Update app.py

app.py

@@ -1,4 +1,5 @@
-# Deploys the LangGraph agent with a feature-rich Gradio UI on Hugging Face Spaces.
+# === FINAL PRODUCTION-READY APP (v2): ADVANCED CAREER NAVIGATOR ===
+# Corrected version with updated imports for PyPDF2 and Pydantic.
 
 # 1. IMPORTS AND SETUP
 import os
@@ -8,21 +9,16 @@ from typing import TypedDict, List, Optional
 from langchain_openai import ChatOpenAI
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.tools import tool
-from langchain_core.pydantic_v1 import BaseModel, Field
+from pydantic import BaseModel, Field # CORRECTED LINE: Import directly from Pydantic
 from langgraph.graph import StateGraph, END
 import requests
 from bs4 import BeautifulSoup
-from PyPDF2 import PdfReader
+from pypdf import PdfReader # CORRECTED LINE: Import from 'pypdf' instead of 'PyPDF2'
 from threading import Thread
 
-# Import the stream_executor to allow the UI to update progressively
-from langchain.callbacks.base import BaseCallbackHandler
-from langchain_core.runnables import RunnableConfig
-
 print("--- Libraries imported. ---")
 
-# IMPORTANT: Set your API keys in the Hugging Face Space "Secrets"
-# The names should be OPENAI_API_KEY, LANGCHAIN_API_KEY, and TAVILY_API_KEY
+# Set API keys from Hugging Face Space Secrets
 os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
 os.environ["LANGCHAIN_API_KEY"] = os.getenv("LANGCHAIN_API_KEY")
 os.environ["TAVILY_API_KEY"] = os.getenv("TAVILY_API_KEY")
@@ -32,7 +28,6 @@ os.environ["LANGCHAIN_PROJECT"] = "Deployed Career Navigator"
 
 # 2. LANGGRAPH AGENT BACKEND (The "Brain" of the App)
 
-# Pydantic Models for structured data
 class SkillAnalysis(BaseModel):
     technical_skills: List[str] = Field(description="List of top 5 technical skills.")
     soft_skills: List[str] = Field(description="List of top 3 soft skills.")
@@ -49,7 +44,6 @@ class CareerActionPlan(BaseModel):
     learning_roadmap: str = Field(description="Markdown-formatted learning plan.")
     portfolio_plan: str = Field(description="Markdown-formatted portfolio project plan.")
 
-# Agent State
 class TeamState(TypedDict):
     student_interests: str
     student_resume: str
@@ -59,7 +53,6 @@ class TeamState(TypedDict):
     resume_analysis: Optional[ResumeFeedback]
     final_plan: Optional[CareerActionPlan]
 
-# Tools
 @tool
 def scrape_web_content(url: str) -> str:
     """Scrapes text content from a URL."""
@@ -70,11 +63,9 @@ def scrape_web_content(url: str) -> str:
     except requests.RequestException:
         return "Error: Could not scrape the URL."
 
-# Specialist Agents
 llm = ChatOpenAI(model="gpt-4o", temperature=0)
 
 def job_market_analyst_agent(state: TeamState):
-    # This is a simplified version for faster UI response. A full version would be more robust.
     print("--- 🕵️ Agent: Job Market Analyst ---")
     structured_llm = llm.with_structured_output(SkillAnalysis)
     prompt = ChatPromptTemplate.from_template(
@@ -116,7 +107,6 @@ def lead_agent_node(state: TeamState):
     })
     return {"final_plan": final_plan}
 
-# Graph Definition
 graph_builder = StateGraph(TeamState)
 graph_builder.add_node("analyze_market", job_market_analyst_agent)
 graph_builder.add_node("review_resume", resume_reviewer_agent)
@@ -131,31 +121,40 @@ print("--- LangGraph Agent Backend is ready. ---")
 
 
 # 3. HELPER FUNCTIONS FOR GRADIO
-def extract_text_from_pdf(pdf_file):
-    """Extracts text from an uploaded PDF file."""
-    if not pdf_file:
-        return ""
-    reader = PdfReader(pdf_file.name)
-    text = ""
-    for page in reader.pages:
-        text += page.extract_text() or ""
-    return text
-
-def run_agent_process(resume_text, chosen_career, progress=gr.Progress(track_tqdm=True)):
-    """The main function to run the agent and yield updates for the UI."""
-    initial_state = {
-        "student_resume": resume_text,
-        "chosen_career": chosen_career,
+def extract_text_from_pdf(pdf_file_obj):
+    if not pdf_file_obj:
+        return "", "Please upload a resume to begin."
+    try:
+        reader = PdfReader(pdf_file_obj.name)
+        text = "".join(page.extract_text() or "" for page in reader.pages)
+        if not text.strip():
+            return "", "Error: Could not extract text from the PDF. Please try a different file."
+        return text, ""
+    except Exception as e:
+        return "", f"An error occurred while reading the PDF: {e}"
+
+
+def run_agent_and_update_ui(resume_text, chosen_career):
+    if not resume_text:
+        return {
+            output_col: gr.update(visible=True),
+            output_overview: gr.update(value="<h3 style='color:red;'>Please upload a resume first.</h3>", visible=True)
+        }
+        
+    yield {
+        output_col: gr.update(visible=True),
+        input_row: gr.update(visible=False),
+        output_overview: gr.update(value="### 🧠 The AI agent team is analyzing your profile...", visible=True)
     }
-    
-    # Use a thread to run the agent so the UI doesn't block
+
+    initial_state = { "student_resume": resume_text, "chosen_career": chosen_career }
     final_state = navigator_agent.invoke(initial_state)
     plan = final_state['final_plan']
-    
-    return {
-        # Update UI components with the final plan
+
+    # Final update
+    yield {
         output_plan_state: plan,
-        output_overview: gr.update(value=f"## 1. Career Overview: {plan.career_overview}", visible=True),
+        output_overview: gr.update(value=f"## 1. Career Overview: {plan.career_overview}"),
         output_skills: gr.update(
             value=f"## 2. Job Market Skill Analysis\n**Top Technical Skills:** {', '.join(plan.skill_analysis.technical_skills)}\n\n**Top Soft Skills:** {', '.join(plan.skill_analysis.soft_skills)}",
             visible=True
@@ -166,54 +165,45 @@ def run_agent_process(resume_text, chosen_career, progress=gr.Progress(track_tqd
         ),
         output_learning_plan: gr.update(value=f"## 4. Your 8-Week Learning Roadmap\n{plan.learning_roadmap}", visible=True),
         output_portfolio_plan: gr.update(value=f"## 5. Your Portfolio Project Plan\n{plan.portfolio_plan}", visible=True),
-        # Hide the input section and show the output/chat sections
-        input_row: gr.update(visible=False),
         chat_row: gr.update(visible=True)
     }
 
 def chat_with_agent(message, history, plan_state):
-    """Handles the follow-up conversation with the agent."""
     if not plan_state:
-        return "Please generate a plan first."
-
+        return "An error occurred. Please generate a new plan."
+    
     prompt = ChatPromptTemplate.from_messages([
-        ("system", "You are a helpful career coach. The user has just received the following career action plan. Answer their follow-up questions based on this plan.\n\n--- CAREER PLAN ---\n{plan_text}"),
-        ("human", "{user_question}")
+        ("system", "You are a helpful career coach. The user has just received the following career action plan. Answer their follow-up questions based ONLY on this plan.\n\n--- CAREER PLAN ---\n{plan_text}"),
+        ("user", "{user_question}")
     ])
-    
     chat_chain = prompt | llm
     
-    # Convert Pydantic model to a string for the context
     plan_text = f"Career: {plan_state.career_overview}\nSkills: {plan_state.skill_analysis.dict()}\nResume Feedback: {plan_state.resume_feedback.dict()}\nLearning Plan: {plan_state.learning_roadmap}\nPortfolio Plan: {plan_state.portfolio_plan}"
     
-    response = chat_chain.invoke({
-        "plan_text": plan_text,
-        "user_question": message
-    })
-    
+    response = chat_chain.invoke({"plan_text": plan_text, "user_question": message})
     return response.content
 
 
 # 4. GRADIO UI DEFINITION
-with gr.Blocks(theme=gr.themes.Soft(), css=".gradio-container {background-color: #f0f4f9;}") as demo:
-    # State object to hold the final plan for the chat
+with gr.Blocks(theme=gr.themes.Soft(), css="footer {visibility: hidden}") as demo:
     output_plan_state = gr.State()
-
+    resume_text_state = gr.State()
+    error_text_state = gr.State()
+    
     gr.Markdown("# 🚀 Your AI Career Navigator")
     gr.Markdown("Upload your resume, select a target career, and get a personalized, data-driven action plan from a team of AI agents.")
 
-    # Page 1: Input Section
     with gr.Row(visible=True) as input_row:
-        with gr.Column(scale=1):
+        with gr.Column(scale=2):
             input_pdf_resume = gr.File(label="Upload Your Resume (PDF)", file_types=[".pdf"])
             input_career_choice = gr.Dropdown(
                 label="Select Your Target Career",
                 choices=["Data Analyst", "Software Engineer", "Product Manager", "UX Designer", "AI/ML Engineer"],
                 value="Data Analyst"
             )
-            submit_button = gr.Button("Generate My Action Plan", variant="primary")
-    
-    # Page 2: Output Section (initially hidden)
+        with gr.Column(scale=1, min_width=200):
+            submit_button = gr.Button("Generate My Action Plan", variant="primary", scale=2)
+
     with gr.Column(visible=False) as output_col:
         output_overview = gr.Markdown(visible=False)
         output_skills = gr.Markdown(visible=False)
@@ -221,24 +211,25 @@ with gr.Blocks(theme=gr.themes.Soft(), css=".gradio-container {background-color:
         output_learning_plan = gr.Markdown(visible=False)
         output_portfolio_plan = gr.Markdown(visible=False)
 
-    # Page 2: Chat Section (initially hidden)
     with gr.Row(visible=False) as chat_row:
          chat_interface = gr.ChatInterface(
             chat_with_agent,
-            chatbot=gr.Chatbot(height=400),
+            chatbot=gr.Chatbot(height=500, label="Chat with your Career Coach"),
             additional_inputs=[output_plan_state],
             title="Ask Follow-up Questions",
             description="Ask any questions about your generated plan."
         )
 
-    # Event Handling
-    submit_button.click(
+    # Event Handling Logic
+    input_pdf_resume.upload(
         fn=extract_text_from_pdf,
         inputs=[input_pdf_resume],
-        outputs=None # We will use the result in the next step
-    ).then(
-        fn=run_agent_process,
-        inputs=[lambda *args: args[0], input_career_choice],
+        outputs=[resume_text_state, error_text_state]
+    )
+    
+    submit_button.click(
+        fn=run_agent_and_update_ui,
+        inputs=[resume_text_state, input_career_choice],
         outputs=[
             output_plan_state,
             output_overview,
@@ -247,10 +238,10 @@ with gr.Blocks(theme=gr.themes.Soft(), css=".gradio-container {background-color:
             output_learning_plan,
             output_portfolio_plan,
             input_row,
+            output_col,
             chat_row
         ]
     )
 
-# Launch the app
 if __name__ == "__main__":
     demo.launch(debug=True)