr.Markdown(value="*Your rejection report will appear here...*")
+    gr.HTML("<div style='margin:10px 0; color:#888; font-size:0.85em; text-align:center;'>⏳ Takes ~20 seconds — runs a keyword engine + 2 AI passes</div>")
+
+    output = gr.Markdown(value="*Your evidence-based rejection report will appear here...*")
+    bullets_out = gr.Markdown()
 
-    analyze_btn.click(fn=analyze, inputs=[resume_input, jd_input], outputs=output)
+    analyze_btn.click(fn=analyze, inputs=[resume_input, resume_file, jd_input, jd_file], outputs=[output, bullets_out])
 
-    gr.HTML("<div style='text-align:center; margin-top:24px; color:#555; font-size:0.82em;'>Built for the 🤗 <b>Build Small Hackathon</b> &nbsp;•&nbsp; Small model, real talk</div>")
+    gr.HTML("<div style='text-align:center; margin-top:24px; color:#555; font-size:0.82em;'>Built for the 🤗 <b>Build Small Hackathon</b> &nbsp;•&nbsp; Engineered pipeline, not just a prompt</div>")
 
 demo.launch()